Is Agile Failing in the Age of AI?
Published:
Agile transformed software development by adapting to changing requirements. But what happens when AI dramatically reduces the cost of implementation? Are we still optimizing for the right bottleneck?
Posts by Tags
agile
agile software development
Is Agile Failing in the Age of AI?
Published:
Agile transformed software development by adapting to changing requirements. But what happens when AI dramatically reduces the cost of implementation? Are we still optimizing for the right bottleneck?
ai
MS-SBN, Part 3: My Ten-Year-Old Built a Video Game From Four-Word Prompts
Published:
I typed two sentences into a coding agent, asked it to write a plan, and handed the laptop to my ten-year-old son. Over four weeks Mathai built a real, playable 2D game without writing a line of code. It was a deliberate experiment: proof that when every step has to verify it works, the software keeps working — whoever is driving. That is the core of Mission-Driven Engineering.
MS-SBN, Part 2: Amy Turned a High-School Dream Into a Website
Published:
Amy Givens owned the MyAmy Designs domain since high school, but the website stayed a dream for years. With ChatGPT and Codex, she finally turned that domain into a real business website for MyAmy Designs & Remodeling.
Modern Software for Small Businesses and Nonprofits, Part 1: The Website Is Becoming the Software
Published:
AI agents and inexpensive hosted services are making the old static-versus-dynamic website distinction less important for small businesses and nonprofits. A website can now become the first useful custom workflow.
From Code Generation to Application Generation, Part 8: If Agents Are Doing the Coding, What Am I Doing?
Published:
If coding agents handle more implementation, the human role does not disappear. It moves toward mission, judgment, validation, integration, accountability, and helping more organizations use software well.
From Code Generation to Application Generation, Part 7: How Mission-Driven Engineering Happened
Published:
Mission-Driven Engineering did not start as a framework. It started when I realized I was using coding agents to manage UI screens, data layers, and implementation artifacts instead of asking them to satisfy the outcome I actually cared about.
From Code Generation to Application Generation, Part 6: Inside Mission-Driven Engineering
Published:
A practical walk-through of Mission-Driven Engineering: how missions, validations, generations, learning loops, and shared MDE memory turn AI coding agents into application-generation systems.
From Code Generation to Application Generation, Part 5: Why I Ended Up Looking Back at Model-Driven Engineering
Published:
AI application generation feels new, but it echoes Model-Driven Engineering: humans describe intent, machines generate implementation, and independent validation decides whether the result actually works.
From Code Generation to Application Generation, Part 4: My Coding Agents Are Productive. I Am Exhausted.
Published:
AI coding agents can make implementation dramatically faster, but they also create a new bottleneck: the human cost of managing context, attention, and learning across many parallel projects.
The End of Software Scarcity, Part 4: Rosa’s Story — Lead Workflow
Published:
A website is only the front door. In this article, I explore how an AI-enabled conversation becomes part of a small operations system for leads, clients, jobs, reviews, videos, and ads.
From Code Generation to Application Generation, Part 3: Why I Stopped Looking at Generated Code
Published:
As AI coding agents improved, the generated code became less interesting than the final application outcome. The question shifted from whether the code looked right to whether the application solved the problem.
From Code Generation to Application Generation, Part 2: I Knew How to Fix It, But Wasn’t Sure You Wanted It Fixed
Published:
Most of my interaction with coding agents became copying error messages from build systems and asking the agent to fix them. That raised an uncomfortable question: why was I in the loop at all?
From Code Generation to Application Generation, Part 1: When Does the Agent Stop?
Published:
I initially trusted AI through code generation because code could be validated. What surprised me was discovering that the hardest problem was no longer implementation, but defining when the work was actually complete.
The End of Software Scarcity, Part 3: Rosa’s Story — Website & AI Chat
Published:
Building the website was easy. The more interesting question was whether a small business could afford an AI-powered customer experience with virtually no recurring software costs.
Is Agile Failing in the Age of AI?
Published:
Agile transformed software development by adapting to changing requirements. But what happens when AI dramatically reduces the cost of implementation? Are we still optimizing for the right bottleneck?
AI Doesn’t Have a Coding Problem. Enterprises Have a Permission Problem.
Published:
What if the biggest obstacle to AI transformation isn’t the technology, but the way we’ve organized our companies?
The End of Software Scarcity, Part 2: Rosa’s Story
Published:
In my previous article, I argued that AI-assisted development may be bringing an end to software scarcity. This article tests that idea through a real-world project with a local small business owner.
The End of Software Scarcity, Part 1: Why Software Can Adapt to the Business
Published:
For decades, organizations adapted themselves to software because software was expensive to build and maintain. AI-assisted development may reverse that relationship, making it practical for software to adapt to the unique needs of individual organizations.
Artificial Intelligent Retail Search is here!-In Progress
Published:
In this article, I explore the evolution of retail search and attempt to predict the future of retail search
Artificial Intelligent Retail Search is here! (2) - The Data Science Era
Published:
Moving beyond simple keyword matching. How the industry transitioned to hybrid systems, query understanding, and the “Builder’s Era” of search relevance.
Artificial Intelligent Retail Search is here! (1) - The Legacy & The Problem
Published:
A look back at the “Black Box” era of retail search, why we moved away from it, and the fundamental tension between finding products and making money.
ai agents
SLAB-RS, Part 7: The Textbook Wins the Benchmark, and Loses the Trade
Published:
Retail is the first dataset in the project with real graded labels — so it is the first place the classical retail-search toolkit gets a fair audition. Field weighting stayed dormant. Learning-to-rank finally woke up, and then relearned the hybrid it was supposed to beat. The full textbook cascade won the benchmark — by +0.13% over the lean stack that was already shipped. Measure everything, ship almost nothing.
SLAB-RS, Part 6: The Agent Meets a Million Real Products
Published:
Five parts of a retail search series, and the documents were never products. Phase 3 changes that: 1.2 million real Amazon products, graded Exact/Substitute/Complement/Irrelevant labels, and one question — does the academic stack survive contact with real retail? It does. The BGE hybrid lands at parity with the published single-model baseline, at production latency, and int8 quantization makes a live million-vector index fit on a free-tier box, losslessly.
SLAB-RS, Part 5: How the Agents Discovered Hybrid Search
Published:
The agents took their Phase 1 wins to fifteen new domains — and discovered hybrid search: the one method that improved every single one, by up to 64%. The keyword tricks that looked brilliant on aeronautics turned out to be aeronautics-shaped, and even the cleverest ranker got demoted by Occam’s razor.
SLAB-RS, Interlude: Why the Agent Is Not in a Store Yet
Published:
Four articles into a series called retail search and there is not a single product — only aeronautics abstracts. Here is the map: what BEIR is, why the same BM25 scores 0.158 on one dataset and 0.789 on another, why I was wrong to call Phase 2 a filter, and what has to happen before the agent reaches real products.
SLAB-RS, Part 4: The Agent Breaks Its Ceiling with Embeddings
Published:
Embeddings from a chat model scored five times worse than random vectors. A purpose-built retrieval model beat the keyword ceiling by 8.4%. The agent’s three embedding attempts, a machine-learned ranking detour, and a live OpenSearch vector index.
SLAB-RS, Part 3: The Agent Climbs Keyword Search to Its Ceiling
Published:
An AI agent ran five ranking experiments on a live OpenSearch baseline in six days — work that would have taken a core search team months. This article shows the process, the failures, and how a rarely-shipped old technique won the keyword round.
Self-Learning Agent-Based Retail Search, Part 2: The Baseline Before the Agents
Published:
Before search agents tune anything, the system needs a measurable baseline. This article shows Phase 1 of the project: an out-of-box OpenSearch BM25 baseline on Cranfield, the live relevance numbers, and the failures agents will need to improve.
Self-Learning Agent-Based Retail Search, Part 1: Why Retail Search Is Harder Than It Looks
Published:
Retail search is not just about returning relevant products. The hard part is deciding which relevant product should come first when customer needs, business goals, inventory, promotions, trust, and mobile behavior all compete.
Modern Software for Small Businesses and Nonprofits, Part 1: The Website Is Becoming the Software
Published:
AI agents and inexpensive hosted services are making the old static-versus-dynamic website distinction less important for small businesses and nonprofits. A website can now become the first useful custom workflow.
From Code Generation to Application Generation, Part 8: If Agents Are Doing the Coding, What Am I Doing?
Published:
If coding agents handle more implementation, the human role does not disappear. It moves toward mission, judgment, validation, integration, accountability, and helping more organizations use software well.
From Code Generation to Application Generation, Part 7: How Mission-Driven Engineering Happened
Published:
Mission-Driven Engineering did not start as a framework. It started when I realized I was using coding agents to manage UI screens, data layers, and implementation artifacts instead of asking them to satisfy the outcome I actually cared about.
From Code Generation to Application Generation, Part 6: Inside Mission-Driven Engineering
Published:
A practical walk-through of Mission-Driven Engineering: how missions, validations, generations, learning loops, and shared MDE memory turn AI coding agents into application-generation systems.
From Code Generation to Application Generation, Part 5: Why I Ended Up Looking Back at Model-Driven Engineering
Published:
AI application generation feels new, but it echoes Model-Driven Engineering: humans describe intent, machines generate implementation, and independent validation decides whether the result actually works.
From Code Generation to Application Generation, Part 4: My Coding Agents Are Productive. I Am Exhausted.
Published:
AI coding agents can make implementation dramatically faster, but they also create a new bottleneck: the human cost of managing context, attention, and learning across many parallel projects.
From Code Generation to Application Generation, Part 3: Why I Stopped Looking at Generated Code
Published:
As AI coding agents improved, the generated code became less interesting than the final application outcome. The question shifted from whether the code looked right to whether the application solved the problem.
From Code Generation to Application Generation, Part 2: I Knew How to Fix It, But Wasn’t Sure You Wanted It Fixed
Published:
Most of my interaction with coding agents became copying error messages from build systems and asking the agent to fix them. That raised an uncomfortable question: why was I in the loop at all?
From Code Generation to Application Generation, Part 1: When Does the Agent Stop?
Published:
I initially trusted AI through code generation because code could be validated. What surprised me was discovering that the hardest problem was no longer implementation, but defining when the work was actually complete.
ai chat
The End of Software Scarcity, Part 3: Rosa’s Story — Website & AI Chat
Published:
Building the website was easy. The more interesting question was whether a small business could afford an AI-powered customer experience with virtually no recurring software costs.
ai search
Artificial Intelligent Retail Search is here!-In Progress
Published:
In this article, I explore the evolution of retail search and attempt to predict the future of retail search
ai transformation
AI Doesn’t Have a Coding Problem. Enterprises Have a Permission Problem.
Published:
What if the biggest obstacle to AI transformation isn’t the technology, but the way we’ve organized our companies?
ai-assisted development
MS-SBN, Part 3: My Ten-Year-Old Built a Video Game From Four-Word Prompts
Published:
I typed two sentences into a coding agent, asked it to write a plan, and handed the laptop to my ten-year-old son. Over four weeks Mathai built a real, playable 2D game without writing a line of code. It was a deliberate experiment: proof that when every step has to verify it works, the software keeps working — whoever is driving. That is the core of Mission-Driven Engineering.
MS-SBN, Part 2: Amy Turned a High-School Dream Into a Website
Published:
Amy Givens owned the MyAmy Designs domain since high school, but the website stayed a dream for years. With ChatGPT and Codex, she finally turned that domain into a real business website for MyAmy Designs & Remodeling.
From Code Generation to Application Generation, Part 8: If Agents Are Doing the Coding, What Am I Doing?
Published:
If coding agents handle more implementation, the human role does not disappear. It moves toward mission, judgment, validation, integration, accountability, and helping more organizations use software well.
From Code Generation to Application Generation, Part 7: How Mission-Driven Engineering Happened
Published:
Mission-Driven Engineering did not start as a framework. It started when I realized I was using coding agents to manage UI screens, data layers, and implementation artifacts instead of asking them to satisfy the outcome I actually cared about.
From Code Generation to Application Generation, Part 6: Inside Mission-Driven Engineering
Published:
A practical walk-through of Mission-Driven Engineering: how missions, validations, generations, learning loops, and shared MDE memory turn AI coding agents into application-generation systems.
From Code Generation to Application Generation, Part 5: Why I Ended Up Looking Back at Model-Driven Engineering
Published:
AI application generation feels new, but it echoes Model-Driven Engineering: humans describe intent, machines generate implementation, and independent validation decides whether the result actually works.
From Code Generation to Application Generation, Part 4: My Coding Agents Are Productive. I Am Exhausted.
Published:
AI coding agents can make implementation dramatically faster, but they also create a new bottleneck: the human cost of managing context, attention, and learning across many parallel projects.
The End of Software Scarcity, Part 4: Rosa’s Story — Lead Workflow
Published:
A website is only the front door. In this article, I explore how an AI-enabled conversation becomes part of a small operations system for leads, clients, jobs, reviews, videos, and ads.
From Code Generation to Application Generation, Part 3: Why I Stopped Looking at Generated Code
Published:
As AI coding agents improved, the generated code became less interesting than the final application outcome. The question shifted from whether the code looked right to whether the application solved the problem.
From Code Generation to Application Generation, Part 2: I Knew How to Fix It, But Wasn’t Sure You Wanted It Fixed
Published:
Most of my interaction with coding agents became copying error messages from build systems and asking the agent to fix them. That raised an uncomfortable question: why was I in the loop at all?
From Code Generation to Application Generation, Part 1: When Does the Agent Stop?
Published:
I initially trusted AI through code generation because code could be validated. What surprised me was discovering that the hardest problem was no longer implementation, but defining when the work was actually complete.
The End of Software Scarcity, Part 3: Rosa’s Story — Website & AI Chat
Published:
Building the website was easy. The more interesting question was whether a small business could afford an AI-powered customer experience with virtually no recurring software costs.
Is Agile Failing in the Age of AI?
Published:
Agile transformed software development by adapting to changing requirements. But what happens when AI dramatically reduces the cost of implementation? Are we still optimizing for the right bottleneck?
The End of Software Scarcity, Part 2: Rosa’s Story
Published:
In my previous article, I argued that AI-assisted development may be bringing an end to software scarcity. This article tests that idea through a real-world project with a local small business owner.
The End of Software Scarcity, Part 1: Why Software Can Adapt to the Business
Published:
For decades, organizations adapted themselves to software because software was expensive to build and maintain. AI-assisted development may reverse that relationship, making it practical for software to adapt to the unique needs of individual organizations.
amazon esci
SLAB-RS, Part 7: The Textbook Wins the Benchmark, and Loses the Trade
Published:
Retail is the first dataset in the project with real graded labels — so it is the first place the classical retail-search toolkit gets a fair audition. Field weighting stayed dormant. Learning-to-rank finally woke up, and then relearned the hybrid it was supposed to beat. The full textbook cascade won the benchmark — by +0.13% over the lean stack that was already shipped. Measure everything, ship almost nothing.
SLAB-RS, Part 6: The Agent Meets a Million Real Products
Published:
Five parts of a retail search series, and the documents were never products. Phase 3 changes that: 1.2 million real Amazon products, graded Exact/Substitute/Complement/Irrelevant labels, and one question — does the academic stack survive contact with real retail? It does. The BGE hybrid lands at parity with the published single-model baseline, at production latency, and int8 quantization makes a live million-vector index fit on a free-tier box, losslessly.
application generation
Modern Software for Small Businesses and Nonprofits, Part 1: The Website Is Becoming the Software
Published:
AI agents and inexpensive hosted services are making the old static-versus-dynamic website distinction less important for small businesses and nonprofits. A website can now become the first useful custom workflow.
From Code Generation to Application Generation, Part 8: If Agents Are Doing the Coding, What Am I Doing?
Published:
If coding agents handle more implementation, the human role does not disappear. It moves toward mission, judgment, validation, integration, accountability, and helping more organizations use software well.
From Code Generation to Application Generation, Part 7: How Mission-Driven Engineering Happened
Published:
Mission-Driven Engineering did not start as a framework. It started when I realized I was using coding agents to manage UI screens, data layers, and implementation artifacts instead of asking them to satisfy the outcome I actually cared about.
From Code Generation to Application Generation, Part 6: Inside Mission-Driven Engineering
Published:
A practical walk-through of Mission-Driven Engineering: how missions, validations, generations, learning loops, and shared MDE memory turn AI coding agents into application-generation systems.
From Code Generation to Application Generation, Part 5: Why I Ended Up Looking Back at Model-Driven Engineering
Published:
AI application generation feels new, but it echoes Model-Driven Engineering: humans describe intent, machines generate implementation, and independent validation decides whether the result actually works.
From Code Generation to Application Generation, Part 4: My Coding Agents Are Productive. I Am Exhausted.
Published:
AI coding agents can make implementation dramatically faster, but they also create a new bottleneck: the human cost of managing context, attention, and learning across many parallel projects.
From Code Generation to Application Generation, Part 3: Why I Stopped Looking at Generated Code
Published:
As AI coding agents improved, the generated code became less interesting than the final application outcome. The question shifted from whether the code looked right to whether the application solved the problem.
From Code Generation to Application Generation, Part 2: I Knew How to Fix It, But Wasn’t Sure You Wanted It Fixed
Published:
Most of my interaction with coding agents became copying error messages from build systems and asking the agent to fix them. That raised an uncomfortable question: why was I in the loop at all?
From Code Generation to Application Generation, Part 1: When Does the Agent Stop?
Published:
I initially trusted AI through code generation because code could be validated. What surprised me was discovering that the hardest problem was no longer implementation, but defining when the work was actually complete.
beir
SLAB-RS, Part 5: How the Agents Discovered Hybrid Search
Published:
The agents took their Phase 1 wins to fifteen new domains — and discovered hybrid search: the one method that improved every single one, by up to 64%. The keyword tricks that looked brilliant on aeronautics turned out to be aeronautics-shaped, and even the cleverest ranker got demoted by Occam’s razor.
SLAB-RS, Interlude: Why the Agent Is Not in a Store Yet
Published:
Four articles into a series called retail search and there is not a single product — only aeronautics abstracts. Here is the map: what BEIR is, why the same BM25 scores 0.158 on one dataset and 0.789 on another, why I was wrong to call Phase 2 a filter, and what has to happen before the agent reaches real products.
benchmarks
SLAB-RS, Interlude: Why the Agent Is Not in a Store Yet
Published:
Four articles into a series called retail search and there is not a single product — only aeronautics abstracts. Here is the map: what BEIR is, why the same BM25 scores 0.158 on one dataset and 0.789 on another, why I was wrong to call Phase 2 a filter, and what has to happen before the agent reaches real products.
bm25
SLAB-RS, Interlude: Why the Agent Is Not in a Store Yet
Published:
Four articles into a series called retail search and there is not a single product — only aeronautics abstracts. Here is the map: what BEIR is, why the same BM25 scores 0.158 on one dataset and 0.789 on another, why I was wrong to call Phase 2 a filter, and what has to happen before the agent reaches real products.
SLAB-RS, Part 3: The Agent Climbs Keyword Search to Its Ceiling
Published:
An AI agent ran five ranking experiments on a live OpenSearch baseline in six days — work that would have taken a core search team months. This article shows the process, the failures, and how a rarely-shipped old technique won the keyword round.
code generation
From Code Generation to Application Generation, Part 8: If Agents Are Doing the Coding, What Am I Doing?
Published:
If coding agents handle more implementation, the human role does not disappear. It moves toward mission, judgment, validation, integration, accountability, and helping more organizations use software well.
From Code Generation to Application Generation, Part 7: How Mission-Driven Engineering Happened
Published:
Mission-Driven Engineering did not start as a framework. It started when I realized I was using coding agents to manage UI screens, data layers, and implementation artifacts instead of asking them to satisfy the outcome I actually cared about.
From Code Generation to Application Generation, Part 6: Inside Mission-Driven Engineering
Published:
A practical walk-through of Mission-Driven Engineering: how missions, validations, generations, learning loops, and shared MDE memory turn AI coding agents into application-generation systems.
From Code Generation to Application Generation, Part 5: Why I Ended Up Looking Back at Model-Driven Engineering
Published:
AI application generation feels new, but it echoes Model-Driven Engineering: humans describe intent, machines generate implementation, and independent validation decides whether the result actually works.
From Code Generation to Application Generation, Part 4: My Coding Agents Are Productive. I Am Exhausted.
Published:
AI coding agents can make implementation dramatically faster, but they also create a new bottleneck: the human cost of managing context, attention, and learning across many parallel projects.
From Code Generation to Application Generation, Part 3: Why I Stopped Looking at Generated Code
Published:
As AI coding agents improved, the generated code became less interesting than the final application outcome. The question shifted from whether the code looked right to whether the application solved the problem.
From Code Generation to Application Generation, Part 2: I Knew How to Fix It, But Wasn’t Sure You Wanted It Fixed
Published:
Most of my interaction with coding agents became copying error messages from build systems and asking the agent to fix them. That raised an uncomfortable question: why was I in the loop at all?
From Code Generation to Application Generation, Part 1: When Does the Agent Stop?
Published:
I initially trusted AI through code generation because code could be validated. What surprised me was discovering that the hardest problem was no longer implementation, but defining when the work was actually complete.
codex
MS-SBN, Part 3: My Ten-Year-Old Built a Video Game From Four-Word Prompts
Published:
I typed two sentences into a coding agent, asked it to write a plan, and handed the laptop to my ten-year-old son. Over four weeks Mathai built a real, playable 2D game without writing a line of code. It was a deliberate experiment: proof that when every step has to verify it works, the software keeps working — whoever is driving. That is the core of Mission-Driven Engineering.
MS-SBN, Part 2: Amy Turned a High-School Dream Into a Website
Published:
Amy Givens owned the MyAmy Designs domain since high school, but the website stayed a dream for years. With ChatGPT and Codex, she finally turned that domain into a real business website for MyAmy Designs & Remodeling.
coding agents
MS-SBN, Part 3: My Ten-Year-Old Built a Video Game From Four-Word Prompts
Published:
I typed two sentences into a coding agent, asked it to write a plan, and handed the laptop to my ten-year-old son. Over four weeks Mathai built a real, playable 2D game without writing a line of code. It was a deliberate experiment: proof that when every step has to verify it works, the software keeps working — whoever is driving. That is the core of Mission-Driven Engineering.
computer science education
Teaching Philosophy as a Part-Time Teacher
Published:
Between 2017 and 2025, I consistently taught undergraduate or graduate courses in most semesters while balancing my teaching responsibilities with a full-time position in industry.
Teaching philosophy
Published:
Teaching methods should be flexible, evolving based on the students, course content, and learning environment.
context switching
From Code Generation to Application Generation, Part 4: My Coding Agents Are Productive. I Am Exhausted.
Published:
AI coding agents can make implementation dramatically faster, but they also create a new bottleneck: the human cost of managing context, attention, and learning across many parallel projects.
cranfield
SLAB-RS, Part 4: The Agent Breaks Its Ceiling with Embeddings
Published:
Embeddings from a chat model scored five times worse than random vectors. A purpose-built retrieval model beat the keyword ceiling by 8.4%. The agent’s three embedding attempts, a machine-learned ranking detour, and a live OpenSearch vector index.
SLAB-RS, Part 3: The Agent Climbs Keyword Search to Its Ceiling
Published:
An AI agent ran five ranking experiments on a live OpenSearch baseline in six days — work that would have taken a core search team months. This article shows the process, the failures, and how a rarely-shipped old technique won the keyword round.
Self-Learning Agent-Based Retail Search, Part 2: The Baseline Before the Agents
Published:
Before search agents tune anything, the system needs a measurable baseline. This article shows Phase 1 of the project: an out-of-box OpenSearch BM25 baseline on Cranfield, the live relevance numbers, and the failures agents will need to improve.
custom software
Modern Software for Small Businesses and Nonprofits, Part 1: The Website Is Becoming the Software
Published:
AI agents and inexpensive hosted services are making the old static-versus-dynamic website distinction less important for small businesses and nonprofits. A website can now become the first useful custom workflow.
The End of Software Scarcity, Part 2: Rosa’s Story
Published:
In my previous article, I argued that AI-assisted development may be bringing an end to software scarcity. This article tests that idea through a real-world project with a local small business owner.
The End of Software Scarcity, Part 1: Why Software Can Adapt to the Business
Published:
For decades, organizations adapted themselves to software because software was expensive to build and maintain. AI-assisted development may reverse that relationship, making it practical for software to adapt to the unique needs of individual organizations.
customer acquisition
The End of Software Scarcity, Part 4: Rosa’s Story — Lead Workflow
Published:
A website is only the front door. In this article, I explore how an AI-enabled conversation becomes part of a small operations system for leads, clients, jobs, reviews, videos, and ads.
customer experience
The End of Software Scarcity, Part 3: Rosa’s Story — Website & AI Chat
Published:
Building the website was easy. The more interesting question was whether a small business could afford an AI-powered customer experience with virtually no recurring software costs.
data science
Artificial Intelligent Retail Search is here! (2) - The Data Science Era
Published:
Moving beyond simple keyword matching. How the industry transitioned to hybrid systems, query understanding, and the “Builder’s Era” of search relevance.
ecommerce search
Self-Learning Agent-Based Retail Search, Part 2: The Baseline Before the Agents
Published:
Before search agents tune anything, the system needs a measurable baseline. This article shows Phase 1 of the project: an out-of-box OpenSearch BM25 baseline on Cranfield, the live relevance numbers, and the failures agents will need to improve.
Self-Learning Agent-Based Retail Search, Part 1: Why Retail Search Is Harder Than It Looks
Published:
Retail search is not just about returning relevant products. The hard part is deciding which relevant product should come first when customer needs, business goals, inventory, promotions, trust, and mobile behavior all compete.
Artificial Intelligent Retail Search is here!-In Progress
Published:
In this article, I explore the evolution of retail search and attempt to predict the future of retail search
Artificial Intelligent Retail Search is here! (2) - The Data Science Era
Published:
Moving beyond simple keyword matching. How the industry transitioned to hybrid systems, query understanding, and the “Builder’s Era” of search relevance.
Artificial Intelligent Retail Search is here! (1) - The Legacy & The Problem
Published:
A look back at the “Black Box” era of retail search, why we moved away from it, and the fundamental tension between finding products and making money.
embeddings
SLAB-RS, Part 5: How the Agents Discovered Hybrid Search
Published:
The agents took their Phase 1 wins to fifteen new domains — and discovered hybrid search: the one method that improved every single one, by up to 64%. The keyword tricks that looked brilliant on aeronautics turned out to be aeronautics-shaped, and even the cleverest ranker got demoted by Occam’s razor.
SLAB-RS, Part 4: The Agent Breaks Its Ceiling with Embeddings
Published:
Embeddings from a chat model scored five times worse than random vectors. A purpose-built retrieval model beat the keyword ceiling by 8.4%. The agent’s three embedding attempts, a machine-learned ranking detour, and a live OpenSearch vector index.
endeca
Artificial Intelligent Retail Search is here! (1) - The Legacy & The Problem
Published:
A look back at the “Black Box” era of retail search, why we moved away from it, and the fundamental tension between finding products and making money.
engineering leadership
Is Agile Failing in the Age of AI?
Published:
Agile transformed software development by adapting to changing requirements. But what happens when AI dramatically reduces the cost of implementation? Are we still optimizing for the right bottleneck?
AI Doesn’t Have a Coding Problem. Enterprises Have a Permission Problem.
Published:
What if the biggest obstacle to AI transformation isn’t the technology, but the way we’ve organized our companies?
engineering productivity
From Code Generation to Application Generation, Part 4: My Coding Agents Are Productive. I Am Exhausted.
Published:
AI coding agents can make implementation dramatically faster, but they also create a new bottleneck: the human cost of managing context, attention, and learning across many parallel projects.
enterprise ai
AI Doesn’t Have a Coding Problem. Enterprises Have a Permission Problem.
Published:
What if the biggest obstacle to AI transformation isn’t the technology, but the way we’ve organized our companies?
enterprise software
AI Doesn’t Have a Coding Problem. Enterprises Have a Permission Problem.
Published:
What if the biggest obstacle to AI transformation isn’t the technology, but the way we’ve organized our companies?
entrepreneurship
The End of Software Scarcity, Part 4: Rosa’s Story — Lead Workflow
Published:
A website is only the front door. In this article, I explore how an AI-enabled conversation becomes part of a small operations system for leads, clients, jobs, reviews, videos, and ads.
The End of Software Scarcity, Part 3: Rosa’s Story — Website & AI Chat
Published:
Building the website was easy. The more interesting question was whether a small business could afford an AI-powered customer experience with virtually no recurring software costs.
The End of Software Scarcity, Part 2: Rosa’s Story
Published:
In my previous article, I argued that AI-assisted development may be bringing an end to software scarcity. This article tests that idea through a real-world project with a local small business owner.
The End of Software Scarcity, Part 1: Why Software Can Adapt to the Business
Published:
For decades, organizations adapted themselves to software because software was expensive to build and maintain. AI-assisted development may reverse that relationship, making it practical for software to adapt to the unique needs of individual organizations.
field weighting
SLAB-RS, Part 7: The Textbook Wins the Benchmark, and Loses the Trade
Published:
Retail is the first dataset in the project with real graded labels — so it is the first place the classical retail-search toolkit gets a fair audition. Field weighting stayed dormant. Learning-to-rank finally woke up, and then relearned the hybrid it was supposed to beat. The full textbook cascade won the benchmark — by +0.13% over the lean stack that was already shipped. Measure everything, ship almost nothing.
game development
MS-SBN, Part 3: My Ten-Year-Old Built a Video Game From Four-Word Prompts
Published:
I typed two sentences into a coding agent, asked it to write a plan, and handed the laptop to my ten-year-old son. Over four weeks Mathai built a real, playable 2D game without writing a line of code. It was a deliberate experiment: proof that when every step has to verify it works, the software keeps working — whoever is driving. That is the core of Mission-Driven Engineering.
hybrid search
SLAB-RS, Part 6: The Agent Meets a Million Real Products
Published:
Five parts of a retail search series, and the documents were never products. Phase 3 changes that: 1.2 million real Amazon products, graded Exact/Substitute/Complement/Irrelevant labels, and one question — does the academic stack survive contact with real retail? It does. The BGE hybrid lands at parity with the published single-model baseline, at production latency, and int8 quantization makes a live million-vector index fit on a free-tier box, losslessly.
SLAB-RS, Part 5: How the Agents Discovered Hybrid Search
Published:
The agents took their Phase 1 wins to fifteen new domains — and discovered hybrid search: the one method that improved every single one, by up to 64%. The keyword tricks that looked brilliant on aeronautics turned out to be aeronautics-shaped, and even the cleverest ranker got demoted by Occam’s razor.
SLAB-RS, Part 4: The Agent Breaks Its Ceiling with Embeddings
Published:
Embeddings from a chat model scored five times worse than random vectors. A purpose-built retrieval model beat the keyword ceiling by 8.4%. The agent’s three embedding attempts, a machine-learned ranking detour, and a live OpenSearch vector index.
industry and academia
Teaching Philosophy as a Part-Time Teacher
Published:
Between 2017 and 2025, I consistently taught undergraduate or graduate courses in most semesters while balancing my teaching responsibilities with a full-time position in industry.
information retrieval
SLAB-RS, Part 7: The Textbook Wins the Benchmark, and Loses the Trade
Published:
Retail is the first dataset in the project with real graded labels — so it is the first place the classical retail-search toolkit gets a fair audition. Field weighting stayed dormant. Learning-to-rank finally woke up, and then relearned the hybrid it was supposed to beat. The full textbook cascade won the benchmark — by +0.13% over the lean stack that was already shipped. Measure everything, ship almost nothing.
SLAB-RS, Part 6: The Agent Meets a Million Real Products
Published:
Five parts of a retail search series, and the documents were never products. Phase 3 changes that: 1.2 million real Amazon products, graded Exact/Substitute/Complement/Irrelevant labels, and one question — does the academic stack survive contact with real retail? It does. The BGE hybrid lands at parity with the published single-model baseline, at production latency, and int8 quantization makes a live million-vector index fit on a free-tier box, losslessly.
SLAB-RS, Part 5: How the Agents Discovered Hybrid Search
Published:
The agents took their Phase 1 wins to fifteen new domains — and discovered hybrid search: the one method that improved every single one, by up to 64%. The keyword tricks that looked brilliant on aeronautics turned out to be aeronautics-shaped, and even the cleverest ranker got demoted by Occam’s razor.
SLAB-RS, Interlude: Why the Agent Is Not in a Store Yet
Published:
Four articles into a series called retail search and there is not a single product — only aeronautics abstracts. Here is the map: what BEIR is, why the same BM25 scores 0.158 on one dataset and 0.789 on another, why I was wrong to call Phase 2 a filter, and what has to happen before the agent reaches real products.
SLAB-RS, Part 4: The Agent Breaks Its Ceiling with Embeddings
Published:
Embeddings from a chat model scored five times worse than random vectors. A purpose-built retrieval model beat the keyword ceiling by 8.4%. The agent’s three embedding attempts, a machine-learned ranking detour, and a live OpenSearch vector index.
SLAB-RS, Part 3: The Agent Climbs Keyword Search to Its Ceiling
Published:
An AI agent ran five ranking experiments on a live OpenSearch baseline in six days — work that would have taken a core search team months. This article shows the process, the failures, and how a rarely-shipped old technique won the keyword round.
Self-Learning Agent-Based Retail Search, Part 2: The Baseline Before the Agents
Published:
Before search agents tune anything, the system needs a measurable baseline. This article shows Phase 1 of the project: an out-of-box OpenSearch BM25 baseline on Cranfield, the live relevance numbers, and the failures agents will need to improve.
Self-Learning Agent-Based Retail Search, Part 1: Why Retail Search Is Harder Than It Looks
Published:
Retail search is not just about returning relevant products. The hard part is deciding which relevant product should come first when customer needs, business goals, inventory, promotions, trust, and mobile behavior all compete.
kids and ai
MS-SBN, Part 3: My Ten-Year-Old Built a Video Game From Four-Word Prompts
Published:
I typed two sentences into a coding agent, asked it to write a plan, and handed the laptop to my ten-year-old son. Over four weeks Mathai built a real, playable 2D game without writing a line of code. It was a deliberate experiment: proof that when every step has to verify it works, the software keeps working — whoever is driving. That is the core of Mission-Driven Engineering.
large language models
Artificial Intelligent Retail Search is here!-In Progress
Published:
In this article, I explore the evolution of retail search and attempt to predict the future of retail search
lead workflow
The End of Software Scarcity, Part 4: Rosa’s Story — Lead Workflow
Published:
A website is only the front door. In this article, I explore how an AI-enabled conversation becomes part of a small operations system for leads, clients, jobs, reviews, videos, and ads.
learning to rank
SLAB-RS, Part 7: The Textbook Wins the Benchmark, and Loses the Trade
Published:
Retail is the first dataset in the project with real graded labels — so it is the first place the classical retail-search toolkit gets a fair audition. Field weighting stayed dormant. Learning-to-rank finally woke up, and then relearned the hybrid it was supposed to beat. The full textbook cascade won the benchmark — by +0.13% over the lean stack that was already shipped. Measure everything, ship almost nothing.
SLAB-RS, Part 5: How the Agents Discovered Hybrid Search
Published:
The agents took their Phase 1 wins to fifteen new domains — and discovered hybrid search: the one method that improved every single one, by up to 64%. The keyword tricks that looked brilliant on aeronautics turned out to be aeronautics-shaped, and even the cleverest ranker got demoted by Occam’s razor.
SLAB-RS, Part 4: The Agent Breaks Its Ceiling with Embeddings
Published:
Embeddings from a chat model scored five times worse than random vectors. A purpose-built retrieval model beat the keyword ceiling by 8.4%. The agent’s three embedding attempts, a machine-learned ranking detour, and a live OpenSearch vector index.
local business
MS-SBN, Part 2: Amy Turned a High-School Dream Into a Website
Published:
Amy Givens owned the MyAmy Designs domain since high school, but the website stayed a dream for years. With ChatGPT and Codex, she finally turned that domain into a real business website for MyAmy Designs & Remodeling.
The End of Software Scarcity, Part 4: Rosa’s Story — Lead Workflow
Published:
A website is only the front door. In this article, I explore how an AI-enabled conversation becomes part of a small operations system for leads, clients, jobs, reviews, videos, and ads.
The End of Software Scarcity, Part 3: Rosa’s Story — Website & AI Chat
Published:
Building the website was easy. The more interesting question was whether a small business could afford an AI-powered customer experience with virtually no recurring software costs.
The End of Software Scarcity, Part 2: Rosa’s Story
Published:
In my previous article, I argued that AI-assisted development may be bringing an end to software scarcity. This article tests that idea through a real-world project with a local small business owner.
mission-driven development
From Code Generation to Application Generation, Part 7: How Mission-Driven Engineering Happened
Published:
Mission-Driven Engineering did not start as a framework. It started when I realized I was using coding agents to manage UI screens, data layers, and implementation artifacts instead of asking them to satisfy the outcome I actually cared about.
From Code Generation to Application Generation, Part 6: Inside Mission-Driven Engineering
Published:
A practical walk-through of Mission-Driven Engineering: how missions, validations, generations, learning loops, and shared MDE memory turn AI coding agents into application-generation systems.
From Code Generation to Application Generation, Part 5: Why I Ended Up Looking Back at Model-Driven Engineering
Published:
AI application generation feels new, but it echoes Model-Driven Engineering: humans describe intent, machines generate implementation, and independent validation decides whether the result actually works.
mission-driven engineering
SLAB-RS, Part 7: The Textbook Wins the Benchmark, and Loses the Trade
Published:
Retail is the first dataset in the project with real graded labels — so it is the first place the classical retail-search toolkit gets a fair audition. Field weighting stayed dormant. Learning-to-rank finally woke up, and then relearned the hybrid it was supposed to beat. The full textbook cascade won the benchmark — by +0.13% over the lean stack that was already shipped. Measure everything, ship almost nothing.
SLAB-RS, Part 6: The Agent Meets a Million Real Products
Published:
Five parts of a retail search series, and the documents were never products. Phase 3 changes that: 1.2 million real Amazon products, graded Exact/Substitute/Complement/Irrelevant labels, and one question — does the academic stack survive contact with real retail? It does. The BGE hybrid lands at parity with the published single-model baseline, at production latency, and int8 quantization makes a live million-vector index fit on a free-tier box, losslessly.
MS-SBN, Part 3: My Ten-Year-Old Built a Video Game From Four-Word Prompts
Published:
I typed two sentences into a coding agent, asked it to write a plan, and handed the laptop to my ten-year-old son. Over four weeks Mathai built a real, playable 2D game without writing a line of code. It was a deliberate experiment: proof that when every step has to verify it works, the software keeps working — whoever is driving. That is the core of Mission-Driven Engineering.
SLAB-RS, Part 5: How the Agents Discovered Hybrid Search
Published:
The agents took their Phase 1 wins to fifteen new domains — and discovered hybrid search: the one method that improved every single one, by up to 64%. The keyword tricks that looked brilliant on aeronautics turned out to be aeronautics-shaped, and even the cleverest ranker got demoted by Occam’s razor.
SLAB-RS, Interlude: Why the Agent Is Not in a Store Yet
Published:
Four articles into a series called retail search and there is not a single product — only aeronautics abstracts. Here is the map: what BEIR is, why the same BM25 scores 0.158 on one dataset and 0.789 on another, why I was wrong to call Phase 2 a filter, and what has to happen before the agent reaches real products.
SLAB-RS, Part 4: The Agent Breaks Its Ceiling with Embeddings
Published:
Embeddings from a chat model scored five times worse than random vectors. A purpose-built retrieval model beat the keyword ceiling by 8.4%. The agent’s three embedding attempts, a machine-learned ranking detour, and a live OpenSearch vector index.
SLAB-RS, Part 3: The Agent Climbs Keyword Search to Its Ceiling
Published:
An AI agent ran five ranking experiments on a live OpenSearch baseline in six days — work that would have taken a core search team months. This article shows the process, the failures, and how a rarely-shipped old technique won the keyword round.
Self-Learning Agent-Based Retail Search, Part 2: The Baseline Before the Agents
Published:
Before search agents tune anything, the system needs a measurable baseline. This article shows Phase 1 of the project: an out-of-box OpenSearch BM25 baseline on Cranfield, the live relevance numbers, and the failures agents will need to improve.
Self-Learning Agent-Based Retail Search, Part 1: Why Retail Search Is Harder Than It Looks
Published:
Retail search is not just about returning relevant products. The hard part is deciding which relevant product should come first when customer needs, business goals, inventory, promotions, trust, and mobile behavior all compete.
From Code Generation to Application Generation, Part 8: If Agents Are Doing the Coding, What Am I Doing?
Published:
If coding agents handle more implementation, the human role does not disappear. It moves toward mission, judgment, validation, integration, accountability, and helping more organizations use software well.
From Code Generation to Application Generation, Part 7: How Mission-Driven Engineering Happened
Published:
Mission-Driven Engineering did not start as a framework. It started when I realized I was using coding agents to manage UI screens, data layers, and implementation artifacts instead of asking them to satisfy the outcome I actually cared about.
From Code Generation to Application Generation, Part 6: Inside Mission-Driven Engineering
Published:
A practical walk-through of Mission-Driven Engineering: how missions, validations, generations, learning loops, and shared MDE memory turn AI coding agents into application-generation systems.
model driven engineering
From Code Generation to Application Generation, Part 6: Inside Mission-Driven Engineering
Published:
A practical walk-through of Mission-Driven Engineering: how missions, validations, generations, learning loops, and shared MDE memory turn AI coding agents into application-generation systems.
From Code Generation to Application Generation, Part 5: Why I Ended Up Looking Back at Model-Driven Engineering
Published:
AI application generation feels new, but it echoes Model-Driven Engineering: humans describe intent, machines generate implementation, and independent validation decides whether the result actually works.
From Code Generation to Application Generation, Part 3: Why I Stopped Looking at Generated Code
Published:
As AI coding agents improved, the generated code became less interesting than the final application outcome. The question shifted from whether the code looked right to whether the application solved the problem.
From Code Generation to Application Generation, Part 2: I Knew How to Fix It, But Wasn’t Sure You Wanted It Fixed
Published:
Most of my interaction with coding agents became copying error messages from build systems and asking the agent to fix them. That raised an uncomfortable question: why was I in the loop at all?
From Code Generation to Application Generation, Part 1: When Does the Agent Stop?
Published:
I initially trusted AI through code generation because code could be validated. What surprised me was discovering that the hardest problem was no longer implementation, but defining when the work was actually complete.
nonprofit technology
Modern Software for Small Businesses and Nonprofits, Part 1: The Website Is Becoming the Software
Published:
AI agents and inexpensive hosted services are making the old static-versus-dynamic website distinction less important for small businesses and nonprofits. A website can now become the first useful custom workflow.
From Code Generation to Application Generation, Part 8: If Agents Are Doing the Coding, What Am I Doing?
Published:
If coding agents handle more implementation, the human role does not disappear. It moves toward mission, judgment, validation, integration, accountability, and helping more organizations use software well.
opensearch
SLAB-RS, Part 6: The Agent Meets a Million Real Products
Published:
Five parts of a retail search series, and the documents were never products. Phase 3 changes that: 1.2 million real Amazon products, graded Exact/Substitute/Complement/Irrelevant labels, and one question — does the academic stack survive contact with real retail? It does. The BGE hybrid lands at parity with the published single-model baseline, at production latency, and int8 quantization makes a live million-vector index fit on a free-tier box, losslessly.
SLAB-RS, Part 5: How the Agents Discovered Hybrid Search
Published:
The agents took their Phase 1 wins to fifteen new domains — and discovered hybrid search: the one method that improved every single one, by up to 64%. The keyword tricks that looked brilliant on aeronautics turned out to be aeronautics-shaped, and even the cleverest ranker got demoted by Occam’s razor.
SLAB-RS, Interlude: Why the Agent Is Not in a Store Yet
Published:
Four articles into a series called retail search and there is not a single product — only aeronautics abstracts. Here is the map: what BEIR is, why the same BM25 scores 0.158 on one dataset and 0.789 on another, why I was wrong to call Phase 2 a filter, and what has to happen before the agent reaches real products.
SLAB-RS, Part 4: The Agent Breaks Its Ceiling with Embeddings
Published:
Embeddings from a chat model scored five times worse than random vectors. A purpose-built retrieval model beat the keyword ceiling by 8.4%. The agent’s three embedding attempts, a machine-learned ranking detour, and a live OpenSearch vector index.
SLAB-RS, Part 3: The Agent Climbs Keyword Search to Its Ceiling
Published:
An AI agent ran five ranking experiments on a live OpenSearch baseline in six days — work that would have taken a core search team months. This article shows the process, the failures, and how a rarely-shipped old technique won the keyword round.
Self-Learning Agent-Based Retail Search, Part 2: The Baseline Before the Agents
Published:
Before search agents tune anything, the system needs a measurable baseline. This article shows Phase 1 of the project: an out-of-box OpenSearch BM25 baseline on Cranfield, the live relevance numbers, and the failures agents will need to improve.
organizational design
AI Doesn’t Have a Coding Problem. Enterprises Have a Permission Problem.
Published:
What if the biggest obstacle to AI transformation isn’t the technology, but the way we’ve organized our companies?
part-time teaching
Teaching Philosophy as a Part-Time Teacher
Published:
Between 2017 and 2025, I consistently taught undergraduate or graduate courses in most semesters while balancing my teaching responsibilities with a full-time position in industry.
product development
Is Agile Failing in the Age of AI?
Published:
Agile transformed software development by adapting to changing requirements. But what happens when AI dramatically reduces the cost of implementation? Are we still optimizing for the right bottleneck?
product discovery
Self-Learning Agent-Based Retail Search, Part 1: Why Retail Search Is Harder Than It Looks
Published:
Retail search is not just about returning relevant products. The hard part is deciding which relevant product should come first when customer needs, business goals, inventory, promotions, trust, and mobile behavior all compete.
Artificial Intelligent Retail Search is here!-In Progress
Published:
In this article, I explore the evolution of retail search and attempt to predict the future of retail search
Artificial Intelligent Retail Search is here! (1) - The Legacy & The Problem
Published:
A look back at the “Black Box” era of retail search, why we moved away from it, and the fundamental tension between finding products and making money.
product search
SLAB-RS, Part 7: The Textbook Wins the Benchmark, and Loses the Trade
Published:
Retail is the first dataset in the project with real graded labels — so it is the first place the classical retail-search toolkit gets a fair audition. Field weighting stayed dormant. Learning-to-rank finally woke up, and then relearned the hybrid it was supposed to beat. The full textbook cascade won the benchmark — by +0.13% over the lean stack that was already shipped. Measure everything, ship almost nothing.
SLAB-RS, Part 6: The Agent Meets a Million Real Products
Published:
Five parts of a retail search series, and the documents were never products. Phase 3 changes that: 1.2 million real Amazon products, graded Exact/Substitute/Complement/Irrelevant labels, and one question — does the academic stack survive contact with real retail? It does. The BGE hybrid lands at parity with the published single-model baseline, at production latency, and int8 quantization makes a live million-vector index fit on a free-tier box, losslessly.
prompts
MS-SBN, Part 3: My Ten-Year-Old Built a Video Game From Four-Word Prompts
Published:
I typed two sentences into a coding agent, asked it to write a plan, and handed the laptop to my ten-year-old son. Over four weeks Mathai built a real, playable 2D game without writing a line of code. It was a deliberate experiment: proof that when every step has to verify it works, the software keeps working — whoever is driving. That is the core of Mission-Driven Engineering.
pseudo-relevance feedback
SLAB-RS, Part 3: The Agent Climbs Keyword Search to Its Ceiling
Published:
An AI agent ran five ranking experiments on a live OpenSearch baseline in six days — work that would have taken a core search team months. This article shows the process, the failures, and how a rarely-shipped old technique won the keyword round.
quality gates
From Code Generation to Application Generation, Part 2: I Knew How to Fix It, But Wasn’t Sure You Wanted It Fixed
Published:
Most of my interaction with coding agents became copying error messages from build systems and asking the agent to fix them. That raised an uncomfortable question: why was I in the loop at all?
quantization
SLAB-RS, Part 6: The Agent Meets a Million Real Products
Published:
Five parts of a retail search series, and the documents were never products. Phase 3 changes that: 1.2 million real Amazon products, graded Exact/Substitute/Complement/Irrelevant labels, and one question — does the academic stack survive contact with real retail? It does. The BGE hybrid lands at parity with the published single-model baseline, at production latency, and int8 quantization makes a live million-vector index fit on a free-tier box, losslessly.
query understanding
SLAB-RS, Part 7: The Textbook Wins the Benchmark, and Loses the Trade
Published:
Retail is the first dataset in the project with real graded labels — so it is the first place the classical retail-search toolkit gets a fair audition. Field weighting stayed dormant. Learning-to-rank finally woke up, and then relearned the hybrid it was supposed to beat. The full textbook cascade won the benchmark — by +0.13% over the lean stack that was already shipped. Measure everything, ship almost nothing.
Artificial Intelligent Retail Search is here! (2) - The Data Science Era
Published:
Moving beyond simple keyword matching. How the industry transitioned to hybrid systems, query understanding, and the “Builder’s Era” of search relevance.
ranking
Self-Learning Agent-Based Retail Search, Part 1: Why Retail Search Is Harder Than It Looks
Published:
Retail search is not just about returning relevant products. The hard part is deciding which relevant product should come first when customer needs, business goals, inventory, promotions, trust, and mobile behavior all compete.
remodeling
MS-SBN, Part 2: Amy Turned a High-School Dream Into a Website
Published:
Amy Givens owned the MyAmy Designs domain since high school, but the website stayed a dream for years. With ChatGPT and Codex, she finally turned that domain into a real business website for MyAmy Designs & Remodeling.
retail search
SLAB-RS, Part 7: The Textbook Wins the Benchmark, and Loses the Trade
Published:
Retail is the first dataset in the project with real graded labels — so it is the first place the classical retail-search toolkit gets a fair audition. Field weighting stayed dormant. Learning-to-rank finally woke up, and then relearned the hybrid it was supposed to beat. The full textbook cascade won the benchmark — by +0.13% over the lean stack that was already shipped. Measure everything, ship almost nothing.
SLAB-RS, Part 6: The Agent Meets a Million Real Products
Published:
Five parts of a retail search series, and the documents were never products. Phase 3 changes that: 1.2 million real Amazon products, graded Exact/Substitute/Complement/Irrelevant labels, and one question — does the academic stack survive contact with real retail? It does. The BGE hybrid lands at parity with the published single-model baseline, at production latency, and int8 quantization makes a live million-vector index fit on a free-tier box, losslessly.
SLAB-RS, Part 5: How the Agents Discovered Hybrid Search
Published:
The agents took their Phase 1 wins to fifteen new domains — and discovered hybrid search: the one method that improved every single one, by up to 64%. The keyword tricks that looked brilliant on aeronautics turned out to be aeronautics-shaped, and even the cleverest ranker got demoted by Occam’s razor.
SLAB-RS, Interlude: Why the Agent Is Not in a Store Yet
Published:
Four articles into a series called retail search and there is not a single product — only aeronautics abstracts. Here is the map: what BEIR is, why the same BM25 scores 0.158 on one dataset and 0.789 on another, why I was wrong to call Phase 2 a filter, and what has to happen before the agent reaches real products.
SLAB-RS, Part 4: The Agent Breaks Its Ceiling with Embeddings
Published:
Embeddings from a chat model scored five times worse than random vectors. A purpose-built retrieval model beat the keyword ceiling by 8.4%. The agent’s three embedding attempts, a machine-learned ranking detour, and a live OpenSearch vector index.
SLAB-RS, Part 3: The Agent Climbs Keyword Search to Its Ceiling
Published:
An AI agent ran five ranking experiments on a live OpenSearch baseline in six days — work that would have taken a core search team months. This article shows the process, the failures, and how a rarely-shipped old technique won the keyword round.
Self-Learning Agent-Based Retail Search, Part 2: The Baseline Before the Agents
Published:
Before search agents tune anything, the system needs a measurable baseline. This article shows Phase 1 of the project: an out-of-box OpenSearch BM25 baseline on Cranfield, the live relevance numbers, and the failures agents will need to improve.
Self-Learning Agent-Based Retail Search, Part 1: Why Retail Search Is Harder Than It Looks
Published:
Retail search is not just about returning relevant products. The hard part is deciding which relevant product should come first when customer needs, business goals, inventory, promotions, trust, and mobile behavior all compete.
Artificial Intelligent Retail Search is here!-In Progress
Published:
In this article, I explore the evolution of retail search and attempt to predict the future of retail search
Artificial Intelligent Retail Search is here! (2) - The Data Science Era
Published:
Moving beyond simple keyword matching. How the industry transitioned to hybrid systems, query understanding, and the “Builder’s Era” of search relevance.
Artificial Intelligent Retail Search is here! (1) - The Legacy & The Problem
Published:
A look back at the “Black Box” era of retail search, why we moved away from it, and the fundamental tension between finding products and making money.
search
Artificial Intelligent Retail Search is here!-In Progress
Published:
In this article, I explore the evolution of retail search and attempt to predict the future of retail search
Artificial Intelligent Retail Search is here! (2) - The Data Science Era
Published:
Moving beyond simple keyword matching. How the industry transitioned to hybrid systems, query understanding, and the “Builder’s Era” of search relevance.
Artificial Intelligent Retail Search is here! (1) - The Legacy & The Problem
Published:
A look back at the “Black Box” era of retail search, why we moved away from it, and the fundamental tension between finding products and making money.
search evaluation
SLAB-RS, Interlude: Why the Agent Is Not in a Store Yet
Published:
Four articles into a series called retail search and there is not a single product — only aeronautics abstracts. Here is the map: what BEIR is, why the same BM25 scores 0.158 on one dataset and 0.789 on another, why I was wrong to call Phase 2 a filter, and what has to happen before the agent reaches real products.
SLAB-RS, Part 3: The Agent Climbs Keyword Search to Its Ceiling
Published:
An AI agent ran five ranking experiments on a live OpenSearch baseline in six days — work that would have taken a core search team months. This article shows the process, the failures, and how a rarely-shipped old technique won the keyword round.
Self-Learning Agent-Based Retail Search, Part 2: The Baseline Before the Agents
Published:
Before search agents tune anything, the system needs a measurable baseline. This article shows Phase 1 of the project: an out-of-box OpenSearch BM25 baseline on Cranfield, the live relevance numbers, and the failures agents will need to improve.
From Code Generation to Application Generation, Part 7: How Mission-Driven Engineering Happened
Published:
Mission-Driven Engineering did not start as a framework. It started when I realized I was using coding agents to manage UI screens, data layers, and implementation artifacts instead of asking them to satisfy the outcome I actually cared about.
search relevance
SLAB-RS, Part 4: The Agent Breaks Its Ceiling with Embeddings
Published:
Embeddings from a chat model scored five times worse than random vectors. A purpose-built retrieval model beat the keyword ceiling by 8.4%. The agent’s three embedding attempts, a machine-learned ranking detour, and a live OpenSearch vector index.
SLAB-RS, Part 3: The Agent Climbs Keyword Search to Its Ceiling
Published:
An AI agent ran five ranking experiments on a live OpenSearch baseline in six days — work that would have taken a core search team months. This article shows the process, the failures, and how a rarely-shipped old technique won the keyword round.
Self-Learning Agent-Based Retail Search, Part 2: The Baseline Before the Agents
Published:
Before search agents tune anything, the system needs a measurable baseline. This article shows Phase 1 of the project: an out-of-box OpenSearch BM25 baseline on Cranfield, the live relevance numbers, and the failures agents will need to improve.
Self-Learning Agent-Based Retail Search, Part 1: Why Retail Search Is Harder Than It Looks
Published:
Retail search is not just about returning relevant products. The hard part is deciding which relevant product should come first when customer needs, business goals, inventory, promotions, trust, and mobile behavior all compete.
Artificial Intelligent Retail Search is here!-In Progress
Published:
In this article, I explore the evolution of retail search and attempt to predict the future of retail search
Artificial Intelligent Retail Search is here! (2) - The Data Science Era
Published:
Moving beyond simple keyword matching. How the industry transitioned to hybrid systems, query understanding, and the “Builder’s Era” of search relevance.
Artificial Intelligent Retail Search is here! (1) - The Legacy & The Problem
Published:
A look back at the “Black Box” era of retail search, why we moved away from it, and the fundamental tension between finding products and making money.
self-learning systems
From Code Generation to Application Generation, Part 6: Inside Mission-Driven Engineering
Published:
A practical walk-through of Mission-Driven Engineering: how missions, validations, generations, learning loops, and shared MDE memory turn AI coding agents into application-generation systems.
small business
The End of Software Scarcity, Part 4: Rosa’s Story — Lead Workflow
Published:
A website is only the front door. In this article, I explore how an AI-enabled conversation becomes part of a small operations system for leads, clients, jobs, reviews, videos, and ads.
The End of Software Scarcity, Part 3: Rosa’s Story — Website & AI Chat
Published:
Building the website was easy. The more interesting question was whether a small business could afford an AI-powered customer experience with virtually no recurring software costs.
The End of Software Scarcity, Part 2: Rosa’s Story
Published:
In my previous article, I argued that AI-assisted development may be bringing an end to software scarcity. This article tests that idea through a real-world project with a local small business owner.
The End of Software Scarcity, Part 1: Why Software Can Adapt to the Business
Published:
For decades, organizations adapted themselves to software because software was expensive to build and maintain. AI-assisted development may reverse that relationship, making it practical for software to adapt to the unique needs of individual organizations.
small business software
MS-SBN, Part 3: My Ten-Year-Old Built a Video Game From Four-Word Prompts
Published:
I typed two sentences into a coding agent, asked it to write a plan, and handed the laptop to my ten-year-old son. Over four weeks Mathai built a real, playable 2D game without writing a line of code. It was a deliberate experiment: proof that when every step has to verify it works, the software keeps working — whoever is driving. That is the core of Mission-Driven Engineering.
MS-SBN, Part 2: Amy Turned a High-School Dream Into a Website
Published:
Amy Givens owned the MyAmy Designs domain since high school, but the website stayed a dream for years. With ChatGPT and Codex, she finally turned that domain into a real business website for MyAmy Designs & Remodeling.
Modern Software for Small Businesses and Nonprofits, Part 1: The Website Is Becoming the Software
Published:
AI agents and inexpensive hosted services are making the old static-versus-dynamic website distinction less important for small businesses and nonprofits. A website can now become the first useful custom workflow.
From Code Generation to Application Generation, Part 8: If Agents Are Doing the Coding, What Am I Doing?
Published:
If coding agents handle more implementation, the human role does not disappear. It moves toward mission, judgment, validation, integration, accountability, and helping more organizations use software well.
small business website
The End of Software Scarcity, Part 3: Rosa’s Story — Website & AI Chat
Published:
Building the website was easy. The more interesting question was whether a small business could afford an AI-powered customer experience with virtually no recurring software costs.
software economics
From Code Generation to Application Generation, Part 8: If Agents Are Doing the Coding, What Am I Doing?
Published:
If coding agents handle more implementation, the human role does not disappear. It moves toward mission, judgment, validation, integration, accountability, and helping more organizations use software well.
The End of Software Scarcity, Part 1: Why Software Can Adapt to the Business
Published:
For decades, organizations adapted themselves to software because software was expensive to build and maintain. AI-assisted development may reverse that relationship, making it practical for software to adapt to the unique needs of individual organizations.
software engineering
From Code Generation to Application Generation, Part 8: If Agents Are Doing the Coding, What Am I Doing?
Published:
If coding agents handle more implementation, the human role does not disappear. It moves toward mission, judgment, validation, integration, accountability, and helping more organizations use software well.
From Code Generation to Application Generation, Part 7: How Mission-Driven Engineering Happened
Published:
Mission-Driven Engineering did not start as a framework. It started when I realized I was using coding agents to manage UI screens, data layers, and implementation artifacts instead of asking them to satisfy the outcome I actually cared about.
From Code Generation to Application Generation, Part 6: Inside Mission-Driven Engineering
Published:
A practical walk-through of Mission-Driven Engineering: how missions, validations, generations, learning loops, and shared MDE memory turn AI coding agents into application-generation systems.
From Code Generation to Application Generation, Part 5: Why I Ended Up Looking Back at Model-Driven Engineering
Published:
AI application generation feels new, but it echoes Model-Driven Engineering: humans describe intent, machines generate implementation, and independent validation decides whether the result actually works.
From Code Generation to Application Generation, Part 4: My Coding Agents Are Productive. I Am Exhausted.
Published:
AI coding agents can make implementation dramatically faster, but they also create a new bottleneck: the human cost of managing context, attention, and learning across many parallel projects.
The End of Software Scarcity, Part 4: Rosa’s Story — Lead Workflow
Published:
A website is only the front door. In this article, I explore how an AI-enabled conversation becomes part of a small operations system for leads, clients, jobs, reviews, videos, and ads.
From Code Generation to Application Generation, Part 3: Why I Stopped Looking at Generated Code
Published:
As AI coding agents improved, the generated code became less interesting than the final application outcome. The question shifted from whether the code looked right to whether the application solved the problem.
From Code Generation to Application Generation, Part 2: I Knew How to Fix It, But Wasn’t Sure You Wanted It Fixed
Published:
Most of my interaction with coding agents became copying error messages from build systems and asking the agent to fix them. That raised an uncomfortable question: why was I in the loop at all?
From Code Generation to Application Generation, Part 1: When Does the Agent Stop?
Published:
I initially trusted AI through code generation because code could be validated. What surprised me was discovering that the hardest problem was no longer implementation, but defining when the work was actually complete.
The End of Software Scarcity, Part 3: Rosa’s Story — Website & AI Chat
Published:
Building the website was easy. The more interesting question was whether a small business could afford an AI-powered customer experience with virtually no recurring software costs.
Is Agile Failing in the Age of AI?
Published:
Agile transformed software development by adapting to changing requirements. But what happens when AI dramatically reduces the cost of implementation? Are we still optimizing for the right bottleneck?
AI Doesn’t Have a Coding Problem. Enterprises Have a Permission Problem.
Published:
What if the biggest obstacle to AI transformation isn’t the technology, but the way we’ve organized our companies?
The End of Software Scarcity, Part 2: Rosa’s Story
Published:
In my previous article, I argued that AI-assisted development may be bringing an end to software scarcity. This article tests that idea through a real-world project with a local small business owner.
The End of Software Scarcity, Part 1: Why Software Can Adapt to the Business
Published:
For decades, organizations adapted themselves to software because software was expensive to build and maintain. AI-assisted development may reverse that relationship, making it practical for software to adapt to the unique needs of individual organizations.
software engineering education
Teaching philosophy
Published:
Teaching methods should be flexible, evolving based on the students, course content, and learning environment.
software scarcity
MS-SBN, Part 2: Amy Turned a High-School Dream Into a Website
Published:
Amy Givens owned the MyAmy Designs domain since high school, but the website stayed a dream for years. With ChatGPT and Codex, she finally turned that domain into a real business website for MyAmy Designs & Remodeling.
Modern Software for Small Businesses and Nonprofits, Part 1: The Website Is Becoming the Software
Published:
AI agents and inexpensive hosted services are making the old static-versus-dynamic website distinction less important for small businesses and nonprofits. A website can now become the first useful custom workflow.
software validation
From Code Generation to Application Generation, Part 7: How Mission-Driven Engineering Happened
Published:
Mission-Driven Engineering did not start as a framework. It started when I realized I was using coding agents to manage UI screens, data layers, and implementation artifacts instead of asking them to satisfy the outcome I actually cared about.
From Code Generation to Application Generation, Part 6: Inside Mission-Driven Engineering
Published:
A practical walk-through of Mission-Driven Engineering: how missions, validations, generations, learning loops, and shared MDE memory turn AI coding agents into application-generation systems.
From Code Generation to Application Generation, Part 5: Why I Ended Up Looking Back at Model-Driven Engineering
Published:
AI application generation feels new, but it echoes Model-Driven Engineering: humans describe intent, machines generate implementation, and independent validation decides whether the result actually works.
From Code Generation to Application Generation, Part 4: My Coding Agents Are Productive. I Am Exhausted.
Published:
AI coding agents can make implementation dramatically faster, but they also create a new bottleneck: the human cost of managing context, attention, and learning across many parallel projects.
From Code Generation to Application Generation, Part 3: Why I Stopped Looking at Generated Code
Published:
As AI coding agents improved, the generated code became less interesting than the final application outcome. The question shifted from whether the code looked right to whether the application solved the problem.
From Code Generation to Application Generation, Part 2: I Knew How to Fix It, But Wasn’t Sure You Wanted It Fixed
Published:
Most of my interaction with coding agents became copying error messages from build systems and asking the agent to fix them. That raised an uncomfortable question: why was I in the loop at all?
From Code Generation to Application Generation, Part 1: When Does the Agent Stop?
Published:
I initially trusted AI through code generation because code could be validated. What surprised me was discovering that the hardest problem was no longer implementation, but defining when the work was actually complete.
spec-driven development
From Code Generation to Application Generation, Part 7: How Mission-Driven Engineering Happened
Published:
Mission-Driven Engineering did not start as a framework. It started when I realized I was using coding agents to manage UI screens, data layers, and implementation artifacts instead of asking them to satisfy the outcome I actually cared about.
startups
The End of Software Scarcity, Part 1: Why Software Can Adapt to the Business
Published:
For decades, organizations adapted themselves to software because software was expensive to build and maintain. AI-assisted development may reverse that relationship, making it practical for software to adapt to the unique needs of individual organizations.
story points
Is Agile Failing in the Age of AI?
Published:
Agile transformed software development by adapting to changing requirements. But what happens when AI dramatically reduces the cost of implementation? Are we still optimizing for the right bottleneck?
teaching
Teaching Philosophy as a Part-Time Teacher
Published:
Between 2017 and 2025, I consistently taught undergraduate or graduate courses in most semesters while balancing my teaching responsibilities with a full-time position in industry.
Teaching philosophy
Published:
Teaching methods should be flexible, evolving based on the students, course content, and learning environment.
teaching philosophy
Teaching Philosophy as a Part-Time Teacher
Published:
Between 2017 and 2025, I consistently taught undergraduate or graduate courses in most semesters while balancing my teaching responsibilities with a full-time position in industry.
Teaching philosophy
Published:
Teaching methods should be flexible, evolving based on the students, course content, and learning environment.
vector search
SLAB-RS, Part 6: The Agent Meets a Million Real Products
Published:
Five parts of a retail search series, and the documents were never products. Phase 3 changes that: 1.2 million real Amazon products, graded Exact/Substitute/Complement/Irrelevant labels, and one question — does the academic stack survive contact with real retail? It does. The BGE hybrid lands at parity with the published single-model baseline, at production latency, and int8 quantization makes a live million-vector index fit on a free-tier box, losslessly.
SLAB-RS, Part 5: How the Agents Discovered Hybrid Search
Published:
The agents took their Phase 1 wins to fifteen new domains — and discovered hybrid search: the one method that improved every single one, by up to 64%. The keyword tricks that looked brilliant on aeronautics turned out to be aeronautics-shaped, and even the cleverest ranker got demoted by Occam’s razor.
SLAB-RS, Part 4: The Agent Breaks Its Ceiling with Embeddings
Published:
Embeddings from a chat model scored five times worse than random vectors. A purpose-built retrieval model beat the keyword ceiling by 8.4%. The agent’s three embedding attempts, a machine-learned ranking detour, and a live OpenSearch vector index.
vibe coding
MS-SBN, Part 3: My Ten-Year-Old Built a Video Game From Four-Word Prompts
Published:
I typed two sentences into a coding agent, asked it to write a plan, and handed the laptop to my ten-year-old son. Over four weeks Mathai built a real, playable 2D game without writing a line of code. It was a deliberate experiment: proof that when every step has to verify it works, the software keeps working — whoever is driving. That is the core of Mission-Driven Engineering.
websites
MS-SBN, Part 2: Amy Turned a High-School Dream Into a Website
Published:
Amy Givens owned the MyAmy Designs domain since high school, but the website stayed a dream for years. With ChatGPT and Codex, she finally turned that domain into a real business website for MyAmy Designs & Remodeling.
Modern Software for Small Businesses and Nonprofits, Part 1: The Website Is Becoming the Software
Published:
AI agents and inexpensive hosted services are making the old static-versus-dynamic website distinction less important for small businesses and nonprofits. A website can now become the first useful custom workflow.
workflow automation
Modern Software for Small Businesses and Nonprofits, Part 1: The Website Is Becoming the Software
Published:
AI agents and inexpensive hosted services are making the old static-versus-dynamic website distinction less important for small businesses and nonprofits. A website can now become the first useful custom workflow.
The End of Software Scarcity, Part 4: Rosa’s Story — Lead Workflow
Published:
A website is only the front door. In this article, I explore how an AI-enabled conversation becomes part of a small operations system for leads, clients, jobs, reviews, videos, and ads.
zero-shot retrieval
SLAB-RS, Part 5: How the Agents Discovered Hybrid Search
Published:
The agents took their Phase 1 wins to fifteen new domains — and discovered hybrid search: the one method that improved every single one, by up to 64%. The keyword tricks that looked brilliant on aeronautics turned out to be aeronautics-shaped, and even the cleverest ranker got demoted by Occam’s razor.
SLAB-RS, Interlude: Why the Agent Is Not in a Store Yet
Published:
Four articles into a series called retail search and there is not a single product — only aeronautics abstracts. Here is the map: what BEIR is, why the same BM25 scores 0.158 on one dataset and 0.789 on another, why I was wrong to call Phase 2 a filter, and what has to happen before the agent reaches real products.