AI at Work : TSAM 2026
Thank you for your time at the TSAM 2026. Here is the presentation shared during our discussion. More updates to follow on this page based on our discussion.
Writing
-
-
Agentic Engineering, Part 9: Product Guardrails — How to Turn Vague Values Into Mechanical Checks Your Agent Cannot Ignore
Every product team has values. “We care about quality.” “User trust is paramount.” “Performance matters.” These are nice sentiments. They are also completely useless as instructions for an…
-
Agentic Engineering, Part 8: Decision Classification — How One-Way and Two-Way Doors Tell Your Agent When to Be Careful
I borrowed this idea from Amazon, and it has completely changed how I think about technical decisions in an Agentic Engineering workflow. The concept is simple: some decisions…
-
Agentic Engineering, Part 7: Dual Quality Gates — Why Validation and Testing Must Be Separate Processes
Okay so here is something that took me embarrassingly long to figure out: validation and testing are not the same thing. I know, I know — obvious in…
-
Agentic Engineering, Part 6: Forensic Verification — Why a Perfect Score From Your AI Agent Should Make You Nervous
I have a confession to make. When I first set up the verification pass for my AI-generated knowledge store, I expected it to find problems. Lots of them.…
-
Agentic Engineering, Part 5: Traceability Chains — How to Connect Product Beliefs to Code That Actually Enforces Them
Okay so here is a question that keeps coming up in Agentic Engineering: how do you know your product values are actually being enforced in the code? It…
-
Agentic Engineering, Part 4: The Agent Entry Point — Why CLAUDE.md Should Be a Table of Contents, Not an Encyclopedia
If you have worked with AI coding agents for any meaningful period, you have probably hit this wall: the agent knows things that are documented somewhere in your…
-
Agentic Engineering, Part 3: Role-Based Agent Personas — Why Specialization Beats Generalization
This is Part 3 of the Agentic Engineering series. In Part 2, I introduced Knowledge-First Development and the 10-step Knowledge Store Generator. This post goes deeper into the…
-
Agentic Engineering, Part 2: Knowledge-First Development — Why I Generate 44 Documents Before Writing a Single Line of Code
This is Part 2 of the Agentic Engineering series. In Part 1, I made the case for why we need an engineering discipline for agent-driven development. This post…
-
Why Agentic Engineering & Why Now
It was 2021 when they gave my access to Codex to GPT-3. An excited afternoon later I felt like an audience to a marketing gimmick as the code…