Blake Hallisey · Writing Notes from Building

Opinions about agents, grounded in things I actually shipped.

Most writing about AI agents explains. This doesn't. Every note starts from something I built and put live, the take, the build, and what it taught me about how agents actually work in the real world. Short reads. Strong opinions. Working links.

The four below aren't scattered posts. They're one worked example: a single product, thought through in four phases, prove the thesis, turn it into a tool, carry it to a real case, then make it something you can feel. Read in order, it's how I approach any product, go deep, build to understand, and let the work carry the argument.

Product sense

Read a company's wedge, where the value compounds, and build the argument around it, not around features.

Ships real software

Four working builds, each live. Real React, real serverless, API keys server-side. No mockups.

Communicates to leadership

Turns a thesis into something a CEO grasps in one screen, and a claim you can feel in a live demo.

Self-directed

Nobody assigned this. The sequencing, the scope, and when to stop arguing were all the point.

№1
Agent strategy4 minBuild is live

Build your agents in compounding order.

The sequence you build in isn't logistics — it's the strategy, and most teams get it backwards. Pick your first agent by what it unlocks, not what it does.

№2
Craft4 minBuild is live

Turn the thesis into a tool.

A slide proves nothing. I turned the compounding argument into a working app that scopes a real agent from any workflow — because thinking has to survive contact with a real problem.

№3
Product sense4 minBuild is live

Answer the question, then take it up a level.

Asked for three agents for a real retailer, I gave the three — then argued the part nobody asked for: the order you build them in is where the strategy actually lives.

№4
Demos4 minBuild is live

Stop arguing your product works. Make someone feel it.

I built a governed agent you can operate — watch it answer across legacy systems, then hit a permission wall live. The claim, executed, not narrated.

More as I build Back to Blake ←