02
Natural language analysis over your own datasets
Connect a database or drop in a flat file and get back answers, analysis, plots, and written-up reports - not just a query.
Notes from the
workshop floor of an AI engineer.
Building AI agent systems that survive long sessions, real users, and real consequences. A working record of how things work, what ships, what doesn't, and what gets learned along the way.
Colophon
On the right, two parts of the same trade. Products is where I disclose how the things I have shipped were actually built - decisions, trade-offs, what I would do differently. Learning is where I work out, in writing, how parts of the agent stack actually function.
From the workshop
All products →From the field
All field notes → 05
Catching tool errors at the right layer
The mental model is the easy part - handle each kind of tool error where it can actually be fixed. The build is where the detail lives: telling failures apart when you can't trust their wording, retrying in the harness, and stopping a model that won't stop itself.
04
Tools fail. Your agent shouldn't.
Tools fail constantly, and what separates an agent that recovers from one that stalls or spins isn't a smarter model. It's where you handle the error.
03
Do it all at once: parallel tool calls and how to build them
When an agent needs a few independent lookups, there's no reason to do them one at a time. Parallel tool calls, what the model is actually deciding, and the cheapest speed-up there is in an agent.