Daniel Chu / notes from real workflows

Notes from building AI tools that have to survive real workflows.

I write about the awkward gap between AI demos and work that has users, deadlines, data, quality bars, support paths, and people who need the system to behave.

Some notes are polished. Some are field observations from things I am still trying to understand: agents, tools, workflows, evals, recovery paths, and product judgment.

Daniel Chu
Daniel Chu Building and studying AI systems in real workflows.

Current focus: multi-agent development systems, workflow evals, and recovery paths for AI actions.

Start with evidence Bug report A real workflow, edge case, or failure that made the problem visible.
Map the system Workflow trace Where context, tools, people, and incentives shape the outcome.
Carry the decision Decision record What should change in the product, process, or evaluation.

Threads

Problems I am working through.

Field notes

Essays and drafts from building, breaking, and thinking in public.

Open questions

These are not conclusions. They are questions I'm still working through.

Artifacts

Small diagrams, sketches, and work-in-progress fragments.

Compare notes

If something here matches what you are seeing, I would like to hear from you.

LinkedIn X