Prompts teach patterns, not facts
The single move that mattered most across every version of my workflow engine — drag the hard-coded facts out of the prompt and let them arrive at runtime, so the prompt only ever teaches shape.
The graph is read-only
I rebuilt a workflow engine around one rule — code is the single source of truth, the visual graph is a projection of it. Twenty years of round-trip tools say that's the only direction that holds.
Two agents, one workflow
Turning natural language into an executable workflow with one agent is a slog. I split it into a fast agent that scopes and a heavy one that builds — and the win came from giving each its own clean context.
Evals are the product
Most AI products don't fail on the model. They fail on the absence of a way to know whether a change made things better. The eval harness — not the model — is the asset you own.
A retriever for agents, not eyes
A search box is built for a human who scans one page of results. A retriever for an agent is a function it calls in a loop. That one difference changes the whole pipeline — and how you prove it got better.
An LLM backend that survives concurrency
A backend that "survives concurrency" is making a tail-latency claim, not an average one. Here is the staged pipeline I run behind an AI answer box, and the three boring guardrails that keep the slow tail from eating everyone.