#agent-design
Every post tagged "agent-design".
112 posts · showing 31–40
-
Choosing Your First Three Tools
Find, read, finish. The third one is the one people leave out, and it's the one that turns "the agent stopped talking" into something you can actually check.
-
The Timeout That Looked Like an Empty Result
The health check timed out, the handler returned an empty list, and the agent reported all clear while two services were down. An empty result and a failed check must not share a shape.
-
Budgeting the Context Window: Dividing a Fixed Space
The window wasn't full and the constraints still vanished — because six claimants compete for one space and nobody allocated it. Making history the residual rather than a claimant is what makes the scheme work.
-
Positions Worth Revising About Agents
Eight beliefs that are reasonable on their face and don't survive production. Every correction points the same direction — which makes it a useful prior for the next problem.
-
Agent Vocabulary: What the Terms Actually Mean
People discussing the same word are frequently discussing different things. Four of the distinctions are load-bearing — and when an agent conversation isn't converging, it's usually one of them.
-
Working With an Agent as a Pair, Not a Vending Machine
Describe, wait, review, repeat — the mode most people start in and the one that hits a ceiling fastest. The difference is fifteen seconds spent on what you know that isn't written down.
-
The Second-System Effect in Agent Deployments
The first agent works because it was scoped well. The second aims at exactly the cases the first one escalated — which is the residual that resisted automation for structural reasons.
-
Model, Loop, Harness: Three Layers and Who Owns Each
Three layers, three change rates, three skill requirements. Conflating the loop and the harness is why loop bugs get fixed with prompt edits — and why domain experts can't fix domain problems.
-
What Distributed-Systems Experience Transfers to Agent Loops
An agent run is a distributed system with unreliable participants, so most of the discipline transfers. Four things twist — and one microservice instinct actively hurts, because agent boundaries are lossy.
-
Prompt Engineering Was the Beginning, Not the Skill
It got named as a discipline when the prompt was the entire interface. It's now one input among several — and if better prompts have stopped helping, five specific things are usually why.