#ai-agents
Every post tagged "ai-agents".
303 posts · showing 271–280
-
Designing for Resumability: Agents That Survive a Restart
Serializing the message array is the obvious approach and it produces subtly wrong resumptions. What has to survive a crash is a work ledger, idempotent side effects, and enough state to rebuild context from scratch.
-
Chatbot, Workflow, or Agent? Pick the Simplest Thing That Works
Six weeks building an agent for a task with three fixed steps. One question — can you draw the flowchart before seeing the input? — separates the three architectures and saves most of that time.
-
Flaky Agents: Separating Model Nondeterminism From Your Bugs
A test passed on re-run. That's ambiguous for agents in a way it isn't for other software — and the fix is to stop reporting pass/fail and start reporting distributions.
-
Debate or Vote? Getting Real Value From Multiple Model Opinions
Voting harvests independent error; debate harvests challenge. Pick wrong and you multiply your token bill for agreement you'd have had from a single call — and the disagreement, the part worth paying for, gets logged away.
-
What Breaks First When You Give an Agent a Browser
Six failures, in the order they arrive: the page isn't what you think it is, selectors rot, state assumptions break silently, and the session carries more authority than the task needs.
-
One Prompt Per Job Beats One Prompt For All: The Router Pattern
Every new case adds a paragraph, and adherence to all of them drops. Classify first and run a small prompt built for that class — with per-route tools, limits, and approval policy.
-
Reading Your First Agent Trace: Wrong Tool, Wrong Argument, or Wrong Plan?
Four buckets, checked in order, and most agent failures resolve before you get to the interesting one. The trick is finding the first wrong turn and reading the raw array — not the pretty rendering.
-
Rate Limits Are an Agent Design Constraint, Not an Ops Problem
Backoff assumes a predictable call count. Agents burst, retry at three layers, and generate more traffic the more they're throttled — which makes rate limits an architecture question, not an ops ticket.
-
The Skill Agents Erode Fastest: Reading Unfamiliar Code
Delegating code traversal is pure gain. Delegating comprehension means not having the model — and review quality is bounded by the model you don't have.
-
Build or Buy the Eval Harness? What Each Choice Locks In
Teams buy an eval platform and keep their own scripts anyway. The reason is deterministic replay — it hooks into your dispatch layer, which is the one part no vendor can own.