#tutorial
Every post tagged "tutorial".
92 posts · showing 81–90
-
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.
-
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.
-
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.
-
Where to Put the Approval: Human-in-the-Loop Is a Design, Not a Checkbox
A confirm dialog nobody reads has all the latency of oversight and none of the protection. Four placements, a routing rule based on reversibility, and the metric that tells you your gate has become a rubber stamp.
-
What Belongs in Long-Term Memory (and What's Just Transcript)
Embedding every turn gives you a transcript with a search box, not memory. Three categories deserve to outlive a conversation — and the contradiction problem needs deciding before it arrives, not after.
-
Streaming an Agent's Progress Without Lying About It
Token streaming goes quiet exactly when an agent gets slow — inside the tool call. The fix is an event stream from the loop, and the hard part is not inventing certainty the loop doesn't have.
-
The Read-Only Agent That Wasn't: Auditing What Your Tools Can Actually Reach
A tool named `check_service_health` woke someone at 3am. Read-only is a claim about effects at the far end of every call, and there's a short audit that either proves it or shows you what you actually deployed.
-
Assert on the Trajectory, Not the Answer
A final-answer check will happily pass a run that took nineteen turns and touched a tool it should never have called. Five lines of trajectory assertions catch what output tests structurally cannot.