All posts
Everything published here, newest first.
316 posts · showing 11–20
2026
10 posts-
Your Coding Agent Hit Its Cost Cap Mid-Refactor and Left Nothing Behind. Reserve the Last Fifth of the Budget for the Handoff.
A hard spend cap protects your bill, but when it trips mid-task it throws away everything the agent learned. Split the budget into phases so the run always ends with a usable handoff instead of a dead process.
-
The Refund Tool Capped Each Refund at $500. The Support Agent Issued Eleven $490 Refunds to One Customer.
A per-call limit only answers "is this action too big?" Agents fail on a different question: "is this sequence too big?" Here is how a guardrail that never fired still let the money leave, and the ledger check that would have stopped it.
-
Adopt the Agent Framework or Write the Loop Yourself? Count the Defaults You'd Have to Override
Framework feature lists don't settle this choice. What settles it is how many of the framework's hidden defaults your agent would have to fight, and a short audit on one real task tells you before you commit.
-
The Analytics Agent's SQL Was Correct. It Answered a Different Question. Make It Print Its Definitions Before Its Number.
The query ran clean, the chart looked right, and the churn number went into the board deck. It counted trial accounts as customers. The fix is not better SQL; it is making the agent commit to what every word in the question means before it touches the warehouse.
-
Your Scheduling Agent Moved One Meeting and Said "Done." Teach the Loop What Finished Looks Like.
An agent loop ends when the model stops asking for tools, not when your task is finished. Here is why that gap produces confident half-done work, and a small done-check that closes it.
-
Your Assistant Agent Reads Your Inbox and Pays Your Bills. Split It Where the Permissions Change, Not Where the Topics Do.
An email agent, a calendar agent and a finance agent look like clean architecture. They leave every agent exactly as manipulable as before and add three handoffs. There is a better place to draw the line.
-
The On-Call Agent Restarted the Primary Anyway. The Instruction Not To Had Been Summarised Away.
Context compaction keeps the story of a long session and quietly drops the rules. The fix is a pinned constraint block that the summariser is never allowed to touch, plus a check that proves it survived.
-
Your Research Agent Passed the Eval Once. Run Every Case Five Times and Grade the Worst Run.
A single green run tells you the agent can do the task, not that it will. Repeat each eval case, split the suite into solid, flaky and broken, and the flaky bucket becomes your real to-do list.
-
The Inbox Agent Said Nobody Had Replied. The Search Tool Had Returned Page One of Four.
An agent can't tell "there's nothing here" from "I only saw the first page" unless the tool tells it. Here is how to make a paginated tool announce its own incompleteness, and why claims of absence need a stricter rule than claims of presence.
-
Your Agent Fleet Kept Its Own Quota Pinned for Forty Minutes: Synchronised Retries Are a Self-Inflicted Outage
The provider rejected one batch of calls; the fleet turned that into forty minutes of self-inflicted downtime. Why exponential backoff alone makes synchronised retries worse, the sub-second signal that exposes it, and the three-part fix that actually breaks the loop.