#agent-design
Every post tagged "agent-design".
112 posts · showing 1–10
-
One Big update_task Tool or Three Small Ones? Your To-Do Agent Only Sees the Names and Descriptions
A to-do agent archived a task you meant to finish, and the tool was working fine. The model picks tools from a short menu of names and descriptions, so how you split that menu decides how often it picks wrong.
-
The Travel Agent Reviewed Its Itinerary Three Times and Approved the Wrong Date Every Time. Reflection Needs Something to Check Against.
A self-review loop that reads only its own draft can polish the wrong answer forever. The fix is to give the critic something the generator never had: the original request, a fresh context, or a tool that can say no.
-
Your Support Agent Still Remembers the Customer Who Was Furious in March. Decide What Memory Expires Before You Decide What It Stores.
Cross-session memory fails less often from forgetting than from remembering too long. A four-class expiry scheme for support agents, and the one field every stored memory needs.
-
The Expense Agent Logged "Rate limit exceeded" as a Vendor Name. Make Tool Errors Impossible to Mistake for Results.
When a tool returns its failure as a plain string, the model reads it like any other output and carries on. The fix lives in the tool's return shape, not in the prompt.
-
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.
-
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 Tool Call Failed on Step 3. Retry, Skip, or Replan? Decide by What the Failure Told You About the Plan.
A failed tool call carries two facts: the action didn't happen, and something you believed may be false. Agents act on the first and throw away the second — here's the one question that sorts retry from skip from replan, and how to put the answer in the error contract instead of the prompt.
-
Your Assistant Still Thinks You're Vegetarian Because of One Dinner Party. Build the Memory Write Gate Before the Retriever.
Most agent memory bugs are write bugs: a one-off remark gets stored as a permanent fact, and no retriever can fix what should never have been saved. Here is a four-question gate that decides what goes in, with scope, provenance and an expiry on every entry.
-
Parallel Subagents or One Agent in Sequence? Check Whether the Subtasks Share a Write
Fanning a task out to five workers looks five times faster, until two of them update the same record and the last write quietly wins. One question about shared writes settles most parallel-vs-sequential calls.