#orchestration
Every post tagged "orchestration".
35 posts · showing 1–10
-
The Tax Agent's Workers Counted March Twice and Skipped Late June. Make Every Delegation Return the Range It Actually Covered.
Splitting a year of transactions across four workers looks like clean delegation until the merged total is off and every worker reports success. The fix is a coverage contract the supervisor checks before it adds anything up.
-
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.
-
Your Critic Agent Approves Everything Because It Read the Worker's Reasoning. Starve It of the Argument, Give It Its Own Evidence.
Forward the worker's transcript to your reviewer agent and it will approve nearly everything — anchored by a conclusion it treats as evidence. Here is the information diet, the mutation test, and the disagreement policy that turn a rubber stamp back into a check.
-
Before You Adopt an Agent Framework, Try to Break Its Loop: Four Escape Hatches You'll Need by Week Three
Time-to-demo is the one framework criterion that stops mattering the moment you ship. Four seams to test in an afternoon — and the production incident each one predicts.
-
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.
-
"Done" Is Not a Handback: What a Worker Agent Should Actually Return to Its Supervisor
A worker agent reporting "completed" tells its supervisor nothing it can verify. Here is the handback shape that makes a fabricated result catchable by code instead of by a second model's opinion.
-
Untrusted Text Doesn't Stay Untrusted: Where Provenance Gets Lost in an Agent Pipeline
An injection scanner that fires on the raw email won't fire on the tidy summary of it. Untrusted content gets laundered clean every time an agent rewrites it — here's where the taint disappears, and how to make it survive.
-
Your Two Reviewer Agents Disagree. Who Breaks the Tie?
Running the same document past two agents is easy. Deciding what happens when they return opposite verdicts is the part most multi-agent designs quietly leave undefined — and the default resolution is usually the worst one available.
-
Blackboard or Mailbox: How Should Three Agents Share What They Learn?
Two agents discover the same fact; a third contradicts both and nobody notices. The shape of your shared state — a common board or point-to-point messages — decides which of those happens.
-
Do You Need an Agent Framework? Write the 40-Line Loop First
The agent loop is shorter than the quickstart for the framework that hides it. Write it once — then you can tell which framework features you actually need and which ones you'd be adopting on faith.