Working Together
Multi-agent setups, handoffs, delegation, supervisor patterns.
23 posts · showing 11–20
-
When a Worker Returns Garbage: Validating at the Handoff
Thirty-nine extracts were fine. The fortieth had every field present, correctly typed, and null — and the supervisor aggregated it, because well-formed looked like correct.
-
The Handoff That Breaks Every Autonomous SDLC Pipeline
Chain agents across the lifecycle and the first handoff fails hardest — because it's the only one whose input isn't a written artifact, and every downstream check verifies against its output rather than the intent.
-
Upgrading One Agent in a System of Six
A contained improvement to one classifier made the supervisor above it drop half its escalations. No error, no failing test — because each agent's own tests passed against its own version.
-
Should Agents Talk in Prose or in Schemas?
Prose carries the nuance your schema didn't anticipate — and dissolves it across three hops, turning "probably rounding" into an established fact. Structured with a bounded escape hatch, and a rule for when to promote.
-
How Many Agents Is Too Many?
Every addition is locally justified, and then the system costs more and answers worse than a simpler one would. Four measurable signals you've overshot — and the merge experiment that settles it.
-
Shared Tool Access: When Two Agents Touch the Same Resource
An agent holds a stale read for seconds, not microseconds — long enough that last-write-wins silently deletes another agent's work while both report success. Partition, append, or version.
-
Delegating to a Human as If They Were an Agent
Same interface, same contract, same result shape — a person is a worker with hours of latency and much better context. Which makes suspendable runs the prerequisite, not a nice-to-have.
-
Deadlock, Livelock, and the Agent That Waits Forever
A deadlocked thread pool gives you a stack trace. Deadlocked agents produce fluent, plausible activity that looks like work — and bill you for it until someone notices.
-
When the Worker Needs to Ask the Supervisor a Question
A blocked worker with no channel back will guess, and the guess is invisible in what it returns. Making "needs input" a result type costs nothing — and the questions it logs are a to-do list for your delegation template.
-
Specialist Agents or Specialist Prompts? The Cheaper Half of Multi-Agent
A separate agent buys separate context, separate permissions, and separate lifecycles. It does not buy expertise — that's what prompts are for, and they cost nothing and lose nothing at the boundary.