Agent operations

Supervision and recovery

Inspect fleet progress, resolve blockers, and recover managed application work.

Supervise a fleet by following outcomes and evidence. Begin with the workstream: which issues are eligible, assigned, blocked or finished, and which application changes have reached users? Then inspect the run responsible for a particular issue. The managed environment supplies execution capacity and infrastructure; your intervention should resolve scope, access or acceptance decisions.

Ask for a useful status

A useful report names the workstream and issue, current assignment, last verified result, blocker and next action. It distinguishes active work from queued work and identifies stale or unavailable observations. A quiet terminal is not proof that a task is stuck, and a live process is not proof of progress.

Use the signed-in agent view and conversation/tool history available to your account. Fleet-wide scheduling and lifecycle inspection depend on the managed environment provisioned during onboarding. The CLI assistance guide covers the authorized managed CLI path; access to one assigned slot does not grant fleet administration.

Intervene at the failing boundary

ObservationNext actionEvidence of recovery
Issue never startsCheck dependencies, workstream approval/pause and assigned capacityA current assignment and observed startup
Startup accepted but no session readyReport the command id and assigned slot through managed supportSession readiness
Agent needs a decisionAnswer the specific question and update issue scopeAgent continues with the recorded decision
Two agents change the same filesStop or redirect one assignment and choose an integration ownerOne coherent diff with combined checks
A test repeatedly failsInspect the actual failure and changed behavior before rerunningRelevant test passes on the corrected revision
Session ends during implementationRecover the existing workspace and last recorded resultSaved changes inspected and a clear continuation
Merge succeeds but app serves old behaviorFollow managed publication and deployed revisionIntended revision plus a matching smoke response
External connection failsCheck that integration's account permissions and service responseA successful authorized operation

Example: the change merged, but the old behavior remains

Suppose a duplicate-handling fix passed its tests, yet the support app still creates two queue entries. Keep the issue open while you establish which revision is serving. If publication or rollout has not completed, Redgold recovers that stage. If the intended revision is live, capture a sanitized reproduction and inspect application behavior and data assumptions.

Repeating implementation before checking the revision can create another fix for code that has not run yet. Repeating a write before checking its result can also create more duplicates. Use the smallest authorized read to establish state.

Review the intervention too

Record the decision or recovery action on the issue, including the affected revision and new verification result. A cancelled task needs a reason and a review of dependent work. An active run needs explicit interruption if it should stop; pausing its workstream only prevents new dispatches.

See the application workstream example for how these decisions fit into a complete managed delivery.

Copyright © 2026