AGENT RUNTIME · SUPERVISION

Every run, in
its full context.

Launch and follow supervised agent processes with their workspaces, budgets, events, memory and evidence in view. Each surface connects back to the run that produced it.

iIllustrative run · Static sample data shows the supervision model; it is not a live runtime connection.
RUN / MISSION-2048

Workspace migration review

IN REVIEW
WORKER PROCESSES3 / 42 running · 1 review
ISOLATED WORKSPACES021 active branch · 1 baseline
EXECUTION BUDGET68%3,240 / 4,800 tokens
EVIDENCE CHECKS4 / 51 check needs review
PROCESS TOPOLOGY

Run execution map

SAMPLE
Running Complete Review required
RESOURCE ENVELOPE

Budget consumption

⌁
68%of declared token budget
Tokens3,240 / 4,800
Run time04:39 / 10:00
Events18 / 50
✓Within configured limits
OBSERVABILITY

Recent events

Open event history →
  1. RUN ADMITTEDWorkspace + execution profile attached
  2. WORKER STARTEDResearcher · process p-042
  3. BUDGETToken allocation updated · 2,400 remaining
  4. HANDOFFEvidence review requested
PROVENANCE

Evidence report

RPT-2048
MISSION CLAIMMigration is isolated and reversible
Workspace diff reviewedPASS
Worker outputs attachedPASS
Rollback procedure verifiedPENDING
Inspect report structure →
THE SUPERVISION SURFACES

One run. Six ways
to inspect it.

Move from process state to the context, limits and evidence behind a result.

WHAT THIS VIEW REPRESENTS

Operational visibility,
with clear boundaries.

This dashboard illustrates how run state, worker activity, budgets and evidence can be brought together. It uses sample values and does not connect to or launch a live GenOS process.

Read the runtime model →