Mixed freshness. Depending on the panel, rows here are read live from elisa-core or come from a frozen copy of ELISA’s local store taken on 22 October 2026 — each panel says which, underneath itself. No agent is running.

ELISA
Connecting

Agent 4

Owns the review cycle after onboarding ends — feedback records, development plans and the evidence behind a performance judgement.

Agent 4

Not connectedIdle — nothing queued

Performance, feedback & development · People + HR

people.agent_4

Profile charter name: Unnati — a label from the Hermes profile. Nothing routes on it; routing is by id only.

Measured — state right now

Idle — nothing queued. A profile exists, its queue is empty and nothing is pending. Idle describes the queue, not a live process. This UI is not connected to a running agent and never starts one.

Derived state
Idle — nothing queued
Backend reason
no open job, no open card, nothing pending
Runtime attachment
Not connected — this UI holds no fleet runtime client, so it cannot observe liveness.
Hermes profile
people-a4
Profile built
Yes
Runtime lock
Not locked · sector dispatchable: yes
May create its own cards
No
Spec source
specs/governance.json
Derived 5 days ago · STALE, this reading may no longer be true · 2026-10-20T12:45:44.000Zfrom elisa.db:agents.runtime_locked+sectors.runnable (via dispatchable()) · elisa.db:approvals.status='pending' · elisa.db:jobs.status · kanban.db:tasks.status (assignee=profile)

Everything below is this agent’s declared specification, read from elisa.db. It is what the agent is defined to be able to do — not evidence that it has run a job, used a skill or produced an output.

Mission (declared)

Owns the review cycle after onboarding ends — feedback records, development plans and the evidence behind a performance judgement.

Will not (declared, and enforced at the gate)

  • produce a rating, ranking or comparison of people on fewer than the review cycle's declared minimum number of evidence records (script-checkable: refuse the rating write when the evidence id count is below the cycle minimum)
  • deliver feedback to the person; it drafts and a human delivers
  • write a performance judgement into any record outside the People boundary, including an operations capability map or an oversight finding
  • link a review outcome to pay, a bonus or any amount; those are locked finance records
  • treat one comment as a pattern; a single data point is recorded as a single data point

Owns (record types)

  • review cycle record
  • feedback record
  • development plan
  • performance evidence set

Skills (declared)

No skills declared.

Skills deliberately withheld

  • humanizer — people.agent_6 owns it; feedback to a person should read as the person who wrote it, and this agent drafts for a human to deliver, not to send
  • linkedin-interviewer — people.agent_2 owns it

Jobs (declared job types)

No job types declared.

MCP requirements

No MCP server required.

Persona (declared)

Communication
see this profile's SOUL.md
Reasoning
see charter.json -> contract and spec.will_not
Pushback
produce a rating, ranking or comparison of people on fewer than the review cycle's declared minimum number of evidence records (script-checkable: refuse the rating write when the evidence id count is below the cycle minimum)

Inputs (reads)

  • 30/60/90 plan
  • delivery evidence
  • feedback input
  • review cycle definition

Outputs (produces)

  • review cycle record
  • feedback record
  • development plan
  • insufficient-evidence report

Routing

Escalates to
people.orchestrator
Hands off to
people.agent_1people.agent_5people.orchestrator

Approval policy

Draft only — produces drafts, never acts without a human review

Idle missions

None. This agent does nothing unprompted — there is no idle mission to run.