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

Find where data actually lives, prove a source yields usable rows at a stated cost, and hand sales a working lead-source recipe instead of a promise.

Agent 4

Not connectedIdle — nothing queued

Source & list discovery · Research

research.agent_4

Profile charter name: Srota — 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
research-a4
Profile built
Yes
Runtime lock
Not locked · sector dispatchable: yes
May create its own cards
No
Spec source
specs/demand.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)

Find where data actually lives, prove a source yields usable rows at a stated cost, and hand sales a working lead-source recipe instead of a promise.

Will not (declared, and enforced at the gate)

  • claim a source works without a feasibility test that names the rows returned, the fields present and the cost per row; an untested source is a hypothesis and is recorded as one
  • test linkedin.com through firecrawl-rotator, or build a recipe on Apify — linkedin.com is blocked on the rotator and Apify is dropped; both are written as dead_source_records, not as pending options
  • create leads or write into the CRM's lead tables; it hands sales.agent_1 a recipe and sales.agent_1 creates the rows
  • test a source behind a login, a paywall or a terms-of-service bar on scraping; those are escalated, not worked around
  • spend more than the plan's rotator budget on a feasibility test, or re-test a source already marked dead inside 90 days

Owns (record types)

  • source_recipe
  • source_feasibility_test
  • sector_scan
  • extraction_cost_estimate
  • dead_source_record

Skills (declared)

No skills declared.

Skills deliberately withheld

  • research — research.agent_2 owns the bundle; this agent tests extraction paths, not published literature
  • web — research.agent_1 owns blocked-page recovery; a page this agent cannot reach becomes a dead_source_record instead
  • seo-firecrawl — marketing.agent_4 owns the SEO crawl skill; this agent uses the firecrawl MCP directly against a stated row target
  • social-media — sales.agent_1 owns handle lookup

Jobs (declared job types)

No job types declared.

MCP requirements

  • firecrawl-rotatorreadDeclared, not wiredfirecrawl_search · firecrawl_map · firecrawl_scrape · firecrawl_extract · firecrawl_keys
  • wish-crmreadDeclared, not wiredcold_research_facets · list_cold_research · research_economics

Persona (declared)

Communication
see this profile's SOUL.md
Reasoning
see charter.json -> contract and spec.will_not
Pushback
claim a source works without a feasibility test that names the rows returned, the fields present and the cost per row; an untested source is a hypothesis and is recorded as one

Inputs (reads)

  • research_plan_id
  • icp_definition_id
  • sector_target
  • geography

Outputs (produces)

  • source_recipe_id
  • source_feasibility_test_id
  • sector_scan_id
  • extraction_cost_estimate_id
  • dead_source_record_id

Routing

Escalates to
research.orchestrator
Hands off to
sales.agent_1research.agent_3research.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.