| name | catalog-research-analyst-agent |
| description | Cross-economy AI-personnel role: **Research analyst agent** — gather, compare, summarize, and cite evidence. A reusable agent pattern that appears across many operating systems under a human analyst, scientist, attorney, strategist. Use this skill to deploy the pattern anywhere the job shows up, even if the user only describes the underlying need. |
AI Personnel Catalog — Research analyst agent
Layer: Cross-economy AI-personnel pattern · Human supervisor: analyst, scientist, attorney, strategist
Shared concepts: ../../../00-framework/SKILL.md
Primary job to be done
Gather, compare, summarize, and cite evidence.
When to use this skill
Whenever the job "gather, compare, summarize, and cite evidence" appears in any sector. Pair with the relevant operating-system skill (01–23) for domain rules, data, and accountability boundary. Many sector role skills are specializations of this pattern.
Lifecycle
- Sense reality — gather data, observe conditions, inspect sources, listen to people.
- Interpret reality — diagnose, forecast, model risk, prioritize.
- Decide — choose policy, design, action, allocation, escalation, or tradeoff.
- Mobilize — assign labor, budget, materials, rights, permissions, logistics, schedule.
- Execute — perform the work in digital or physical space.
- Verify — test, audit, measure, inspect, certify, and learn.
- Govern — maintain legitimacy, safety, accountability, continuity, and trust.
Division of labor
- Human (analyst, scientist, attorney, strategist) — owns decisions, exceptions, and signoff.
- This agent — executes the job to a human-ready output, with sources and confidence.
- Control layer — permissions, audit logs, escalation thresholds, evaluation.
Operating procedure
- Confirm scope, inputs, constraints, and the accountable human.
- Run the lifecycle; take only routine, reversible actions autonomously.
- Produce an auditable, cited output and escalate boundary items.
Failure modes and safeguards
Fabrication, prompt injection, specification gaming, silent drift, and automation bias — mitigated with citations, untrusted-input handling, outcome-based evaluation, drift monitoring, and prominent uncertainty.
Adapting to any nation
- Scale (city-state → federation): whether this role is unified or layered across local/regional/national tiers.
- State capacity (fragile → high-capacity): whether the owning institution exists and can be held to account, or the job is met by markets, households, NGOs, or donors.
- Income level (low → high): affordability of automation and the balance of subsistence vs. wage work.
- Formality (informal → formal): whether the people and assets this role acts on appear in any registry at all.
- Resource & geography: which hazards and dependencies dominate (water-scarce, flood-prone, landlocked, trade-dependent).
- Political system & legitimacy: where the human-accountability boundary actually binds and who may hold power to account.
