4.0 KiB
name, description, version, author, license, platforms, metadata
| name | description | version | author | license | platforms | metadata | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| deep-research | Dispatch exhaustive deep web research to the research profile. Triggered by "deep research", "ask web", or "research this". The research profile runs with the deep-web-research skill loaded — five-move flow, external ledger, mechanical saturation, disconfirmation, condensation from disk. | 1.0.0 | Hermes Agent | MIT |
|
|
deep-research — Exhaustive Web Research Delegation
Overview
Dispatches a research question to the research profile, which runs with the deep-web-research skill loaded. The research agent does exhaustive, trail-following research — any tool, any trail, no rush — then condenses everything into a tight, concrete, evidence-backed answer. This agent just relays the result.
Trigger phrases: "deep research", "ask web", "research this", "deep dive on", "exhaustive research on"
Command
hermes -p research -s deep-web-research chat -q "<question>" -Q --max-turns 200 --yolo
- Output line 1:
session_id: <id>— capture this - Output line 2+: the research agent's condensed answer
- Hold the session_id for follow-up questions
Subsequent asks (resume the session):
hermes -p research -s deep-web-research chat --resume <session_id> -q "<follow-up>" -Q --max-turns 200 --yolo
What the Research Agent Does
The deep-web-research skill on the research profile enforces:
- Decompose — break the question into sub-questions with time classifications
- Landscape Pass — shallow sweep, identify key sources and terms
- Deep-Dive — 3+ search angles per sub-question, full-page reads, citation trails, depth-first
- Disconfirmation — actively hunt for contradiction and outdated claims
- Condensation — read the external findings ledger from disk, synthesize into a concrete answer
The research agent writes all findings to /tmp/research-<sid>.md (external ledger) and uses a phase gate file to enforce completion before condensing. Mechanical saturation checks (grep -c) prevent endless searching.
When to Use
- User says "deep research", "ask web", "research this", "deep dive on"
- Question requires exhaustive multi-source investigation
- User wants current, verified, cross-referenced information
- Phone number lookup, person research, topic investigation, fact verification
When NOT to Use
- Simple factual question (capital of France, current time)
- Question I can answer from a single search
- Task that needs my exact context state
- User explicitly says "quick search" or "just look it up"
Relay Rule
Relay the research agent's actual response. Do not paraphrase or summarize. If the response is long, chunk it. The research agent already condensed — don't re-condense.
Spot-check Rule
The research agent self-reports are not verified fact. If it claims a file write, read_file the path to confirm. If it claims a specific finding, spot-check the source URL.
Session Persistence
Capture session_id from output line 1. Every follow-up in the same line of research MUST use --resume <session_id>. Starting fresh discards the research context and wastes turns.
Common Pitfalls
- Profile flag required. Always use
-p research. The sticky default may be general. - Skill flag required. Always use
-s deep-web-research. Without it, the research agent runs in normal mode without the methodology. - --yolo is required. The research agent runs headless. Without it, approval prompts fail closed.
- 200 turns is the ceiling, not the target. The research agent should condense well before 200. Hitting the ceiling means it failed to condense.
- Don't re-condense. The research agent already produced a condensed answer. Relay it, don't summarize it further.
- Don't do the research yourself. If the user triggers deep research, dispatch it. Don't run a few searches and call it done.