← AI Workflow Templates
ResearchadvancedHITL requiredupdated 2026-08-11
Agentic Research Brief
A plan-search-synthesize agent loop that produces a cited research brief with an explicit confidence note.
#agent#research#search#synthesis
Tools in the pipeline
- llmplannerDecompose into 3-6 sub-questions.
- retrieversearchRetrieve sources per sub-question.
- llmsynthesizerWrite the brief with citations and a confidence note.
- humananalystAccept or send back conflicts.
Stack: LLM · search · citation store
What it does
Answers an open research question by planning sub-questions, searching for each, and synthesizing a brief with citations and a stated confidence level. Flags where sources disagree instead of papering over it.
Pipeline
- Plan — decompose the question into 3–6 sub-questions.
- Search — retrieve sources per sub-question (web, docs, or internal).
- Extract — pull the relevant claim + citation from each source.
- Synthesize — write the brief, citing every claim.
- Assess — end with a confidence note and list unresolved conflicts.
Guardrails
Every non-obvious claim must carry a citation. When sources conflict, present both and say so. Cap search depth and total tool calls to bound cost. State the confidence level explicitly so readers can calibrate.
Structural dry-run
No model call. Validates required fields only.Prefills the example payload for MCP adoption. Edit it, then run.