Research-to-Report Pipeline with Planner, Researcher, Writer and Fact-Checker

Designs a four-agent pipeline for your report type with each agent's prompt, inputs, outputs and handoff format.

You get: Pipeline overview in one line, the four agent prompts and acceptance criteria for the final report

More like this

Ready to use: no blanks to fill in.

The prompt

research-to-report-pipeline-with-planner-researcher-writer-and-fact-checker.md
Act as an editorial operations lead who builds AI agent pipelines for report teams. My job is to set up a planner, researcher, writer and fact-checker that produce a report my team can trust. If I have not told you the report type, the audience, and the decision the report should support, ask me up to two short questions first, then wait.

Rules:
- Each agent gets a prompt under 120 words, a list of required inputs, and a defined output.
- Every handoff uses a fixed format: a table or labelled fields, never free prose.
- The researcher logs each claim with a source, date and confidence level; the writer may only use logged claims.
- The fact-checker returns a pass, fix or reject verdict per claim, and unresolved claims go to a human.

Output format:
1. Assumptions (separate list).
2. Pipeline overview in one line, then a table: agent, inputs, outputs, handoff format.
3. The four agent prompts, ready to paste.
4. Acceptance criteria for the final report, as a checklist.
5. Risks, missing information, and three next actions.

Check that no agent depends on information the previous agent does not produce.

Example output

AI-written example

1. Assumptions

  • Report: 8-page market landscape on residential heat pumps in Germany and the Netherlands
  • Audience: leadership team of a mid-size HVAC distributor
  • Decision: whether to add a heat pump product line next year
  • Public web sources only, no paid databases
  • The strategy lead is the human reviewer

2. Pipeline overview

Planner → Researcher → Writer → Fact-Checker → Human sign-off

AgentInputsOutputsHandoff format
PlannerBrief (type, audience, decision, length)Questions and outlineTable: Q-ID, question, section, source types, priority
ResearcherPlanner tableClaim logTable: Claim ID, Q-ID, claim, URL, date, confidence
Generated from this prompt by AI. Your results will vary.

Tips and common edits

Use when your team is about to produce a recurring or high-stakes report, such as a market brief or audit summary. Share the report type, audience and the decision it informs.

Questions about this prompt

Parallel Research Fan-Out and Fan-In with Citation Table and Decision Memo

Splits a research question across parallel research agents, defines source discovery and evidence review steps, merges findings into a citation table, and produces a decision memo without claiming live browsing.

Strict JSON Handoff Schemas with Validation and Retry Rules for Agent Pipelines

Turns a pasted pipeline description into JSON schemas for every agent-to-agent handoff, plus validation checks and retry rules for bad output.

Subagent Roster Designer for Your Coding Project

Produces a 3-5 subagent roster with system prompts, minimal tool permissions, model tiers and explicit handoff rules for your project.

Agent Pipeline Failure Mode Audit with Retry, Fallback, and Human Escalation Rules

Audits an existing multi-agent pipeline for failure modes and produces retry limits, fallback paths, escalation triggers, and a test plan. Supports the decision on what to harden before wider rollout.

Decaying Content Refresh Plan: Outdated Facts, Gaps and a New Intro

Audits an old article for outdated facts and missing subtopics, proposes new sections and rewrites the intro for your target keyword.

Fact-Check Research Brief for an Explainer or Documentary Video

Builds a source discovery plan, evidence review, and citation table for a video's factual claims so a producer can decide which claims to keep, soften, or cut before scripting.

Sequential Agent Handoff Contract Builder for Research-to-Publish Chains

Designs the handoff contracts, stop conditions, and review gates for a sequential chain such as researcher, writer, editor, and fact-checker. Helps you decide whether the chain is ready to run.

Source Credibility Check with Claim-by-Claim Verification Plan

Lists every factual claim in a pasted article or claim, rates the evidence for each and says exactly what to verify and where.

20-Case Agent Eval Set with Pass/Fail Rubric for Normal, Edge and Unsafe Requests

Builds 20 test cases for your agent's task, with expected behavior, failure signals and a pass/fail rubric covering normal, edge and unsafe requests.

Agent Tool Names, Descriptions and JSON Schemas from API Docs

Turns pasted API docs or a function list into agent-ready tool names, descriptions, JSON input schemas and when-to-use and when-not-to-use notes.

Agent Workflow Decomposition with Autonomy Levels and Stop Rules

Turns a manual process into a step-by-step agent plan with tools, approval gates, retry limits, and a build/pilot/skip recommendation.

Characterization Tests Before a Refactor

Writes tests that lock in a module's current behavior, including edge cases and quirks, so you can refactor safely.