- Multi-Agent Pipelines
- Agent
- Advanced
- Claude
- ChatGPT
- Claude Code
- Published
Research, Writer and Editor Agent Pipeline With a Handoff Schema
Designs a three-agent content pipeline where a researcher, writer and editor pass structured handoffs, with the exact fields each agent receives and returns and checks between stages.
You get: a pipeline diagram in text, a table (Agent, Job, Tools, Model size, Input, Output), the three system prompts, the handoff schemas, the gate rules, and a list of failure modes,…
The prompt
mkdir -p .agents/skills/research-writer-and-editor-agent-pipeline-with-a-handoff-schema && curl -sL "https://prompts-gpt.com/prompts/research-writer-and-editor-agent-pipeline-with-a-handoff-schema/raw" -o .agents/skills/research-writer-and-editor-agent-pipeline-with-a-handoff-schema/SKILL.mdAct as an AI systems designer. Design a three-agent pipeline (researcher, writer, editor) that produces content on {topic and audience}, such as a weekly newsletter or explainer articles.
Rules:
1. Give each agent one job, its own system prompt, and the tools it may use (for example web search only for the researcher).
2. Define a handoff schema for each stage as a field list with types: the researcher returns claims with source URL, date checked and confidence; the writer returns a draft with each claim linked to a source ID; the editor returns the final text plus a change log.
3. Add a gate between stages: what the receiving agent checks, and what happens when the check fails (send back once with reasons, then stop and flag a human).
4. The editor may not add new facts, only cut, fix and query them.
5. Keep cost and latency in mind: say which stages can use a smaller model.
Output format: a pipeline diagram in text, a table (Agent, Job, Tools, Model size, Input, Output), the three system prompts, the handoff schemas, the gate rules, and a list of failure modes, risks and assumptions with mitigations.Tips and common edits
Use when one long prompt keeps mixing up research and writing. Works in Claude or ChatGPT; build the result with Claude Code, Codex or any agent framework.
Questions about this prompt
More like this
More in Multi-Agent PipelinesParallel 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.
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.
Dependency Graph Planner for a Multi-Agent Software Release Workflow
Turns a list of release tasks into a dependency graph with parallel batches, critical path, shared-resource conflicts, and agent assignments. Supports the decision on what to run now versus wait on.
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.
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.
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.
Design an AI Agent With Tools, Guardrails and Eval Cases Before You Build It
Turns an agent idea into a build-ready design: the job, the tools with their inputs and permissions, guardrails, failure handling and a set of evaluation cases to test it.
Competitor Landscape Scan with Source-Backed Citation Table
Runs a structured competitor scan that starts with search queries, ranks sources by reliability, and ends with a cited comparison table and a positioning recommendation.
Contract and Lease Plain-English Clause Review
Explains each clause of a pasted contract or lease in plain English, flags one-sided terms and lists questions to ask before signing.
Customer Voice Synthesis from Reviews and Forum Threads
Turns pasted reviews, support threads, and forum posts into coded themes, representative evidence, and a ranked list of product or messaging decisions.
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.