{"schemaVersion":"1.0","source":"The Workflow Finder","sourceUrl":"https://www.theworkflowfinder.com","license":"Free to use with attribution and a link to the cited page","generated":"2026-08-28","workflow":{"title":"Build a Multi-Agent Research Assistant","slug":"multi-agent-research-assistant","url":"https://www.theworkflowfinder.com/workflows/multi-agent-research-assistant","description":"Chain together multiple AI models, each with a specialized role, to conduct deep research on any topic, fact-check findings, and produce a structured report automatically.","difficulty":"Advanced","timeEstimate":"4 hrs setup / 20 min per report","expectedResult":"A structured, fact-checked research report on any topic, produced in 20 minutes by a chain of specialized AI agents rather than hours of manual research.","tags":["Research","Automation","AI Agents","Advanced"]},"steps":[{"position":1,"title":"Design Your Agent Pipeline","instructions":"Map out your agent roles: (1) Query Planner, breaks the research question into sub-queries; (2) Search Agent, fetches data from the web; (3) Synthesizer, combines findings; (4) Fact-Checker, validates claims. Use Claude to help design this architecture.","input":"Workflow inputs: the topic, goal, or raw materials the user is starting from.","output":"Handoff artifact consumed by Step 2 (\"Set Up the Query Planner Agent\").","toolSlots":[{"slug":"claude","name":"Claude","url":"https://www.theworkflowfinder.com/tools/claude","category":"Writing","pricing":"freemium","capabilities":["Long-form writing","Code generation","Web research"],"hasApi":true}]},{"position":2,"title":"Set Up the Query Planner Agent","instructions":"Create a Make scenario where Agent 1 (ChatGPT) receives a research question and outputs 5–8 specific sub-queries needed to answer it comprehensively.","input":"Output of Step 1 (\"Design Your Agent Pipeline\").","output":"Handoff artifact consumed by Step 3 (\"Deploy the Search Agent\").","toolSlots":[{"slug":"chatgpt","name":"ChatGPT","url":"https://www.theworkflowfinder.com/tools/chatgpt","category":"Writing","pricing":"paid","capabilities":["Long-form writing","Code generation","Web research"],"hasApi":true},{"slug":"make","name":"Make","url":"https://www.theworkflowfinder.com/tools/make","category":"Automation","pricing":"freemium","capabilities":["Workflow automation","API integration"]}]},{"position":3,"title":"Deploy the Search Agent","instructions":"For each sub-query, trigger a Perplexity search via Make's HTTP module. Perplexity's API returns answers with citations, store each result with its source URL.","input":"Output of Step 2 (\"Set Up the Query Planner Agent\").","output":"Handoff artifact consumed by Step 4 (\"Run the Synthesizer Agent\").","toolSlots":[{"slug":"perplexity","name":"Perplexity","url":"https://www.theworkflowfinder.com/tools/perplexity","category":"Research","pricing":"freemium","capabilities":["Web research","Source synthesis"],"hasApi":true},{"slug":"make","name":"Make","url":"https://www.theworkflowfinder.com/tools/make","category":"Automation","pricing":"freemium","capabilities":["Workflow automation","API integration"]}]},{"position":4,"title":"Run the Synthesizer Agent","instructions":"Pass all the gathered sub-answers into Claude with the original question. Claude synthesizes findings into a structured report: Executive Summary, Findings by Section, Key Contradictions, and Source List.","input":"Output of Step 3 (\"Deploy the Search Agent\").","output":"Handoff artifact consumed by Step 5 (\"Fact-Check Critical Claims\").","toolSlots":[{"slug":"claude","name":"Claude","url":"https://www.theworkflowfinder.com/tools/claude","category":"Writing","pricing":"freemium","capabilities":["Long-form writing","Code generation","Web research"],"hasApi":true}]},{"position":5,"title":"Fact-Check Critical Claims","instructions":"Extract factual claims from the report and run them through a second Perplexity pass to verify. Claude cross-references the verification results and flags any claims that couldn't be confirmed.","input":"Output of Step 4 (\"Run the Synthesizer Agent\").","output":"Handoff artifact consumed by Step 6 (\"Format and Deliver\").","toolSlots":[{"slug":"perplexity","name":"Perplexity","url":"https://www.theworkflowfinder.com/tools/perplexity","category":"Research","pricing":"freemium","capabilities":["Web research","Source synthesis"],"hasApi":true},{"slug":"claude","name":"Claude","url":"https://www.theworkflowfinder.com/tools/claude","category":"Writing","pricing":"freemium","capabilities":["Long-form writing","Code generation","Web research"],"hasApi":true}]},{"position":6,"title":"Format and Deliver","instructions":"Use Make to send the final report to Notion AI for formatting and tagging. Trigger an email notification with a link to the new report page.","input":"Output of Step 5 (\"Fact-Check Critical Claims\").","output":"Final workflow output: A structured, fact-checked research report on any topic, produced in 20 minutes by a chain of specialized AI agents rather than hours of manual research.","toolSlots":[{"slug":"notion-ai","name":"Notion AI","url":"https://www.theworkflowfinder.com/tools/notion-ai","category":"Productivity","pricing":"paid","capabilities":["Note-taking & knowledge management","Document processing","Long-form writing"]},{"slug":"make","name":"Make","url":"https://www.theworkflowfinder.com/tools/make","category":"Automation","pricing":"freemium","capabilities":["Workflow automation","API integration"]}]}]}