Workflow playbook
Research assistant workflow
Turn open web research into source-backed notes, comparison tables, and a decision-ready recommendation.
Target users
- Founders
- Product managers
- AI builders
Inputs
- Research question
- Decision criteria
- Known sources
Outputs
- Source notes
- Comparison matrix
- Recommendation memo
Boundaries
- Never treat cited answers as final without opening key sources.
- Separate external evidence from Qidao interpretation.
- Re-check time-sensitive facts before publishing.
Common mistakes
- Mixing source facts and model inference in the same notes.
- Letting the AI summarize sources without preserving URLs and dates.
- Searching before defining the decision criteria.
Templates
- Source-backed research memo
- Tool comparison matrix
Primary tools
Alternatives
GeminiGoogle model family for multimodal and workspace-aware AI.OpenAI APIGeneral-purpose model APIs for product builders.ExaAI search API for grounded agents and research workflows.LlamaIndexData and RAG framework for knowledge-heavy AI applications.LangChainAgent engineering framework and observability platform.PineconeManaged vector database for RAG, semantic search, and AI assistants.WeaviateAI-native vector database with free cloud and deployment flexibility.CohereEnterprise AI platform for Command, Embed, Rerank, and RAG systems.FirecrawlWeb data API for search, scraping, crawling, and agent context.ApifyActor platform for web scraping, automation, and AI agent data.JasperAI marketing platform for brand content, campaigns, agents, and GEO workflows.Otter.aiAI meeting notes, live transcription, and meeting workflows.
Steps
- 1
Frame the decision
Define what will be chosen, who uses it, and which criteria matter before searching.
Output: Decision criteria list.
- 2
Collect cited sources
Search the web and capture source URLs, claims, dates, and points that need verification.
Output: Source-backed research notes.
- 3
Synthesize tradeoffs
Convert notes into options, risks, and a clear recommendation.
Output: Decision memo.
Copyable prompts
Turn this research question into decision criteria, source types, and disqualifying evidence.
Summarize these sources into claims, evidence URLs, confidence, and open questions.
Related tools
PerplexityAnswer engine for cited market, product, and tool research.TavilySearch API designed for AI agents and research workflows.ClaudeLong-context assistant for writing, analysis, and coding workflows.OpenAI APIGeneral-purpose model APIs for product builders.ExaAI search API for grounded agents and research workflows.LlamaIndexData and RAG framework for knowledge-heavy AI applications.LangChainAgent engineering framework and observability platform.PineconeManaged vector database for RAG, semantic search, and AI assistants.WeaviateAI-native vector database with free cloud and deployment flexibility.CohereEnterprise AI platform for Command, Embed, Rerank, and RAG systems.FirecrawlWeb data API for search, scraping, crawling, and agent context.ApifyActor platform for web scraping, automation, and AI agent data.Notion AIWorkspace AI for docs, meeting notes, search, and team agents.JasperAI marketing platform for brand content, campaigns, agents, and GEO workflows.Otter.aiAI meeting notes, live transcription, and meeting workflows.
Related guides
The Qidao AI tool selection frameworkA practical seven-part framework for choosing AI tools by task fit, workflow fit, quality, cost, privacy, replaceability, and automation readiness.How to write source-backed AI research memosA method for turning AI-assisted web research into cited claims, comparison tables, confidence notes, and decision-ready recommendations.How to judge whether an AI tool is worth paying forA practical framework covering replacement cost, reliability, privacy, team fit, and switching risk.Model API selection framework for AI product buildersA method for comparing model APIs by task fit, quality, latency, cost, privacy, and fallback strategy.
Use cases
- Tool evaluation
- Market scan
- Vendor shortlist