Research Agent
A multi-step agent that plans, searches, reads, and writes a cited report.
When a Simple Search Isn’t Enough
You’ve used the Search API. You send a query, you get back a list of web results — titles, URLs, snippets. It works great for quick lookups, building search UIs, and feeding results into RAG pipelines.
But some questions need more than a list of links. Questions like “what are the latest breakthroughs in quantum computing” or “how do mRNA vaccines work” need someone (or something) to actually read through dozens of sources, cross-reference them, and write up a coherent answer with citations.
That’s what the Research API does. It’s like having a research assistant that reads the web and writes you a report with footnotes.
Try It Live
Run a real Research API request right here — no setup. Open the Try It panel below, paste your API key, edit the input, and send it against the live endpoint. (Research can take up to ~60s at higher effort levels.)
What You’ll Build
A single Research API call that synthesizes a cited Markdown report from multiple web searches under the hood. You pick how thorough — lite for fast answers up to exhaustive for the deepest research — and the API returns content with inline numbered citations and a sources array.
Here’s the difference between Search and Research for the same query:
Search API returns raw results:
Research API returns a synthesized, grounded answer with inline citations:
Same question, fundamentally different output. Search gives you building blocks. Research gives you the finished product.
How the Research API Works
The Research API doesn’t just run one search. It’s powered by the You.com search index, purpose-built for speed, accuracy, and relevance. On top of that index sits an agentic system that works in an iterative loop:
- Reads your question and decides what to search for
- Searches the web and reviews the results
- Visits promising pages and extracts the relevant content
- Decides whether to search again, visit more pages, or start writing
- Repeats until it has enough information (controlled by the effort level)
- Synthesizes everything into a cited markdown answer
When to Use Research vs Search
Prerequisites
Walkthrough
Python
TypeScript
Effort Levels
The research_effort parameter controls how deep the Research API digs. Higher effort means more searches, more sources read, and more thorough analysis.
Full Working Example
We’ve built a complete sample app you can fork and deploy:
Next Steps
Fan out parallel Research calls into a structured, cited brief.
If you need raw search results instead of a synthesized answer.
Full API docs with all parameters and response fields.
Resources
- Research API Reference
- Python SDK (
pip install youdotcom) - TypeScript SDK (
npm install @youdotcom-oss/sdk) - GitHub: ydc-research-sample
- Try the Research API in your browser