Introducing /answers: web research in one API call
Backed byYCombinator

Ask the web.
Get answers you can use.

Give your agent a research question. Get structured findings in your chosen shape, with source URLs it can cite and verify.

Get API keyView documentation

What are Linear’s main product features?

Research task

Answer

Structured JSON

{
  "features": [
    "Issue tracking",
    "Project planning",
    "Product roadmaps"
  ]
}

Sources: linear.app · linear.app/features

View sources

Teams build with Context.dev

  • Mintlify
  • daily.dev
  • Daydream
  • Super.com
Start with a question
Describe the research task instead of assembling a set of pages by hand.
Choose the structure
Define the JSON shape your product needs, so the result can move straight into your workflow.
Keep the sources
Use the returned page URLs to show your users where the answer came from.

Your question.
Your output shape.

Send a task and an example JSON structure. The response includes the structured answer and the URLs used as evidence.

npm install context.dev
Read the API reference
TypeScriptanswers.ts
import ContextDev from 'context.dev';

const client = new ContextDev({ apiKey: 'YOUR_API_KEY' });

const answer = await client.web.answers({
  task: 'Find the main product features on linear.app.',
  mode: 'fast',
  json_format: {
    features: [''],
  },
});

console.log(answer.json_content);
console.log(answer.sources);

Give your agents
a research capability.

Move from a question to sourced findings that your application can work with.

Run deep research on demand

Answer “tell me about this company” with actual sources. Resolve a domain to a typed profile, then expand with schema-based extraction from the live site.

Input

notion.com

Company domain

Enriched

Notion

San Francisco, CA

Industry
Software (B2B)
Founded
2013
Product
Workspace
Source
notion.com
x · linkedin

Ground RAG in fresh content

Keep your retrieval index current. Crawl a sitemap, convert every page to clean markdown, and pipe it straight into embeddings, with no brittle parsers in between.

acme.com/docs/api/auth
acme.com/blog/release-v3
acme.com/pricing
acme.com/changelog
acme.com/docs/sdk
markdown → your embeddings

Knowledge base

5 docs indexed

A few things
to know.

More details in the API documentation.

How are the sources returned?

The response includes a sources array of URLs that supplied search results or readable page content. Keep those URLs with the answer so your users can inspect its evidence.

Can I choose the answer format?

Yes. Set json_format to the structure your application expects and read the result from json_content.

How is Answers different from page extraction?

Answers begins with a research task and gathers web evidence. Use extraction when you already have a particular page and want specific fields from it.

What if research stops before it is finished?

The response can include a partial flag when the deadline ends research. Your application can distinguish that result from a completed research run.

Start with your next request.

One API key for scraping, research, brand data, batches, and monitoring.

Get API keyView documentation