Octen Docs | The Search infrastructure for AI

For AI agents: docs.octen.ai/capabilities/answer.md

Getting from a question to a grounded answer takes a pipeline: decompose the question, run the searches, feed results to a model, synthesize, and keep track of sources. Octen Answer runs that pipeline in one call: it decomposes your messages into sub-queries, searches them, and synthesizes an answer with an LLM, returning the sources it used. For the full list of parameters, see the Answer API reference.

Why Answer

One call, complete loop. A question goes in; a grounded answer comes out. No search, prompt, and synthesis plumbing to build or maintain.
Multi-angle grounding. Questions decompose into multiple sub-queries, so the answer draws on wider coverage.
Citable answers. The sub-queries and sources come back with the answer, so replies can link to the pages they stand on.

To run synthesis in your own stack, use Broad Search. For long-form research reports, use Deep Research.

How It Works

Send a question or a conversation.
Octen decomposes it into sub-queries and searches them concurrently.
A model synthesizes an answer grounded in the results; the response returns the answer together with the sub-queries and sources used.

Scenarios

Ask a question

One message in, one grounded answer out, with the sub-queries and sources it drew on.

curl -X POST https://api.octen.ai/answer \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "messages": [{ "role": "user", "content": "What changed in the EU AI Act this year?" }]
  }'

Build a grounded chat assistant

In a conversation, questions build on each other. Pass the chat history along, and every reply stays grounded in live search, with follow-ups understood in context.

{
  "messages": [
    { "role": "user", "content": "What are the current US tariffs on Chinese EVs?" },
    { "role": "assistant", "content": "The current rate is..." },
    { "role": "user", "content": "How does the EU compare?" }
  ]
}

Get the full picture on a broad topic

Some questions are really many questions: a market, a technology, a policy area. Answer decomposes them into up to 30 sub-queries and returns a structured Markdown answer that covers the topic angle by angle, cited throughout.

{
  "messages": [{ "role": "user", "content": "the state of the European EV market in 2026" }]
}

Answer from sources you trust

When answers must stand on vetted sources, such as in finance or news products, constrain the searches behind the answer. Answer accepts the same search options as Web Search.

{
  "messages": [{ "role": "user", "content": "central bank rate decisions this week" }],
  "web_search_options": {
    "include_domains": ["reuters.com", "bloomberg.com"],
    "time_range": "week"
  }
}

Answer

Why Answer

How It Works

Scenarios

Ask a question

Build a grounded chat assistant

Get the full picture on a broad topic

Answer from sources you trust

Next Steps

Try in Console

Answer API Reference

​Why Answer

​How It Works

​Scenarios

​Ask a question

​Build a grounded chat assistant

​Get the full picture on a broad topic

​Answer from sources you trust

​Next Steps

Try in Console

Answer API Reference

Why Answer

How It Works

Scenarios

Ask a question

Build a grounded chat assistant

Get the full picture on a broad topic

Answer from sources you trust

Next Steps