Lookio Docs
Lookio websiteOpen Lookio
Get startedQuickstart

Quickstart

Add a resource, create an assistant and ask a first question, in the Lookio app and then over the REST API with curl.

You need a Lookio account. A new workspace comes with free welcome credits, which is enough for the questions below.

Add a resource

Open Resources and choose Add a resource. Pick Text, give it a title such as “Refund policy”, and paste a few paragraphs. Markdown headings (#) become the sections an answer cites.

The resource shows Indexing for a few seconds, then Ready.

Create an assistant

Open Assistants and choose Create an assistant. Name it, then open it and choose what it answers from: all resources, the ones you pick, or a tag. In the first case there is nothing else to set.

Ask a question

Open Chat, pick the assistant and ask something your text answers. The answer cites its sources as [1], [2]. Open a citation to read the passage it relies on.

The API answers at https://api.lookio.app/v1. Every call needs an API key. See Authentication for the details.

Create an API key

In the app, open Developer tools, then the API tab, and choose Create key. Pick the Editor preset: it can read, add and update resources and assistants, and ask questions. Copy the key now. Lookio shows it once.

Terminal
export LOOKIO_API_KEY="sk_live_..."

Check the key

Terminal
curl https://api.lookio.app/v1/account \
  -H "Authorization: Bearer $LOOKIO_API_KEY"

The response lists the scopes this key holds.

Add a text

Terminal
curl https://api.lookio.app/v1/resources \
  -H "Authorization: Bearer $LOOKIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "type": "text",
    "title": "Refund policy",
    "text": "# Refunds\n\nYou can return any item within 30 days for a full refund."
  }'

The resource comes back with status set to queued. Note its data.id.

Wait until it is ready

Terminal
curl https://api.lookio.app/v1/resources/RESOURCE_ID \
  -H "Authorization: Bearer $LOOKIO_API_KEY"

Repeat until data.status is ready. If it is failed, read data.status_detail.

Create an assistant

Terminal
curl https://api.lookio.app/v1/assistants \
  -H "Authorization: Bearer $LOOKIO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Support",
    "context": "You are the support assistant of Acme. You answer customers who want a quick, accurate reply.",
    "resource_ids": ["RESOURCE_ID"]
  }'

Note the assistant’s data.id.

Ask a question

Terminal
curl https://api.lookio.app/v1/assistants/ASSISTANT_ID/query \
  -H "Authorization: Bearer $LOOKIO_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{ "question": "How long do I have to return an item?" }'

data.answer holds the answer, data.citations the passages behind it, and data.credit_cost what it cost. The default mode is Flash, 30 credits.

Next steps

Use these docs with your AI tools

An AI agent can read this documentation directly. You do not need an account or an API key. Everything here is public and read-only.

Query these docs via MCP

Recommended

Add this server to Claude, Claude Code, Cursor, Mistral, or any tool that supports MCP. Your agent can then search Lookio Docs documentation and read it in full, instead of answering from memory.

https://lookio.app/docs/mcp
  • searchFind the passages that answer a question.
  • fetchRead one page in full, as Markdown.
  • list_pagesSee every page in this documentation.

Query these docs over HTTP

The same tools also work as plain web requests. Use this for scripts, or for any tool that does not support MCP. There is one endpoint per tool. Arguments go in the query string, and the answer comes back as JSON.

https://lookio.app/docs/api/docs/search?query=custom+domain

Read the OpenAPI description. It is built from the same definitions as the tools, so it always matches what the endpoints do.

Read these docs as Markdown

Add .md to any page URL to get its Markdown source. You can also send the headerAccept: text/markdown to the page URL itself.

To read the whole documentation in one file, open llms-full.txt. For a short index of every page, open llms.txt.