Ask your documents
Ask fact, comparison, and summary questions across your organization's documents and get an answer whose every claim quotes the passage it came from. When the evidence is weak, Colrows says so instead of guessing. Complete queries go further and read every document to count, sum, or list matches. To connect or upload documents first, see Document sources.
Where you ask
Open Docent → Ingestion Pipelines and choose Ask a Question under Ask About Documents. A question covers every document your organization's connections have synced and indexed; there is nothing to select. Any member of the organization can ask. Files uploaded as knowledge in Consensus → Document Upload are not used. See Document access for which documents count.
A follow-up question can refer to the earlier conversation ("what is its notice period?"). The conversation only helps rewrite the question; it is never used as evidence.
Ask from an agent
Agents ask the same questions through the askDocuments tool on the Colrows MCP server, or POST /api/agents/v1/document-questions on the agent REST API. The client needs the documents:read scope. The body takes a question, an optional mode (AUTO, FACT, COMPARISON, or SUMMARY; default AUTO), and, for a comparison, two to four subjects. The answer is verified exactly as it is for a signed-in user. Complete queries are not available through this tool. See MCP & REST API.
Question types
| Type | Use it for |
|---|---|
| Automatic | Let Colrows pick the right mode for the question. |
| Fact | A single answer backed by specific passages - "what is the notice period in the Acme contract?" |
| Comparison | Compare a point across subjects, with evidence gathered from each in turn. |
| Summary | Summarise every document. Available while the organization has at most 100 documents, all fully processed. |
How an answer is built
- Colrows retrieves candidate passages with hybrid search - dense and sparse vectors - and reranks them.
- A model drafts the answer as separate claims, each carrying an exact quote and the element it came from.
- Every quote is checked in code to be a verbatim substring of the source. Claims whose quote is not found are dropped.
- A second, independent model pass reviews each remaining claim and removes any it cannot support.
- The platform verifies the answer once more before returning it.
Each claim shows a Source button that opens the cited passage: the quote, its page, heading path, and element, any table with its headers, and a link to download that exact version of the original document.
Answer statuses
| Status | Meaning |
|---|---|
| Answered | Supported claims, each with a citation. |
| Partial | Answered as far as the evidence goes, with the gaps and limitations listed. |
| Abstained | No answer: the evidence was missing or too weak, or a comparison had too few subjects. Colrows shows the closest passages so you can judge for yourself. |
| Unavailable | The question asks for something this mode cannot do safely - for example a count or "list all", which belong to a complete query (below). |
Complete queries: count, sum, and list
A ranked search answers "what does the evidence say?" It cannot answer "how many?" - the top results are not the whole set. Complete queries close that gap by reading every document in the organization, up to 1,000.
- Complete count - how many documents match.
- Complete sum - a total across the matching documents. You name the amount to extract (for example
contract_value) and its exact unit (for exampleUSD). - Complete match list - the documents that match, with evidence.
Each document is given a definite outcome - Match, No match, Ambiguous, or Unreadable - with a quote for the decision. A final number is returned only once every document has a definite outcome, so a total is never built from a partial read. Progress and per-document outcomes are shown while the query runs.
This is the document equivalent of the SQL compiler's explicit error: an answer quotes its source, or Colrows tells you the evidence is not there. Answers are not combined with SQL query results today.