Skip to Content
Platform
How-toAnswer from your documents

Answer from your documents

The agent reads your documents and cites the file and page, instead of answering from memory.

The agent answers from documents it opens with its tools. Pick where they live:

DocumentsPut themThe agent finds them with
A small fixed set (policies, a price list)The recipe’s files/ foldergrep and read
Different per task, up to 100 filesUploads attached to the taskread, and the documents tool for PDF and Word
Spreadsheets or presentationsUploads attached to the task, with document tools in the recipeA view_file tool you add
More than 100, or changing (a wiki, a data room)Your search or storage MCP serverThat server’s tools

You need: a recipe you can change (Build).

1. Ship a small set with the recipe

Put text or Markdown (not PDF: grep can’t search it) in a subfolder of files/, and give the agent the file tools.

agents/agent.yaml
tools: [read, grep, find, ls, bash]
SYSTEM.md
Answer only from the documents in /workspace/files/policies/. Search them with grep, read the matching file, and cite its name. If nothing matches, say so.

files/policies/refunds.md arrives read-only at /workspace/files/policies/refunds.md.

2. Attach documents per task

introspection tasks create --runtime support-agent -e production \ --file @./contract.pdf --prompt "Does this contract allow early termination?"

A task takes up to 100 attachments, each up to 25 MB (Send files in and out). Read PDF and Word attachments with the documents tool: declare the formats and add it to the agent’s tools (Read Word and PDF files).

package.json
{ "pi": { "documents": [{ "format": "pdf" }, { "format": "docx" }] } }
agents/agent.yaml
tools: [read, grep, find, ls, documents]

3. Cite the page

The documents tool’s read returns a PDF page by page, so every quote has a page number:

SYSTEM.md
Read PDFs and Word files with the documents tool. Cite every figure and quote as (file name, p. N). Never cite a page you did not read.

To require citations rather than hope for them, make sources a required field of a submit tool.

4. Review a large set

Past 100 files, or for a findings grid across a data room:

  • Search: bind a search or storage server holding the set (MCP).
  • Fan out: start one task per document, in waves (batch), each writing one small JSON output, then merge them in your code.
  • Split in one task: the main agent hands documents to helpers, up to 64 running at once (Split work across agents).

Verify

introspection local -p "What is our refund window? Cite the file." introspection conversations get <task-id> -o json \ --query "items[?attributes.gen_ai.operation.name=='execute_tool'].attributes.gen_ai.tool.name"

Run introspection local from the recipe directory. Expect an answer naming a file, and grep, read, bash, or search calls in the cloud task.

Or ask your agent: “Make support-agent answer only from files/policies and cite file and page.”

Limits

Not supportedDo this instead
A built-in vector indexYour search server (step 4).
More than 100 attachments per taskSearch, or fan out (step 4).
Reading Word files with read or grepThe documents tool.
Reading Excel or PowerPoint files with read or grepAdd document tools to the recipe.
Scanned PDFs as textThe documents tool’s render, then read the page images with a vision model.
One shared search key for every end userAuthorize an application on the endpoint and filter on the JWT sub.
Last updated on