Knowledge

Cite the source.

Documents in. Ranked passages out — attached, not recalled.

How it works

Ingest. Index. Retrieve — with receipts.

Ingest

Upload files or point at a site. Extraction handles PDFs, office documents, and pages — including files already in the agent's Workspace.

Index

Content is chunked and embedded for relevance-ranked search, billed per million tokens processed — so re-index only what changes.

Retrieve

At run time the agent pulls the most relevant passages into context and cites them in its answer. Every search is journaled, like any other capability call, and billed at its published per-query rate.

What it looks like

Answers with the source attached.

knowledge_search · journaled
knowledge_search("termination notice period — Acme MSA")
→ 3 passages · 214ms
  [1] acme-msa-2025.pdf · §12.4  "…either party may terminate with
      sixty (60) days' written notice…"
  [2] acme-msa-2025.pdf · §12.6  "…obligations surviving termination…"
  [3] renewal-addendum.pdf · §2  "…auto-renewal unless notice per §12.4…"

agent: Sixty days' written notice, per §12.4 of the MSA [1] —
       and note the addendum auto-renews unless that notice lands [3].

Knowledge is what you give the agent; memory is what it learns on the job. They work together — retrieval grounds the facts, memory keeps the relationship — but they're separate stores with separate rules.

What it costs

Three published rates. Nothing hidden.

MeterUnitPrice
Indexed storageper GB / month (vector + search structures)$1.50
Knowledge searchper query$0.00002
Knowledge indexingper 1M tokens processed$0.20
Embedding modelsprovider price + $0.25 / 1M tokensMetered
Displayed monthly, accrued at a finer interval — you pay only while data exists. Full rate card →
Governed like everything else

Your documents stay yours.

· Account-scoped

Every document, chunk, and vector is isolated to your account. Retrieval can't cross tenants.

· Journaled

Every retrieval is on the record — what was asked, what was returned, and when.

· Never trained on

Ingested content serves your agents. It doesn't train models — ours or anyone's.

The full trust story →

Ground an agent in your documents.

Ingest something real and ask about it — the $10 credit covers a lot of retrievals.