Docs
Concepts

How CogniWeave works

The memory model

CogniWeave turns your raw files into compact, searchable "memory units." Each unit is linked to the source file (and page where applicable) so answers stay traceable.

Getting started
Two ways to use CogniWeave

Ingestion lifecycle

  1. 1
    Uploadyour file is accepted and queued; an ingestion job is created to track it.
  2. 2
    Parsetext is extracted using a parser matched to the file type (PDF, Word, Excel, PowerPoint, email, HTML, images, plain text).
  3. 3
    OCRscanned PDFs and image files are automatically run through OCR so their text becomes searchable.
  4. 4
    Cleanmarkup and boilerplate are stripped and the text is normalized.
  5. 5
    Compressthe cleaned text is distilled into compact memory units.
  6. 6
    Embedeach memory unit is converted into a vector embedding so it can be searched by meaning.
  7. 7
    Index & consolidateunits are stored and closely related units are merged into higher-level summaries.
  8. 8
    Readythe file is marked complete and becomes searchable and answerable.
Pipeline
From file to memory

Hybrid retrieval

Searches combine three signals — semantic similarity (meaning), lexical keyword matching, and symbolic filters (time ranges, people, entities, and tags). Results are ranked and each one is traceable to its source file and page.

Cited answers

When an AI agent answers a question, it doesn't improvise. It retrieves the most relevant memory units from your own data, composes an answer grounded in those units, and cites them inline. If your memory doesn't support an answer, the agent says so instead of guessing. The example below walks through a customer-support agent handling a refund request end-to-end.

Agent in the loop
How an AI agent answers — grounded, not guessed
Worked example
A refund question, answered two different ways
1
The situation

A customer asks your support chatbot: “I'd like a refund on invoice #1042.” The catch — your refund policy wording changed last month, but invoice #1042 was issued under the earlier terms.

A generic AI

Answers from its general training or whatever policy text it last saw. It guesses — fluently and confidently — and tells the customer the wrong thing: “Sorry, refunds aren't available.” That's a hallucination: plausible, and wrong.

CogniWeave

Retrieves the exact terms that applied to invoice #1042 on its order date, plus the policy in force then — each one cited. The agent answers only from those retrieved facts: “Per the terms on invoice #1042 (12 Mar), a refund applies within 30 days — you're covered. [1][2]” Correct, cited, and identical every time.

Grounding every answer in cited, retrieved memory — with the right historical context — is the only reliable way to stop AI hallucination. Structured, factual, deterministic.

Why this stops hallucinations

Grounded answers, not guesses

  • 1Every fact is retrieved and cited from your own memory — never invented by the model.
  • 2Answers carry the correct historical version of the facts, with timestamps and citations.
  • 3If your memory doesn't support an answer, the agent says so instead of guessing.
  • 4The result is structured, factual, and deterministic — grounding answers in cited memory is the only reliable way to stop AI hallucination.

Workspaces & isolation

Your data lives in your own workspace. Every API request is automatically scoped to your workspace using your access token.

Isolation
Every account is its own tenant

Your data is sealed inside your own tenant. A token only ever unlocks the memory it belongs to.

Supported file types

CategoryExtensions
Documents.pdf, .docx, .doc, .rtf, .txt, .md
Spreadsheets.csv, .xlsx
Presentations.pptx
Email.eml, .msg, .mbox
Web/Data.html, .json
Images (OCR).png, .jpg, .jpeg, .webp, .tiff

Max upload size: 50 MB per file.

File statuses

StatusMeaning
queuedwaiting to process
processingbeing parsed/indexed
successindexed and searchable
failedcould not be processed — see error
skippednothing to index

Job statuses

StatusMeaning
queuedwaiting to start
runningactively processing
successall files succeeded
failedthe job did not complete
partialsome files succeeded, some failed

Configurable settings

OCR can be toggled and its language set; chunk size and overlap can be tuned per workspace via the API (see /api/settings/workspace).