> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vexa.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Redaction — identifiers stripped before storage

> Strip names, account numbers and other identifiers out of a meeting transcript before it is written to storage, inside your own infrastructure.

**Can Vexa strip names and account numbers out of a transcript before storing it?**

**Today:** No. Transcripts are stored as captured.

**Sponsorable:** yes — A redaction pass ahead of storage, so the stored artifact never carries the identifiers.

***

*Strip names, account numbers and identifiers before the transcript is stored.*

|                 |                                                |
| --------------- | ---------------------------------------------- |
| **Status**      | **sponsorable**                                |
| **Size**        | size pending                                   |
| **North star**  | 3 · Your data, your rules                      |
| **Measured by** | controls shipped with an API and an audit line |

## What it does

* Detects named entities and identifiers in the transcript.
* Removes them before storage, not after the fact.
* Runs inside your own infrastructure.

## What exists today

Transcripts are stored as captured.

## What this adds

A redaction pass ahead of storage, so the stored artifact never carries the identifiers.

## How sponsorship works

You fund the item. It moves to the front of the queue. You co-write the acceptance criteria, so "done" means done on your meetings. Your name goes on the release note. Sponsorship buys **the order of the queue** — never exclusivity, never a private build, and never a date the work has not earned. The fee basis is per item or per stage, agreed in writing before work begins.

## Two doors

<Columns cols={2}>
  <Card title="Sponsor this" icon="handshake" color="#0D9373" href="https://cal.com/dmitrygrankin/web?utm_source=docs&utm_medium=roadmap&utm_campaign=sponsor&utm_content=redaction" horizontal arrow cta="Book fifteen minutes">
    Fifteen minutes. Bring the constraint you are under.
  </Card>

  <Card title="Watch this" icon="envelope" color="#0D9373" href="mailto:dmitry@vexa.ai?subject=Roadmap%20update%3A%20Redaction%20%E2%80%94%20identifiers%20stripped%20before%20storage&body=watch" horizontal arrow cta="Email me">
    One email when it ships. The mail is already written — send it as it is.
  </Card>
</Columns>

## Questions

<AccordionGroup>
  <Accordion title="Can Vexa strip names and account numbers out of a transcript before storing it?">
    No. Transcripts are stored as captured.
  </Accordion>

  <Accordion title="What would sponsoring this add?">
    A redaction pass ahead of storage, so the stored artifact never carries the identifiers.
  </Accordion>

  <Accordion title="Where does it run?">
    On your own infrastructure. Vexa is Apache-2.0 and self-hosted — the audio and the transcript stay inside it.
  </Accordion>
</AccordionGroup>

***

*Ships upstream Apache-2.0 when sponsored.*