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

# Sub-processors

> Every third party involved in running Agentick, and what reaches each one.

A sub-processor is a third party that processes data on our behalf. This is the
complete list for the platform as it stands.

<Note>
  We will give notice before adding a sub-processor that receives customer data.
  If you need that commitment in contract form, ask — it belongs in the DPA
  rather than on a page we can edit.
</Note>

## Message content

One sub-processor receives anything a person typed.

<ResponseField name="TypeSafe" type="Message classification" required>
  **What reaches them:** the text of a message addressed to your agent, and the
  word `slack` or `linear`. Capped at 4,000 characters. No identifiers of any
  kind. [Full detail](/trust/what-leaves).

  **Why:** to decide whether an inbound message is work, so that a greeting does
  not open a billable case and a real request is never silently dropped.

  **Model:** a pinned version, so answers cannot change under us without a
  deliberate change on our side.

  **Their commitments:** TypeSafe state that their model is not trained on
  customer requests or responses. See [Retention](/trust/retention) for what we
  have and have not contracted for.
</ResponseField>

## Platform infrastructure

These receive operational data — accounts, connections, telemetry — and none of
them receive your source code.

| Sub-processor             | Purpose                                                           | What reaches them                                                                              |
| ------------------------- | ----------------------------------------------------------------- | ---------------------------------------------------------------------------------------------- |
| **Amazon Web Services**   | Hosting for the control plane, database and object storage        | Case state, transitions, decisions, timings, spend records, and artifacts you choose to upload |
| **WorkOS**                | Authentication, SSO and directory sync for your team's logins     | Names, work email addresses, and your directory's group membership                             |
| **Nango**                 | The OAuth lifecycle for your Slack, Linear and GitHub connections | The connection tokens themselves, encrypted at rest                                            |
| **Slack, Linear, GitHub** | The tools your agent works in                                     | Whatever the agent reads and writes there, at your instruction                                 |

Traces go to whichever target you chose at enrollment — ours or your own
self-hosted instance. If you chose your own, no trace data reaches us at all.
See [Where things run](/trust/where-things-run#traces).

## Who receives nothing

Worth saying explicitly, because it is the question behind the question:

* **No model provider receives your source code from us.** Prompts containing
  your code go from your machine to your provider on your key. We are not in
  that path and could not insert ourselves into it.
* **No sub-processor holds a credential to your repositories**, because
  [we do not hold one either](/trust/where-things-run#we-hold-no-repository-credential).

## If you are filling in a questionnaire

The two answers people usually need:

* **Data residency:** the control plane runs in AWS `ap-south-1`. If your
  procurement requires a specific region, tell us before you sign rather than
  after — it is a real constraint on where we can put your tenant, not a
  checkbox.
* **Sub-processor change notice:** see the note at the top of this page, and get
  it in the DPA.