Linking Devin AI as a source
Let AI connect your sources for you
Skip the manual setup — run this in your project and the wizard auto-detects your databases and APIs and connects them to PostHog.
Contents
This source is currently in alpha. The interface and available tables may change.
The Devin AI connector syncs sessions, playbooks, knowledge notes, and more into the PostHog data warehouse, so you can analyze them alongside your product data.
Prerequisites
Credentials that can read the data you want to sync. PostHog only reads data, so read access is enough.
Adding a data source
- In PostHog, go to the Sources tab of the data pipeline section.
- Click + New source and click Link next to this source.
- Enter your credentials (see Configuration below) and click Next.
- Select the tables you want to sync, choose a sync method and frequency, then click Import.
Once the syncs are complete, you can start querying this data in PostHog.
Enter your Devin service user API key and organization ID to sync your Devin data.
Create a service user API key (prefixed cog_) in your Devin organization settings. The service user needs the following organization-level permissions:
ViewOrgSessions- SessionsManageAccountKnowledge- Playbooks and Knowledge notesViewOrgMembership- MembersManageOrgSecrets- Secrets (metadata only; values are never synced)
Your organization ID is the org-... identifier shown in your Devin organization settings.
You'll be asked for:
- API key: for example
cog_.... - Organization ID: for example
org-....
Sync modes
Each table can be synced in one of several modes, depending on what the source supports:
- Webhook (when available) – the source pushes changes to PostHog in real time. Fastest freshness, lowest ongoing cost, and the only mode that reliably captures updates and deletes.
- Incremental – only new or updated rows are synced on each run, using a cursor field (such as an
updated_attimestamp). Cheaper than a full refresh, but deletes aren't captured. - Append only – new rows are appended using a cursor field; existing rows are never updated. Ideal for immutable, append-only tables like event logs.
- Full refresh – the whole table is reloaded on every sync. Use it when a table has no reliable cursor or when you need deletions reflected.
See sync methods for a full explanation of how each mode works and how to choose between them.
All Devin AI tables are full refresh. Each sync replaces the contents of the table.
Configuration
| Option | Type | Required |
|---|---|---|
API key | password | Yes |
Organization ID | text | Yes |
Supported tables
| Table | Description | Sync method | Incremental field | Primary key |
|---|---|---|---|---|
sessions | A Devin agent session — one run of the autonomous engineer against a task, including its status, consumed ACUs, and any pull requests it opened. | Full refresh | — | session_id |
session_insights | Devin's own read on a completed session: the same session record plus message counts, a size band, and the AI-generated analysis of how the run went. | Full refresh | — | session_id |
session_messages | A single message in a Devin session's conversation, from either the user or Devin. Messages are returned in chronological order. | Full refresh | — | session_id, event_id |
playbooks | A reusable Devin playbook — a saved set of instructions that can be attached to sessions. | Full refresh | — | playbook_id |
knowledge_notes | An org-level knowledge note that Devin can reference while working. | Full refresh | — | note_id |
automations | A Devin automation: a workflow that starts or messages Devin sessions when a trigger fires, such as a Slack message, a GitHub or Linear event, a schedule, or an incoming webhook. | Full refresh | — | automation_id |
members | A member of the Devin organization. Join sessions.user_id to members.user_id to resolve who ran a session to their email and name. | Full refresh | — | user_id |
consumption_daily | Agent Compute Units the organization consumed on one day. Days run midnight to midnight Pacific, which is the boundary Devin bills on. | Full refresh | — | date |
consumption_daily_users | Agent Compute Units one organization member consumed on one day. The per-person split of consumption_daily, so spend can be attributed to people. | Full refresh | — | user_id, date |
secrets | Metadata for an org-level secret available to Devin sessions. Secret values are never returned by the API and are not synced. | Full refresh | — | secret_id |
Troubleshooting
- If the connection fails with an authorization error, the API key is wrong, expired, or has been revoked. Create a new one, then reconnect the source.
- If a table syncs no rows, the credential may not have access to that data. Check its permissions, then reconnect the source.
If your sync is failing or data looks wrong, see the Data warehouse troubleshooting guide. If that doesn't help, contact support – we're happy to help.