Linking The Prompting Company 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.
This source is currently in alpha. The interface and available tables may change.
The Prompting Company connector syncs AI visibility and share of voice analytics data into the PostHog data warehouse, so you can analyze LLM mentions and visibility alongside your product data.
Prerequisites
- A Prompting Company account with permission to create an organization API key.
- At least one product set up in The Prompting Company.
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.
When linking The Prompting Company, you'll need:
- API key – create one in your organization's Settings > API keys. Grant the read scopes required for the tables you want to sync (see required scopes below).
- Product ID – the product to sync data for (e.g.
product_123). Find this in your product settings. Content, suggestions, and share of voice use the product ID. Simulation runs cover the whole organization. - Analytics start date – the date to start syncing share of voice data from, in
YYYY-MM-DDformat. Must be today or earlier.
Required scopes
Each table requires a specific read scope on your API key. Only grant the scopes you need:
| Table | Required scope |
|---|---|
published_content | content:read |
prompt_suggestions | prompts:read |
simulation_runs | simulations:read |
share_of_voice | analytics:read |
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.
| Table | Sync methods |
|---|---|
published_content | Full refresh |
prompt_suggestions | Full refresh |
simulation_runs | Full refresh |
share_of_voice | Incremental sync, full refresh |
Incremental sync for share_of_voice uses the date field. Older revised analytics may require a lookback window or a full refresh to stay up to date.
Configuration
| Option | Type | Required |
|---|---|---|
API key | password | Yes |
Product ID | text | Yes |
Analytics start date | text | Yes |
Supported tables
| Table | Description | Sync method | Incremental field | Primary key |
|---|---|---|---|---|
published_content | Published content for the selected product. Drafts and archived content are excluded. | Full refresh | — | — |
prompt_suggestions | Suggested prompts for the selected product, with target personas and answer engines. | Full refresh | — | — |
simulation_runs | Agent simulation runs across the organization, including results, token usage, and cost. | Full refresh | — | — |
share_of_voice | Daily share of voice for the selected product, using a one-day calculation window in UTC. | Incremental, Full refresh | date | — |
simulation_runs covers the entire organization, regardless of the configured product ID. All other tables use the product ID.
Troubleshooting
- If you see an authentication error, your API key is invalid or expired. Create a new key in your organization's Settings > API keys, then reconnect.
- If you see a permissions error, your API key lacks a required read scope. Check that the key has the correct scopes (
content:read,prompts:read,simulations:read,analytics:read) for the tables you selected.
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.