Linking Writesonic 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.

Writesonic tracks your brand's visibility in AI search — how often, how prominently, and in what context AI platforms like ChatGPT, Perplexity, and Google AI Overviews mention your brand (GEO, generative engine optimization). This connector pulls your daily performance metrics, raw AI answers with brand mentions, citations, keywords, tracked configuration (topics, prompts, platforms, websites), and content optimization pages, issues, and recommended fixes into the PostHog data warehouse, where you can join AI visibility with your product analytics.
Prerequisites
You need a Writesonic account on a plan with API access to GEO data, with at least one website tracked. Your API key is revealed in the API dashboard of your Writesonic account.
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.
Connect Writesonic to pull your GEO (generative engine optimization) data - brand visibility, rank, and mentions across AI platforms like ChatGPT and Perplexity - .
You'll need:
- A Writesonic API key with GEO API access (revealed in your account's API dashboard; requires a plan with API access)
- The site URL of the tracked website, exactly as configured in Writesonic (e.g.
https://example.com) - Optionally, a project ID to disambiguate when the same site is tracked in multiple projects
You'll be asked for:
- API key: for example
Your Writesonic API key. - Site URL: for example
https://example.com.
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.
The performance and content tables (performance_summary, performance_prompts, performance_answers, content_citations, content_keywords) are exported one UTC day at a time and sync incrementally by date — the first sync backfills up to the last 365 days, and each later sync picks up from the last synced day. The configuration tables (topics, platforms, websites, prompts) are small and sync as full refresh. The content optimization tables (content_optimize_pages, content_optimize_issues, content_optimize_recommendations, content_optimize_issues_summary) sync as full refresh. The issues and recommendations tables make one request for each page in the content optimization pages list.
Configuration
| Option | Type | Required |
|---|---|---|
API key | password | Yes |
Site URL | text | Yes |
Project ID (optional) | text | No |
Supported tables
| Table | Description | Sync method | Incremental field | Primary key |
|---|---|---|---|---|
performance_summary | Only syncs the last 365 days on initial sync | Incremental, Full refresh | date | date, website_id |
performance_prompts | Only syncs the last 365 days on initial sync | Incremental, Full refresh | date | date, prompt_id |
performance_answers | Only syncs the last 365 days on initial sync | Incremental, Full refresh | date | date, response_id |
content_citations | Only syncs the last 365 days on initial sync | Incremental, Full refresh | date | date, citation_id |
content_keywords | Only syncs the last 365 days on initial sync | Incremental, Full refresh | date | date, id |
topics | The topics configured for the tracked site. Prompts are grouped under topics. | Full refresh | — | topic_id |
platforms | The AI platforms/models (e.g. ChatGPT, Perplexity, Google AI Overviews) enabled for the tracked site. | Full refresh | — | platform_id |
websites | All websites associated with the tracked site: your own properties and every tracked competitor. | Full refresh | — | website_id |
prompts | All prompts (queries) configured for the tracked site, with their topic, country, and status. | Full refresh | — | prompt_id |
content_optimize_pages | Pages of the tracked site in Writesonic content optimization, with their citation counts, the websites AI answers cite instead, the issues found on each page, and the optimization status. | Full refresh | — | optimization_page_id |
content_optimize_issues | Content optimization issues found on each page of the tracked site, one row per issue. | Full refresh | — | optimization_page_id, issue_id |
content_optimize_recommendations | Recommended fixes for the content optimization issues of each page, one row per fix. | Full refresh | — | optimization_page_id, id |
content_optimize_issues_summary | Content optimization issue counts across all pages of the tracked site, one row per issue type and sub-type. | Full refresh | — | issue_type, sub_issue_type |
Troubleshooting
- Invalid or inactive API key — the key is wrong or was deactivated. Check the key in your Writesonic API dashboard and reconnect.
- Site not found — Writesonic couldn't match the configured site URL (and project ID, if set) to a tracked website in your account. Copy the URL exactly as it appears in your Writesonic workspace.
- Plan does not include API access — GEO data exports require a Writesonic plan with API access. Upgrade your plan and reconnect.
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.





