> For the complete documentation index, see [llms.txt](https://thecontentforge.gitbook.io/thecontentforge-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://thecontentforge.gitbook.io/thecontentforge-docs/feature-guides/data-ingestion.md).

# Data Ingestion

Data Ingestion is how outside data gets into TheContentForge. Alongside manual performance exports, it brings in newsletter feeds, brand accounts you want to track, and your product knowledge - plus tools to tidy up imported rows. The freshness and completeness of what's ingested directly determines the quality of the [Dashboard](/thecontentforge-docs/feature-guides/dashboard.md) and [Patterns](/thecontentforge-docs/feature-guides/patterns.md).

### Who can use it

Editor and Admin only. Members don't see this page.

### What you upload

Per-platform analytics exports covering at least the last 7 days:

* X - post-level analytics export
* Instagram - Insights export
* Facebook - Page Insights export

Use the platform's native export; TheContentForge handles parsing.

### The Monday workflow

The sidebar highlights **Data Ingestion** with a "MON" badge every Monday. The recommended cadence:

1. Monday morning: pull the previous 7 days of analytics from each platform
2. Upload each file in Data Ingestion
3. Confirm the row counts and date range match what you exported
4. Open the Dashboard to verify the new data has landed

### Workflow

1. Open Data Ingestion
2. Select the platform and the file
3. Upload; the platform processes and validates the file
4. Review the import summary (row count, date range, any rejected rows)
5. If something looks off, re-export and re-upload; duplicates are deduped on import

### How it fits with My Account > Social Connections

Data Ingestion is for manual analytics exports. [My Account > Social Connections](/thecontentforge-docs/feature-guides/social-connections.md) can also fetch analytics for tracked connected profiles. Both paths help keep Dashboard and Patterns current.

### Knowledge Base tab

The Ingestion page also hosts the **Knowledge Base** tab, where editors and admins ingest your product docs (a GitBook, sitemap, PDF, or Markdown) for the in-app reader, *Ask your Knowledge Base*, and as generation context. It's a separate system from analytics ingestion - see [Knowledge Base](/thecontentforge-docs/feature-guides/knowledge-base.md) for the full guide.

### RSS Feeds tab

Add the newsletters and blogs you want to keep an eye on by pasting their RSS feed URLs. TheContentForge polls each feed and pulls in new items, so fresh source material is ready when you sit down to create - no manual copy-and-paste.

### Brand Accounts tab

Register the brand handles you want to track. Once an account is added, its activity feeds into your analysis so you can benchmark against competitors and keep tabs on the accounts that matter to you.

### Reconciliation Queue tab

When imported rows can't be matched automatically - a renamed account, a near-duplicate, or an ambiguous entry - they land in the Reconciliation Queue. Review each item and confirm, merge, or discard it so your data stays clean and duplicate-free.

### Algorithm Sources tab

Manage the signals behind platform-algorithm guidance from this tab. It's documented in full under [Algorithm Watch](/thecontentforge-docs/feature-guides/algorithm-watch.md).

### Tips

* Always export with **the longest date range your tool allows** for the period; partial files cause gaps in Patterns
* Don't skip a week. Gaps degrade trend analysis disproportionately
* If you forget a week, just upload it when you remember; the system will fill in


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://thecontentforge.gitbook.io/thecontentforge-docs/feature-guides/data-ingestion.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.