IngestionCopy link to this section
Floe's ingestion pipeline reads your product's content and transforms it into the knowledge the AI agent uses to demo, onboard, and support users.
After you've created a site, ingestion is how you feed Floe the information it needs. The pipeline handles reading, processing, and indexing automatically.
How ingestion worksCopy link to this section
You give Floe the URLs to your content. Floe reads everything, processes it, and makes it available to the AI agent. When the agent is on a demo call or helping a user with in-app guidance, it draws on this knowledge to give accurate, contextual answers about your product.
Supported content typesCopy link to this section
- Documentation: Product docs sites. Best for feature references, setup guides, API docs.
- Knowledge Base: Help center articles. Best for FAQ, troubleshooting, how-to guides.
- Changelog: Release notes. Best for what's new, version history.
- YouTube Video: Video transcripts. Best for product walkthroughs, tutorials.
- Loom Video: Loom recordings. Best for internal demos, feature explanations.
- Image Gallery: Screenshots, diagrams. Best for visual product reference.
Adding an ingestion configCopy link to this section
- Go to your site in the dashboard
- Open the Ingestion tab
- Click Add Config
- Select the content type
- Enter the source URL
- Save and the pipeline starts automatically
You can add multiple configs per site. A typical setup might include your docs site (Documentation), your help center (Knowledge Base), and a few product walkthrough videos (YouTube).
Content handlingCopy link to this section
Floe handles JavaScript-heavy sites and single-page applications. It stays within the same domain and respects robots.txt.
Running ingestion multiple times won't create duplicate entries. Updated content at the same URL replaces the previous version.
Content access and retentionCopy link to this section
Self-service ingestion currently accepts publicly accessible URLs. Sources behind a login are not supported. Do not include credentials, cookies, or access tokens in a source URL.
Floe processes the public documentation and other content you configure as Customer Data only to provide the service. Customer Data is retained for your subscription and deleted within 30 days after termination, unless law requires otherwise; backups are purged within 30 days of deletion. Access is limited to your organization, authorized Floe personnel, and the service providers needed to operate Floe, as described in the Privacy Policy. Removing an ingestion config does not delete already-ingested content; remove that content separately from the Content tab. This policy is separate from session-recording retention.
Monitoring ingestionCopy link to this section
The Ingestion tab shows the status of each config:
- Pending: Queued for processing
- Processing: Currently reading and indexing
- Completed: All content ingested successfully
- Failed: Something went wrong (check the error message)
Typical processing time is 2-5 minutes for a small docs site (50-100 pages).
What's nextCopy link to this section
Once content is ingested, generated capabilities and guided workflow context must be refreshed internally before a demo reflects source changes. See the Quickstart for the full flow, or learn more about how it works.
FAQCopy link to this section
Can I ingest content behind a login? No. Ingestion currently accepts publicly accessible URLs only. Sources behind a login are not supported, and you must not provide credentials, cookies, or tokens in an ingestion configuration.
What if my docs site changes frequently? Re-run ingestion any time. Updated content replaces the previous version automatically, but generated capabilities must be refreshed internally before the demo context reflects the change.
Is there a limit on how much content I can ingest? No hard limit. Most products ingest 50-200 pages. Larger knowledge bases work fine, they just take longer to process.