Operational visibility into ingestion status, per-source stages, reprocess controls, and live logs so content teams can keep the knowledge base accurate without engineering help.
The Data Sources Dashboard is the control room for your AI assistant's knowledge. It's where administrators can see the status of every connected content source, understand what's been successfully ingested, diagnose problems, and trigger updates — all without needing to involve an engineer. This deep dive explains what the dashboard provides and why it's essential for keeping your assistant accurate and reliable at scale.
An AI assistant is only as trustworthy as the content it's working from. If a document ingestion silently fails — say, a PDF didn't process correctly — your assistant might give outdated answers or miss important information entirely. Without visibility into what's happening, you won't know until a customer complains.
Every content source (a document, a web page, a connected knowledge base) goes through several processing stages before the assistant can use it. The dashboard gives you full visibility into each stage.
You can choose exactly how much to redo when a source needs updating:
This granularity saves significant time and cost — you only redo the work that actually needs to be redone.
When you trigger a reprocess, you don't have to wonder if it's working. The dashboard streams live logs as each stage completes, and you get a job ID you can share with your team or reference in a support ticket.
To prevent accidental overload:
- Only organization administrators can trigger reprocess jobs
- There's a limit on how many concurrent reprocess jobs can run per organization
- All actions are logged with the operator's identity and timestamp
The team is building:
Once live, your operations team will have everything they need to keep the knowledge base healthy and up to date, without relying on engineering support for routine maintenance.