AddThisFeature

Knowledge Source Sync

Keep the AI's knowledge current as documents, records, and external sources change.

involved AI Analysis & Search

What it adds

An ingestion pipeline that syncs approved sources on a schedule, tracks versions, and removes content whose source disappears.

What your agent is told to do

5
  1. 1

    Give an operator an explicit approval step for every source, and default to nothing being indexed. Automatic inclusion of whatever the connected account can see is how private material ends up answerable.

  2. 2

    Store a content fingerprint or version for each document alongside the time of the last successful sync, and re-ingest only what has actually changed since then.

  3. 3

    Reuse the app's existing background-job system and make each sync resumable at the document level, so an interruption partway through a large source restarts from the last completed document rather than from the beginning.

  4. 4

    Remove indexed content in the same run in which its source is deleted, revoked, or made private. Content that outlives its source keeps answering questions the user is no longer permitted to ask.

  5. 5

    Query-time retrieval and answer generation belong to Retrieval-Augmented Generation, and the operator's view of index freshness belongs to Vector Index Health. This entry owns ingestion and deletion only.

Edge cases it handles

8
  • Every source needs a recorded version and a last-successful-sync time, and a run that fails must leave the previous successful state intact rather than marking the source as current.
  • When access to an external source is revoked, or a document is deleted or restricted at the source, the corresponding indexed content and its vectors must be removed promptly, not left until the next full crawl.
  • Large syncs get interrupted by deploys, timeouts, and rate limits. Progress must be checkpointed so a resumed run continues rather than reprocessing everything and re-billing the embedding work.
  • Drafts, archived items, trashed pages, private sections, and comment threads are easy to sweep up by accident. Decide explicitly which states are eligible and exclude the rest by default.
  • A run where most documents succeeded and a handful failed is the normal case. Report failures per source and per document with the reason, rather than marking the whole sync green or red.
  • Access to a third-party source expires. Refresh credentials ahead of expiry, and when a refresh fails, pause the source, tell the operator which connection needs reauthorizing, and leave the existing index in place.
  • Third-party sources throttle. Honour the retry signalling they send, back off progressively, and spread scheduled syncs so every account does not start on the same minute.
  • The same document reachable through two connected sources must not be indexed twice, or retrieval will return it twice and crowd out other evidence.

Definition of done

9
  • No source is indexed until an operator approves it.
  • Each document carries a version fingerprint and each source records its last successful sync time.
  • An interrupted sync resumes from the last completed document instead of restarting.
  • Deleting, restricting, or revoking access to a source removes its indexed content and vectors.
  • Drafts, archived, and private items are excluded unless explicitly included.
  • Partial failures are reported per source and per document with a reason and a retry.
  • Expired third-party credentials pause the source with a reauthorization prompt rather than silently ending the sync.
  • The feature matches the existing design system.
  • No existing functionality is broken.

Related features

How it works

  1. 1

    Copy the link

    Grab the Markdown instruction URL for this feature.

  2. 2

    Give it to your AI

    Paste it into Claude Code, Cursor, v0, Lovable — whatever you build with.

  3. 3

    It inspects, then implements

    Your agent reads your existing app first, then adds the feature to fit it.

Works with your stack

These instructions are written to adapt. They tell the agent to detect your framework, match your existing design system, and reuse what you already have — rather than assuming a particular stack.

Need it tighter than that? Customize the feature and tell it exactly what you're running.