Knowledge Source Sync
Keep the AI's knowledge current as documents, records, and external sources change.
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
What your agent is told to do
5-
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
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
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
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
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
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
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
Retrieval-Augmented Generation
Retrieval-Augmented Generation
Ground AI answers in the app's own content by retrieving source passages first.
What it does
A retrieval layer that selects permitted passages from app content and supplies them to the model as cited evidence.
How it works
- 1 Decide which content is answerable from and treat everything else as out of scope. A retrieval feature pointed at the whole database returns confident answers about records nobody meant to expose.
- 2 Apply the requesting user's tenant, record, and field permissions during retrieval, before any passage is assembled into a request. Filtering the answer afterwards is too late — the content has already crossed the boundary.
- 3 Chunk on the content's own structure — sections, headings, rows, message boundaries — and carry enough surrounding context in each chunk that it still means something on its own.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/retrieval-augmented-generation
AI Dashboard Insights
AI Dashboard Insights
Explain what actually changed on a dashboard, in the viewer's own filters and period.
What it does
A short generated commentary attached to a dashboard, describing the movements that matter under the filters currently applied.
How it works
- 1 Compute the numbers first, in the app, using the dashboard's existing queries with the viewer's active filters. Pass the model the computed figures and let it write the wording, never the raw rows to add up itself.
- 2 State the period and the comparison period explicitly in every insight. A sentence saying signups are up is meaningless without saying up against what.
- 3 Filter the input to metrics the viewer is permitted to see before it reaches the model. A commentary that mentions revenue to someone whose dashboard hides revenue is a permissions leak.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/ai-dashboard-insights
AI Insight Cards
AI Insight Cards
Turn a report into a few grounded cards, each tied to a number the app calculated.
What it does
A small set of cards summarising notable movements in a report, each linked to the query and figure that produced it.
How it works
- 1 Detect candidate movements in the app first, using the report's own aggregations. The model ranks and phrases the candidates it is given; it does not go looking for them and it does not produce the arithmetic.
- 2 Bind each card to the query, metric, and period that support it, and make the card link through to the filtered view so a reader can check it in one click.
- 3 Set a materiality threshold before generation, in both relative and absolute terms, so a swing on a metric with three events does not outrank a real change on a metric with thousands.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/ai-insight-cards
How it works
-
1
Copy the link
Grab the Markdown instruction URL for this feature.
-
2
Give it to your AI
Paste it into Claude Code, Cursor, v0, Lovable — whatever you build with.
-
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.