AI Record Summaries
Turn a long record and its history into a short overview of what matters now.
What it adds
A generated overview of a single record's current state and recent history, marked as interpretation and regenerated when the record changes.
What your agent is told to do
5
What your agent is told to do
5-
1
Assemble the input by reading the record through the same authorization path the detail page uses, at generation time, so the summary reflects current values rather than a cached copy.
-
2
Pass factual values — dates, amounts, statuses, counts, identifiers — through unchanged and render them from the record itself rather than from the generated text, so a rounding or transcription error is impossible.
-
3
Label the summary clearly as generated interpretation, and keep the underlying fields visible on the same screen so a reader can check any statement against the source.
-
4
Regenerate when a field that materially changes the picture is written — status, owner, amount, stage — and mark the existing summary stale in the meantime rather than showing it as current.
-
5
Thread and message summarisation belongs to AI Conversation Summaries. This feature covers the record's fields and activity history; do not summarise attached discussions here.
Edge cases it handles
8
Edge cases it handles
8- A summary built from a stale cache will describe a status the record no longer has. Read live at generation time and record which version of the record produced the text.
- Numbers and dates must be exact. Do not let the model restate a figure in prose; render the real value and let the narrative reference it.
- Interpretation presented as fact is the main risk in this feature. Separate what the record says from what the model concludes, and mark the second as such.
- When a material field changes, the old summary becomes misleading. Mark it stale immediately and regenerate in the background rather than leaving it looking fresh.
- Internal notes, restricted fields, and audit entries a viewer cannot open must never appear in the summary text, including paraphrased.
- Records with almost no content produce padded, meaningless summaries. Set a content threshold and show the record plainly instead.
- Regenerating on every write is expensive on busy records. Debounce, cap regenerations per record per day, and skip when only cosmetic fields changed.
- When the model is unavailable or refuses, the record page renders normally with the summary area showing an unavailable state.
Definition of done
9
Definition of done
9- Summaries are generated from a live authorized read and record the record version they describe.
- Dates, amounts, and statuses shown alongside the summary come from the record, not from generated text.
- The summary is labelled as interpretation and sits beside the underlying fields.
- A material field change marks the summary stale and queues a regeneration.
- Restricted fields and internal notes never appear in the summary, including in paraphrase.
- Regeneration is debounced and capped per record, and cosmetic edits do not trigger it.
- The record page is fully usable when the model is unavailable.
- The feature matches the existing design system.
- No existing functionality is broken.
Related features
Natural Language Filters
Natural Language Filters
Let people describe what they want to see and turn it into filters they can inspect and edit.
What it does
A plain-language input on list views that produces the app's normal filter chips, shown for review before they apply.
How it works
- 1 Give the model a machine-readable description of the filterable fields, their types, their allowed operators, and their permitted values, derived from the app's existing filter definitions. It selects from that description and returns a structured filter set; it does not write query syntax.
- 2 Render the result as the app's ordinary filter controls, in the pending state, and require the user to apply them. Do not run the query on the model's output directly, and do not skip the review step even when confidence looks high.
- 3 Resolve relative expressions such as last week or this quarter against the user's time zone and the workspace's week and fiscal-year settings, and show the resolved absolute dates in the chip so the user can see what was assumed.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/natural-language-filters
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
AI Trend Analysis
AI Trend Analysis
Explain what a chart is actually showing, in sentences backed by computed numbers.
What it does
A written summary attached to a time series or metric set, describing direction, magnitude, and comparison period.
How it works
- 1 Compute every number in ordinary code before the model is involved: the change, the rate, the comparison period, the baseline, the seasonal adjustment. The model writes prose about figures it is given and must never produce a figure of its own.
- 2 State the comparison window and the time zone in the summary text, resolved from the workspace's configured zone rather than the server's. A change described as week over week is meaningless without saying which weeks.
- 3 Instruct the model to describe what the data shows and to stop there. Do not let it assert causes, attribute movement to campaigns or releases, or predict what happens next.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/ai-trend-analysis
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.