AI Content Classification
Sort text or records into a fixed set of categories, with review for low confidence.
What it adds
A background classification pass that assigns records to labels from a versioned taxonomy, recording confidence and routing uncertain cases to a person.
What your agent is told to do
5
What your agent is told to do
5-
1
Define the taxonomy as data the app owns, not as prose inside a prompt. Every label needs a definition and examples, and the set of valid labels must be enforced on the result rather than trusted from it.
-
2
Store the taxonomy version alongside every classification, so a label applied last quarter can still be explained against the definitions in force at the time.
-
3
Record a confidence value with each result and set a threshold below which the record is marked needs review instead of being labelled. Route those to an existing queue or list rather than leaving them unclassified and invisible.
-
4
Classify in the app's existing background-job system, batched, with a token ceiling and backoff on provider errors. Do not classify inline when a record is saved, or a provider outage becomes a failure to save.
-
5
Build the input from an explicit allow-list of fields. Restricted or sensitive attributes must be excluded unless an operator has approved them for this purpose, and that approval must be recorded.
Edge cases it handles
8
Edge cases it handles
8- A model will return a label that sounds plausible and does not exist. Validate every returned label against the current taxonomy and treat an invented one as a failed classification, not as a new category.
- Confidence must be part of the contract. A result with no confidence, or one below the threshold, becomes a needs-review record rather than a quietly applied label.
- Some records genuinely belong to more than one category. Decide in advance whether the taxonomy is single or multi label, and for single-label taxonomies send genuinely ambiguous records to review instead of forcing a pick.
- Changing the taxonomy invalidates prior work. Version it, keep old versions readable, and make reclassification after a change an explicit operator action rather than an automatic sweep.
- Restricted fields must never enter the input by default. Where an operator has approved one, record who approved it and when, and exclude it again if the approval is withdrawn.
- Human corrections must outrank the model. Once a person has set a label, a later automatic run must not overwrite it, and the correction should be visible as such.
- Malformed structured output, a refusal, or a timeout must leave the record unclassified and retryable, never labelled with a default category that pollutes the counts.
- When the model is unavailable, records queue as pending classification and every downstream view that filters by category must handle unclassified records rather than dropping them.
Definition of done
9
Definition of done
9- Labels are validated against a stored taxonomy and invented labels are rejected.
- Every classification records its confidence and the taxonomy version in force.
- Results below the confidence threshold are marked needs review and appear in a queue.
- Classification runs in batched background jobs with token ceilings and backoff.
- Input fields come from a documented allow-list, with any restricted field approval recorded.
- A human-set label is never overwritten by a later automatic run.
- Provider failure leaves records pending rather than defaulted, and views handle unclassified records.
- The feature matches the existing design system.
- No existing functionality is broken.
Related features
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
AI Key Point Extraction
AI Key Point Extraction
Reduce long content to the decisions, facts, and requests that actually matter.
What it does
A short list of the salient points in a long document or thread, each tied back to the passage it came from.
How it works
- 1 Apply this where length is the problem: long threads, meeting notes, call transcripts, lengthy tickets, multi-page documents. Content that already fits on a screen does not need extracting.
- 2 Classify each point by kind — decision, fact, risk, request, open question — so a reader can scan for the category they came for instead of reading a flat list.
- 3 Carry a reference to the source passage with every point and let the reader jump to it. A point nobody can verify is a claim, not a summary.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/ai-key-point-extraction
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.