AI Image Captioning
Describe images so they can carry a visible caption and be found by search.
What it adds
A generated description stored per image, offered as a draft caption and indexed for search.
What your agent is told to do
5
What your agent is told to do
5-
1
Store the generated description in its own field and decide explicitly whether each surface shows it, indexes it, or both. Do not write it into the alt attribute, which belongs to AI Image Alt Text and answers a different question.
-
2
Offer the description as a draft caption the user can accept or rewrite, and leave any caption a human already wrote untouched unless they explicitly ask for a replacement.
-
3
Index the description alongside the image's existing metadata so images become findable by what is in them, and reuse the app's existing search infrastructure rather than adding a parallel one.
-
4
Have the model report what it could not determine, and render uncertainty plainly in the draft. A description that hedges is useful; one that confidently names the wrong object poisons search results.
-
5
Run generation through the app's existing background-job system with a per-image and per-account cost ceiling, and make it resumable so a large library can be processed across multiple runs.
Edge cases it handles
8
Edge cases it handles
8- A caption and an alt attribute are different artifacts. A caption adds context a sighted viewer cannot infer; alt text substitutes for the image entirely. Storing one in the other's field degrades both.
- Real people must not be named or identified from an image alone. Allow a description of what a person is doing without asserting who they are, and do not infer relationships or affiliations.
- Uncertain objects and unreadable text must be flagged as uncertain rather than resolved into a confident guess, and the draft must show that flag to the reviewer.
- A user-written caption is authoritative. Regeneration must not replace it, and a bulk pass must skip images that already have human text.
- Unsupported formats, images too small to describe, corrupt files, and images the account has marked private must be skipped cleanly with a recorded reason, not retried forever.
- Decide before shipping whether images may be sent to the provider at all for a given account, and honour a workspace setting that forbids it rather than exempting the feature.
- A refused, timed-out, or truncated response must leave the image with no description and a retryable status, and the surrounding page must render normally without one.
- Regenerating descriptions across a library must not multiply cost invisibly; show the estimated volume and require confirmation before a bulk run starts.
Definition of done
9
Definition of done
9- Generated descriptions are stored in a dedicated field, separate from alt text.
- Drafts are offered for approval and existing human captions are never overwritten.
- Descriptions are indexed and images become findable by their content through the app's existing search.
- Uncertain objects and unreadable text are marked as uncertain rather than guessed.
- Real people are not identified by name from an image alone.
- Unsupported, corrupt, or excluded images are skipped with a recorded reason and no retry loop.
- Bulk generation runs in the background under a stated cost ceiling and is resumable.
- The feature matches the existing design system.
- No existing functionality is broken.
Related features
Multimodal Image Analysis
Multimodal Image Analysis
Let users ask questions about screenshots, photos, charts, and interface images.
What it does
Image input on AI conversations, with safe downscaling, grounded answers, and defined retention of derived copies.
How it works
- 1 Prepare images before they are sent: correct orientation, strip location and camera metadata, and downscale to the smallest size that still keeps small text and fine detail legible.
- 2 Require the answer to distinguish what is visible in the image from what is inferred, and to say when the image is too low in quality to support a conclusion.
- 3 Label and reference images explicitly when more than one is attached, so a question about the second chart is not answered from the first.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/multimodal-image-analysis
AI Changelog Drafting
AI Changelog Drafting
Turn merged work into a changelog draft written for customers, not for engineers.
What it does
A grouped, customer-facing changelog draft generated from merged work items or release notes for a nominated release, held for review before publishing.
How it works
- 1 Take the set of work items belonging to one nominated release as input, and require each item to carry a shipped marker before it is eligible. Unreleased and reverted work must be excluded at the input stage, not filtered out of the prose afterwards.
- 2 Rewrite each item as the outcome a customer notices rather than the change that was made, and keep a link from every drafted line back to the underlying item so a reviewer can check it.
- 3 Group related items under headings the reader would recognise, and keep fixes as their own visible section rather than absorbing them into a feature summary.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/ai-changelog-drafting
AI Knowledge Base Drafting
AI Knowledge Base Drafting
Turn a solved support issue into a help article draft a writer can finish.
What it does
A structured, unpublished help article draft generated from a resolved ticket or a set of product notes, with unverified content marked and customer details removed.
How it works
- 1 Take a resolved ticket thread or a set of product notes as input and produce a draft in the app's existing article structure — title, summary, prerequisites, steps, related links — rather than one block of prose.
- 2 Strip customer identity before the content is sent anywhere: names, addresses, account identifiers, order numbers, and anything else that identifies the person or their organisation. Remove it at the point the input is assembled.
- 3 Mark the steps that were confirmed to resolve the issue separately from the ones that were tried and abandoned during troubleshooting. A draft that presents a failed experiment as instruction is worse than no draft.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/ai-knowledge-base-drafting
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.