AI Changelog Drafting
Turn merged work into a changelog draft written for customers, not for engineers.
What it adds
A grouped, customer-facing changelog draft generated from merged work items or release notes for a nominated release, held for review before publishing.
What your agent is told to do
5
What your agent is told to do
5-
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.
-
4
Pass the app's current product and feature names in as fixed terms the draft must reproduce exactly, and flag any name in the draft that does not match the product's own vocabulary.
-
5
Create the changelog in draft state within the app's existing publishing workflow, with no automatic publish. This brief drafts release notes only; the public changelog page, its feed, and its notifications belong to whatever already renders them.
Edge cases it handles
8
Edge cases it handles
8- Security work must be summarised at the level the company has agreed to disclose and never in detail that describes the vulnerability or how it was reached. Exclude the underlying items from the input rather than trusting the draft to be discreet.
- Grouping is where important fixes disappear. A data-loss or billing fix must appear as its own line, however small the change was, and never be rolled into a sentence about a feature.
- Implementation language is meaningless to customers. A line that names a migration, a service, or a refactor without saying what changed for the reader must be dropped or rewritten.
- Product names must survive verbatim. A draft that renames a feature, expands an abbreviation, or corrects capitalisation creates a name that does not exist in the interface.
- Nothing publishes without review. A drafted changelog is customer communication and requires a person to read it and press publish.
- Work items are written by engineers for engineers and may contain internal customer names, ticket references, or partner details. Strip these before generation.
- A refusal, timeout, or truncated response must leave the previous draft intact rather than replacing it with a partial one.
- Regenerating a draft must not silently discard edits a human has already made. Offer the new version alongside rather than overwriting.
Definition of done
9
Definition of done
9- Only items marked as shipped in the nominated release are eligible inputs.
- Every drafted line links back to the underlying work item.
- Each entry describes a customer-visible outcome rather than an implementation detail.
- Fixes appear as their own visible section and are never absorbed into feature summaries.
- Product and feature names in the draft match the product exactly, with mismatches flagged.
- Internal, security-sensitive, and unreleased detail is excluded before generation.
- The changelog stays in draft until a person publishes it, and regeneration never overwrites human edits.
- 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 Image Captioning
AI Image Captioning
Describe images so they can carry a visible caption and be found by search.
What it does
A generated description stored per image, offered as a draft caption and indexed for search.
How it works
- 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.
Copy the prompt
No account needed
Add this feature to my app:
https://addthisfeature.com/x/ai-image-captioning
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.