Documentation
AI Changelog Generator
Merged pull requests turn into a categorized, readable changelog entry without anyone writing release notes by hand.
Release notes get written at the last minute, or not at all, and customers miss what changed. AI Changelog Generator reads your merged pull requests and commits since the last release and drafts a clear changelog entry, sorted into Added, Fixed and Changed. It writes in the tone you set, so internal jargon stays out of customer-facing notes, and publishes where you choose.
- Release notes drafted from merged work automatically
- Sorted into Added, Fixed and Changed for easy reading
- Written in your tone, without internal jargon
$1,500
20–30 working days
Optional maintenance $249/mo
What it is
AI Changelog Generator is an agent that reads merged pull requests and commits since your last release and drafts the changelog entry, sorted into categories such as Added, Fixed and Changed. It writes in the tone you set, so internal jargon does not leak into a customer-facing note. You approve each entry before it publishes.
Why businesses buy it
Good release notes help customers adopt new features, reduce support questions and show that your product is improving. Yet writing them is a chore that falls to whoever is least busy on release day. AI Changelog Generator turns merged work into a readable, categorized entry every time, so your releases get the communication they deserve and engineers get their time back. It is a small, affordable automation with a visible payoff. The Scope Card fixes the destination, tone, reference examples and sample entries before you order.
Problems this solves
Release notes get written in a rush or not at all
The agent reads merged pull requests and commits since your last release and drafts the changelog entry. Your team edits a ready draft instead of reconstructing what shipped.
Changelogs are hard to scan when everything is one long list
Each entry is sorted into categories such as Added, Fixed and Changed. Readers can find what matters to them without reading every line, and the format stays the same from release to release.
Internal jargon leaks into customer-facing release notes
Drafts are written in the tone you set, using your style profile and reference examples. You approve every entry before it publishes to your chosen destination.
A good fit if
Release notes get written in a rush right before shipping, or skipped entirely when nobody has time.
Your team merges through GitHub, GitLab or Bitbucket with reasonably descriptive pull request titles to draft from.
You want entries sorted into categories like Added, Fixed and Changed automatically, not typed out by hand each time.
You publish changelogs to one destination, such as a CMS, a repository file or a release page, and want that kept current.
Not the right fit if
You need full internal technical documentation, not just release notes. See AI Documentation Agent, built for broader docs.
You need reference docs generated from an API schema specifically. See AI API Documentation, which is built for that.
You publish changelogs to more than one destination or in more than one format at once. Add a note at checkout for a quote, or use our Custom AI enquiry form.
You need changelog entries in more than one language. This build covers one language; a second is priced separately.
How it works
- It reads what merged since the last release. Pull request titles, descriptions and commit messages since the previous changelog entry are pulled in.
- Entries are grouped into categories. Merged work is sorted into categories such as Added, Fixed and Changed based on the rules you set.
- Internal detail is rewritten in your voice. Jargon and ticket numbers get turned into a sentence a customer or teammate can actually read.
- A draft entry is assembled. The categorized, rewritten items come together as one changelog entry ready for a release.
- The draft goes out for review, not publication. It lands as a pull request or a page draft for someone on your side to check.
- Approved entries are published. Once approved, the entry is pushed to your CMS, repository file or release page.
What you provide within 72 hours
Your portal lists these the moment you order. Delivery starts the working day after everything is in and your access is checked.
- Your business information (company basics, hours and brand voice), shared during intake, or confirmation we can reuse what you gave us on an earlier order.
- Access to the repository whose merged pull requests and commits this build reads from.
- 10 to 20 past changelog entries you consider good examples of the tone you want.
- The categories you want entries sorted into, such as Added, Fixed and Changed.
- Access to the destination where the changelog should be published, and the name of the person who approves it.
- Admin access and API keys for every connected system, shared by adding our team as a user or creating a key you control, never by email.
- One person on your side who can approve decisions during setup and sign off at launch.
- An API key for your own AI model account (for example OpenAI or Google Gemini), created for this build with a spending limit.
The 72-hour rule. Send everything on your checklist, including access, within 72 hours of ordering so your build starts on time.
Timeline
Start
Intake verified, repository and destination access confirmed.
Weeks 1–2
Category rules and drafting pipeline built.
Week 3
Destination system connected.
Weeks 3–4
25 sample changelog entries produced for your review.
Week 4
Your review and two rounds of changes.
Go-live
Live, recorded handoff session, support starts.
| Option | Delivery time | Price |
|---|---|---|
| Standard | 20–30 working days | $1,500 |
| Express | 15–25 working days | $1,800 |
| Rush | 10–20 working days | $2,100 |
What you receive at handover
- The changelog generator connected to your repository and one publishing destination
- Tone and category settings, guided by up to 20 reference examples
- Up to three output formats, such as a public changelog and an internal summary
- 25 sample entries reviewed and approved by you
- Admin guide and recorded 45-minute handoff session
- 30 days of post-launch support
Expected benefits and how to measure them
- Can make it easier to publish release notes for every release.
- Helps customers and colleagues see what changed and why it matters.
- Releases with published notes
- Compare how many releases had a published changelog entry in the quarter before launch and the quarter after.
- Time spent on release notes
- Ask whoever writes notes to time the task for a few releases before and after.
- Edits before approval
- Track how many drafts are approved with light edits versus heavy rewrites.
Before you start: Check how many recent releases had notes and roughly how long each took to write.
These are things to track, not promised results. Outcomes depend on your data, your team and your market.
Running costs
The build price is one-time. Running it costs roughly $20 to $150 a month in AI model usage in your own accounts, depending on how often you release and how much merges each time.
AI usage during the build and testing is also billed to your accounts, so you keep ownership of every provider relationship. Nothing runs through us.
Ask about running costsCustom requirements
If you need something outside the Scope Card, add a note at checkout. You get a written Change Quote, and that work only starts once you accept it. Your original order runs on its normal timeline either way. Larger or bespoke projects go through the Custom AI request form.
Request a custom versionKeep it running
Monthly maintenance includes monitoring, fixes, a monthly health report and hours for retuning categories or adjusting tone as your release cadence changes. It starts after the 30 days of support, bills monthly, and can be cancelled any month.
$249/mo (the minimum fee, includes 2 change hours)
Optional. Starts after the post-launch support period. Cancel any month.
How maintenance worksHow this compares
| Do it yourself with a SaaS tool | Hire a custom agency | Upmark Labs | |
|---|---|---|---|
| Price | A release-notes SaaS charges monthly whether or not you ship that month | A custom agency quotes after discovery calls | Ours is one fixed price, shown before you buy |
| Scope | A release-notes SaaS is a template you fill in yourself | An agency agrees scope during the project | Ours is written on the Scope Card before purchase |
| Delivery | A release-notes SaaS is live once you finish connecting and templating it | An agency usually takes several weeks, set per project | Ours has a fixed delivery time shown before you buy, with faster options |
| Tone | A release-notes SaaS publishes your raw commit messages unless you rewrite them | An agency build depends on what was agreed | Ours rewrites merged work into your voice before it publishes |
Questions about this product
What does the AI Changelog Generator build include?
Everything on the Scope Card: changelog entries drafted from merged pull requests and commits, Added, Fixed and Changed categories, your tone, publishing to one destination, and sample entries for your review, two rounds of changes and the recorded handoff session. The price is fixed and shown on this page before you order, and it does not change once your Scope Card is confirmed. AI usage is billed to your own accounts.
How much does it cost to run AI Changelog Generator each month?
Roughly $20 to $150 a month in AI model usage in your own accounts, not ours. The figure depends on how often you release and how much merges each time. Monthly maintenance is separate and optional, for ongoing changes. It covers monitoring, fixes, a monthly health report and hours for retuning categories or adjusting tone.
When does AI Changelog Generator go live?
Delivery runs on a fixed schedule, and the delivery panel shows the standard date plus express and rush options before you order. The clock starts once your repository and destination access are confirmed and your intake is complete, not the day you place the order, so sending them early keeps the date.
What repository access does AI Changelog Generator need?
Scoped, read access to the repository whose merged pull requests and commits it drafts from, plus 10 to 20 past changelog entries as tone examples. It never needs write access to your code. Every credential is shared by adding our team as a user or creating a key you control during intake, not by email.
Does AI Changelog Generator publish entries automatically?
No. Every draft entry lands as a pull request or a page draft for someone on your side to review before a release ships. Nothing publishes until a person approves it, which keeps a mis-categorized item from ever reaching customers unchecked.
Can I change the changelog categories later?
Yes. Adjusting categories or tone fits inside the monthly change hours that come with maintenance. Publishing to a second destination or format is a bigger change and gets a Change Quote before any work starts on it. Maintenance starts after the post-launch support period, includes monitoring and a monthly health report, and can be cancelled any month.
Can I cancel AI Changelog Generator maintenance?
Yes, in any month. Plans bill monthly with no lock-in, and the build keeps drafting entries either way; cancelling only stops the included monitoring, fixes and hours. The 30 days of post-launch support continue regardless of whether you keep a plan.
Who owns the changelog entries AI Changelog Generator writes?
You do. Once approved and published, every entry is your content in your own destination, not licensed from us. The category rules and tone settings built for you also belong to your business, and keep working even if maintenance later lapses.
Stop writing release notes at the last minute.
Order AI Changelog Generator and on a fixed delivery date it starts drafting categorized release notes from your merged work.
Works well with
Documentation
AI Documentation Agent
Generates and maintains technical documentation from code and specs.