Code Quality
AI QA Agent for GitLab
Runs structured test plans against your application and reports defects with evidence, connected natively to GitLab so it reads and updates projects,…
Code Quality
AI QA Agent
Runs your structured test plans against the application and reports every defect with evidence attached.
Manual testing eats release days, and bugs that slip through cost far more to fix later. AI QA Agent runs your structured test plans against your application, on the schedule or trigger you choose, and reports every defect with evidence: steps to reproduce plus a screenshot or log, posted to your issue tracker. It makes no production changes without a person's approval.
- Your test plans run on schedule or on every trigger
- Defects arrive with reproduction steps and evidence attached
- No production changes without a person's approval
$3,900
20–30 working days
Optional maintenance $249/mo
What it is
AI QA Agent runs structured test plans against your application, on the schedule or trigger you choose, and reports every defect it finds with evidence, such as steps to reproduce and a screenshot or log, posted to your issue tracker. You choose what it tests and when.
Why businesses buy it
Every bug that reaches customers costs support time, refunds and trust, and finding it late costs engineering time too. Manual regression testing is slow and often skipped under deadline pressure. AI QA Agent runs your test plans consistently and reports defects with the evidence a developer needs to fix them quickly, so releases ship with fewer surprises and your team stops arguing about whether a bug is real. The Scope Card fixes the repository, connected systems, test workflow and trial runs before you order, so you know exactly what gets tested.
Problems this solves
Manual testing gets skipped when a release is rushed
The agent runs your structured test plan on the schedule or trigger you choose. Testing happens every time, not only when someone finds a spare afternoon.
Bug reports arrive without steps to reproduce them
Each defect it finds is posted to your issue tracker with evidence, including steps to reproduce and a screenshot or log. Developers can start fixing instead of asking questions.
Small teams have no dedicated QA person
You choose what it tests and when, through one automated workflow. It handles the repetitive checks a tester would run, while your developers keep the final say.
Old features break quietly when nobody re-tests them
Running the same plan against each change re-checks existing features as well as new ones. A trial on 20 runs shows how it behaves before you rely on it.
A good fit if
You have a structured test plan, or the outline of one, that currently takes a person hours to run manually before every release.
You want defects reported with real evidence, steps to reproduce and a screenshot or log, not just a pass or fail count.
You want results posted to your existing issue tracker or chat, such as Jira, Linear or Slack, not a separate QA dashboard.
You are comfortable with the agent testing and reporting only, with no production changes made without a human's approval.
Not the right fit if
You want pull requests reviewed for bugs and standards before merge, not test plans run after code is built. See AI Code Review Agent.
You need new test cases written for code that has none yet, not existing plans run. See AI Test Generation.
You mainly want dependency versions checked and updated, not application testing. See AI Dependency Update Agent.
You need broader pipeline and infrastructure monitoring alongside testing. See AI DevOps Agent.
How it works
- You give us scoped access to one repository or pipeline, your CI/CD configuration, and the test plan or scenarios you want run.
- The agent runs the agreed test plan against your application on the trigger you choose, such as every pull request or a nightly schedule.
- Each failure is captured with evidence: the steps that reproduce it, plus a screenshot or log excerpt, not just a red mark on a report.
- Findings are posted to your issue tracker or chat, such as Jira, Linear or Slack, so a defect becomes a ticket without manual copy-pasting.
- A human decides what to fix and when. The agent tests and reports; it never changes production code or ships a fix on its own.
- We trial it on 20 real pull requests or pipeline runs before launch, so you see its judgment against your actual test plan first.
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.
- Scoped repository access, as an app or token, limited to what the agent needs to run tests and report results.
- Your CI/CD configuration details, so tests run on the trigger you actually use.
- Your test plan or scenarios, even a rough outline, for the agent to run and expand on.
- Access to your issue tracker or chat tool, such as Jira, Linear or Slack, where defects should be reported.
- 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.
- Your business information (company basics, hours and brand voice), shared during intake.
- One decision-maker who can approve the test plan before 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 confirmed, with repository access, the test plan and CI/CD details agreed.
Weeks 1–2
Test plan built out and connected to your repository and trigger.
Week 3
Defect reporting to your tracker or chat connected and tested.
Weeks 3–4
Trialled on 20 real pull requests or pipeline runs, with findings reviewed together.
Week 4
Your review and two rounds of changes.
Go-live
Live, with a recorded handoff session, and 30 days of support starts.
| Option | Delivery time | Price |
|---|---|---|
| Standard | 20–30 working days | $3,900 |
| Express | 15–25 working days | $4,600 |
| Rush | 10–20 working days | $5,250 |
What you receive at handover
- The QA agent running your test plan against one repository or pipeline
- Connection to your Git host and issue tracker or chat
- Prompt and guardrail configuration based on your standards or runbooks
- Test report from a trial on 20 runs
- Admin guide and recorded 45-minute handoff session
- 30 days of post-launch support
Expected benefits and how to measure them
- Can catch more defects before customers do.
- Makes bug reports quicker to act on, because evidence comes attached.
- Defects found before release
- Compare defects caught by testing with defects reported by customers, for two months before launch and two after.
- Reports needing clarification
- Count bug reports where a developer had to ask for steps or screenshots, before and after launch.
- Test runs completed
- Check how many planned test runs actually happened each month, using the tracker or pipeline history.
Before you start: Count customer-reported bugs over the last two months. Note how and how often testing is done today.
These are things to track, not promised results. Outcomes depend on your data, your team and your market.
Running costs
You pay for the build once. Running the agent costs roughly $20 to $200 a month in your own accounts, covering AI usage and CI minutes, and it moves with how often tests run and how large your application is.
AI usage during the build and testing is billed to your own accounts too, so your AI model and CI relationships stay in your name.
Ask about running costsCustom requirements
If you need a second repository, more than 2 connected systems, or a second testing workflow, add a note at checkout for a written Change Quote. Your order still runs on its normal timeline. Larger or bespoke projects go through the Custom AI request form.
Request a custom versionKeep it running
Monthly maintenance covers monitoring, fixes and a monthly allowance of change hours, covering an expanded test plan or a new integration. It starts after the 30 days of support 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 QA automation SaaS tool charges per seat every month, testing or not | A QA contractor or agency bills by the hour | Ours is one fixed price, shown before you buy |
| Evidence | A QA tool often reports pass or fail with no reproduction detail | An agency's evidence depends on who wrote the report | Ours reports every defect with steps to reproduce and a screenshot or log |
| Where results land | A QA tool needs a separate dashboard to review results | An agency's reporting format depends on what was agreed | Ours posts findings straight to your issue tracker or chat |
| Delivery | A QA tool is instant to sign up but slow to configure well | An agency engagement usually takes several weeks to ramp up | Ours has a fixed delivery time shown before you buy, with faster options |
Questions about this product
How is AI QA Agent different from AI Code Review Agent?
AI Code Review Agent reviews pull requests for bugs and standards before code merges. AI QA Agent runs your structured test plan against the actual application and reports defects with evidence such as reproduction steps and a screenshot or log. Many teams run both; choose QA Agent if broken behavior after merge is your bigger problem.
What counts as evidence in an AI QA Agent defect report?
Steps that reproduce the failure, plus a screenshot or a relevant log excerpt, attached to the ticket the agent creates. That is meant to save your team the step of reproducing a bug before they can even start fixing it, rather than a bare pass-or-fail line in a report.
Do we need a fully written test plan to start with AI QA Agent?
No. A rough outline of the scenarios that matter is enough for intake; we build it out into a structured plan the agent runs. If you have no test plan at all yet, describing your application's main flows during intake gives us somewhere to start.
How much does AI QA Agent cost to run each month?
Roughly $20 to $200 a month in your own accounts, covering AI usage and CI minutes, and it moves with how often tests run. The build itself is paid once and covers building the test plan and connecting it to your repository and tracker.
Can AI QA Agent run tests automatically on every pull request?
Yes, if that is the trigger you choose during intake. Other common triggers are a nightly schedule or a manual run before release. You set the trigger once, and it stays that way until you change it through monthly maintenance or a new intake.
How long does it take before AI QA Agent is running our tests?
Delivery runs on a fixed schedule from a complete intake, and the delivery panel shows that date plus express and rush options before you buy. Most of the time goes into building out the test plan, connecting your repository and tracker, and trialing it on 20 real runs before launch.
Defects reported with evidence, not a bare pass-fail line.
Order AI QA Agent and it goes live on a fixed delivery date, testing your application and reporting every defect with real evidence.
Works well with
Code Quality
AI QA Agent for GitHub
Runs structured test plans against your application and reports defects with evidence, connected natively to GitHub so it reads and updates repositories,…
Code Quality
AI Code Review Agent for GitLab
Reviews pull requests for bugs, security issues and standards and comments inline, connected natively to GitLab so it reads and updates projects,…