Software testing, test automation and the evals AI features need
We provide quality assurance services for teams releasing software and AI features. Four services cover testing delivery, test automation, AI evaluation and independent assessment, with scope agreed around your product's risks.
01Work
Four ways to strengthen release evidence
We match QA scope to the release decision your team needs to make.
Testing during development
We run manual and automated full-cycle testing for agreed functional, performance, security and usability requirements. Test results and defect reports support prioritizing fixes throughout development.
Repeatable checks before a release
Test automation runs agreed repeatable checks and provides evidence for the release decision. On a seven-country e-commerce platform, our QA work included automation, load and stress testing, plus a test plan and test cases for the client's QA process.
Criteria for AI output
AI evals measure output against criteria for the task, using pass/fail thresholds or graded scores. The scope can assess answers, retrieved sources and agent behavior, including changes in model or data. Conventional application tests remain part of testing an AI feature.
An independent view of current QA
QA consulting and audits assess test coverage, process and risk, with ranked findings and a roadmap. Your team can use the assessment to improve existing testing; implementation with us is a separate decision.
02Services
Four QA services and two security services
Choose the service by the testing or security evidence your product needs.
| Service | What you are actually buying |
|---|---|
| Software testing and QA | The developers are the only testersWe test functional, performance, security and usability requirements with manual and automated checks. Scope and risk priorities are agreed for a recurring engagement or one testing cycle. Our independent QA work includes a client-built real-estate platform in Japan.Software testing and QAOr book a meeting |
| QA and test automation | Every release is checked by handA test suite with repository and CI/CD integration, maintenance and handover agreed with your release owner. On one document-management platform, automated tests and scalable software architecture reduced the time to release updates from weeks to a couple of hours.QA and test automationOr book a meeting |
| AI QA and LLM evaluation | The output variesEvaluation criteria for answers, retrieved sources and agent tasks, with binary thresholds or graded measures suited to the feature. We agree the scope and acceptance criteria with the release owner, including checks for changes in model, data or behavior.AI QA and LLM evaluationOr book a meeting |
| QA consulting and audit | A second opinionAn independent assessment of test coverage, working practices and release risk. You receive ranked findings and a roadmap your own team can use. Implementing the recommendations with us can be commissioned separately.QA consulting and auditOr book a meeting |
| Security and compliance consulting | Buyers are askingReadiness work for applicable ISO 27001, GDPR, HIPAA or PCI DSS requirements: a gap assessment, proposed controls and supporting evidence. Engineering remediation can be included in the agreed scope, with implementation and review responsibilities defined for your systems.Security and compliance consultingOr book a meeting |
| Penetration testing | Prove it, offensivelyAuthorized offensive testing of named systems, with boundaries agreed before testing begins. AI application surfaces can be included where relevant. Ranked findings give you point-in-time evidence for remediation decisions; fixes and retesting follow their agreed scope.Penetration testingOr book a meeting |
03Fit
Which QA work fits your release process?
Choose QA around the risk to each release and the evidence your existing tests provide.
| Your situation | What we recommend |
|---|---|
| A suite that exists, and that nobody believes any more | Fix the suite firstInvestigate inconsistent failures before expanding coverage. Timing, selectors and shared test data are possible causes to check. Keep the checks that provide useful signal for the release. |
| Screens that change shape every sprint | Automate underneathUse manual testing for interactions that are changing, and select stable interfaces or services for automation. The choice follows the behavior to check and the cost of maintaining the tests as the product develops. |
| A verdict that is genuinely a matter of judgment | Keep it humanRetain expert review for decisions that need contextual judgment, such as an appropriate tone or a plausible specialist answer. Automated checks can support that review within an agreed testing scope. |
| An internal argument about whether QA is worth it | Buy the auditA quality audit assesses the evidence your testing provides and prioritizes improvements. The findings and roadmap support a decision about the next scope; implementing that work with us is a separate choice. |
| A stable release path checked by hand every time | Automate thatBegin with the path a release actually takes. Select repeated checks that suit automation, then agree how the suite joins your pipeline and who maintains it. |
| An LLM feature about to go in front of customers | Evals, nowAgree answer and retrieval criteria with the release owner. Our AI QA and evals service evaluates representative cases using binary thresholds or graded scores. The findings support your release decision and later model-change reviews. |
Who does the testing
unicrew has 100+ senior in-house engineers across six countries and has built software since 2012, under our former Artelogic brand before the rebrand. We have ISTQB-certified QA engineers; ISTQB is a qualification held by individuals. The company holds ISO 27001:2022 and ISO 9001:2015 certifications, renewed through a multi-stage audit with Quay Audit UK.
04Trust
How we start and hand over a QA engagement
A QA engagement starts with existing release evidence and an agreed initial scope of work. Delivery work includes a defined handover.
- Read existing build and test evidenceWe review recent build history, test cases and defect reports to understand coverage and failure patterns. From you: agreed read access and a release owner who can explain the product's testing and recent defects.You getAn assessment of where defects go undetected
- Recommend the QA service, in writingWe recommend the testing, automation, evaluation or assessment scope that fits the evidence, including improvements to existing tests where useful. The reasoning accompanies the recommendation. From you: the release owner and agreement on priorities and acceptance criteria.You getA named next step, with the reasoning behind it
- Deliver an agreed first sliceFor delivery work, agree a release path, feature or dataset to test, with the deliverable and its acceptance criteria defined. The slice is scoped and priced before implementation; further work follows what it shows and what you agree. From you: access to an agreed environment and representative test data.You getA first slice, running
- Hand over to your release teamWe document the agreed test scope and how to run the checks. For automation, repository and pipeline integration are agreed with your technical owner. The handover names maintenance responsibilities and who accepts the work and authorizes releases. From you: a named recipient for the handover.You getWork your team can run without us
Before we add tests, we measure how often your existing tests change their result on an unchanged build. That one number decides whether the plan starts with making the suite reliable or with more coverage.
Ihor PrudyvusDelivery Director, unicrew05Proof
Independent QA and testing within platform delivery
Real EstateQuality assurance for a Japanese real estate platformunicrew provided QA consultancy for a leading Japanese real estate platform, which resulted in a refined QA workflow and test automation.
SaaSWaiverKing: Software Development for a Waiver Form CreatorWaiverKing is a document management business serving primarily the health and fitness industries. The platform integrates with Mindbody Online, one of the largest business-systems providers for gyms and yoga studios.Weeks to hoursTime to release an update to production
eCommerceEcommerce software development for JewelCandleJewelCandle, a mid-size European manufacturer of scented products, sells across seven EU countries (B2B and B2C) via online shops.10,000-plusProducts manufactured
06Clients
Five clients on testing and engineering quality
Artelogic’s work had a very positive impact on our team’s morale. As our development quality was improving, our engineers were more confident in what they were doing, allowing them to work faster and with more confidence. As a result, our releases took less time and were less stressful.
Our platform has been refactored to Laravel ensuring the code base is more stable, easier to maintain and easier to add new features. Their professionalism and quality of work have stood out in the partnership. We have had the code audited by a 3rd party who was extremely complimentary of the work.
We were able to get the work completed in the expected time frame. There were little to no defects which was very nice because it allowed us to release and move on to our next project without having to back peddle. They were very accessible and took the time to understand our needs. They truly felt like part of the team.
We have had six out of seven on time and on budget project executions. Each engagement was a minimum of six months of effort. They had a flexibility and willingness to adapt their processes to match my requirements both on communication and the development processes. I never had a problem with any of their code from a code quality perspective.
The work is ongoing, but the impact that Artelogic has had on our development team has been substantial. They can work on developing other projects while still seeking guidance from Artelogic. Artelogic always provides our team with solutions backed up with the right research and analysis.
07Questions
Questions about QA scope and delivery
We provide software testing for agreed application requirements, using manual and automated checks.
- Functional behavior.
- Performance under agreed workloads.
- Security requirements within the testing scope.
- Usability for the intended workflows.
Test automation integrates repeatable checks with an agreed CI/CD workflow. AI QA and evals addresses criteria for model output. Coverage and priorities follow the product's risks.
We test AI features with agreed evaluation criteria alongside conventional software testing.
AI QA and evals uses pass/fail thresholds or graded scores according to the task's criteria. The scope can cover answer and retrieval quality, with task-level checks for agents and model changes. Conventional application testing, including APIs and user interfaces, continues alongside evaluation.
We provide independent QA on software built by your team or another development partner.
On a client-built real-estate platform in Japan, our work included a QA workflow, automation based on a tailored test-case system and a testing roadmap. QA consulting and audits provide an independent assessment and prioritized plan; implementation can be commissioned separately.
We quote QA work for the agreed coverage and delivery scope.
- Time and materials is billed hourly and quoted per project.
- Fixed price is outcome based and quoted per project.
- Team extension is billed monthly per team member.
For test automation, repository and pipeline integration are agreed with your release owner.
There is no minimum engagement period. Most engagements start within two to four weeks.
unicrew holds ISO 27001:2022 and ISO 9001:2015 certifications.
These certifications cover information security and quality management and were renewed through a multi-stage audit with Quay Audit UK. We have QA engineers with ISTQB certification, an individual qualification. We agree the evidence procurement needs for your engagement, including relevant organizational certificates and personnel credentials.
What teams usually pair this with
All servicesDefine the QA scope for your next release
Send recent build history or describe the AI feature you want to evaluate. We will recommend the QA service and initial scope of work, including what your release owner needs to provide.