AI quality, LLM evaluation and test automationRupali Kumar
Catch bugs, and bad AI answers, before your users do. We plan, write and automate tests, then wire them into your CI so every change is checked.
What we test
LLM evaluation: accuracy, grounding, format, tone and bias, with LLM-as-judge checks on every change (our Verity framework)
Drift checks that catch quality drops when models or prompts change
Web UI automation: Playwright, Selenium, Cypress
Mobile automation: Appium on real Android and iOS devices
API testing (Postman, RestAssured, pytest) and load testing (JMeter, k6)
Packages
Starter ($250, ~3 days): test plan, 20 manual/API cases, bug report
Automation or AI eval ($800, ~10 days): 40 automated UI/API tests in your CI, or an evaluation suite for 1 AI feature
Full coverage ($2,000, ~3 weeks): 100+ web and mobile tests, load test, nightly CI run, plus LLM evaluation
Experienced with regulated domains such as healthcare and finance. Message me with your app or AI feature, and I'll confirm the package.
FAQs
Starting at$250
Duration1 week
Tags
API Testing
Large Language Model
LLM Evaluation
Playwright
QA Testing
Selenium
Quality Assurance
Test Automation
Appium
Service provided by
Rupali Kumar Pune, India
AI quality, LLM evaluation and test automationRupali Kumar
Starting at$250
Duration1 week
Tags
API Testing
Large Language Model
LLM Evaluation
Playwright
QA Testing
Selenium
Quality Assurance
Test Automation
Appium
Catch bugs, and bad AI answers, before your users do. We plan, write and automate tests, then wire them into your CI so every change is checked.
What we test
LLM evaluation: accuracy, grounding, format, tone and bias, with LLM-as-judge checks on every change (our Verity framework)
Drift checks that catch quality drops when models or prompts change
Web UI automation: Playwright, Selenium, Cypress
Mobile automation: Appium on real Android and iOS devices
API testing (Postman, RestAssured, pytest) and load testing (JMeter, k6)
Packages
Starter ($250, ~3 days): test plan, 20 manual/API cases, bug report
Automation or AI eval ($800, ~10 days): 40 automated UI/API tests in your CI, or an evaluation suite for 1 AI feature
Full coverage ($2,000, ~3 weeks): 100+ web and mobile tests, load test, nightly CI run, plus LLM evaluation
Experienced with regulated domains such as healthcare and finance. Message me with your app or AI feature, and I'll confirm the package.
FAQs
$250