Check a bot's answers without manual conversations and verifying each result.
Test automation & QA
Repository on GitHub (GitHub)The system automates QA checks of Telegram bots: it sends test messages, collects the answers and uses AI to evaluate whether they match the expected behavior. Instead of the repetitive cycle “write — wait — compare — record”, the team gets the results in one table.
The tester sets scenarios and expected results in Google Sheets. The system goes through the tests one by one via a user Telegram session, and AI gives PASS or FAIL with an explanation. Access to the bot's internals is not required — what an ordinary user sees is what gets checked.
Automatic run of prepared tests one by one, without sending messages by hand.
Checking ordinary dialogues, non-standard requests, negative scenarios and attempts to get around the bot's instructions.
AI evaluation of the answer with a verdict and a reason.
Storing the request, expected behavior, actual answer and grade in one table row.
Repeatable checks for regression testing after changes.
Test automation & QA · AI evaluation & model selection
Check answer quality and resistance to provocative requests — without running conversations by hand.
Automatic checks of AI chatbots in Telegram: functional tests, AI evaluation of answers and security checks.
Process automation & integrations · Test automation & QA
The team works in Jira — managers get a clear summary without manual data transfer.
An automatic bug summary for QA, managers and other teams instead of shortening tickets by hand.
Result Manual data transfer when preparing the summary has been eliminated
Voice & meetings · Test automation & QA
Tell Telegram about a bug — get a formatted report and a Jira task.
A tester's voice notes turn into structured bug reports in English.
Result Generate a bug report in 60 seconds
Describe what is currently done manually, what data is involved and what result you would like to achieve. You do not need a technical specification or a chosen model to begin.
Please do not share trade secrets, source code, or sensitive personal data before an NDA (non-disclosure agreement) is signed.
