MaxTAF 2.8.0: AI writes the regression test and your suite runs it every night

MaxTAF 2.8.0 records what the AI does while it tests, and hands it back as an ordinary MXML case, the scripted test format MaxTAF already runs. The thinking is paid for once, when the test is built. What runs every night afterwards is an ordinary scripted test.

Keep an AI run as an MXML case

Until now you had to choose between two approaches, each with a cost. A hand-scripted case is deterministic and costs almost nothing to run, but someone must write and maintain it. An AI case takes minutes to create in plain English, but the AI does the work again on every run, so each run costs money and no two take the same route.

In 2.8.0 you describe the test once, the AI runs it against your live Maximo, and a case lands in your Workspace. Read it, press Compile once, and it runs on demand or on a schedule.

Ask us to switch recording on for your project. Nothing else changes on your side.

The Assistant fixes and re-runs a failed case

The AI Assistant now reads a failed run, proposes a fix, applies it, recompiles and re-runs to show whether it now passes. Every change is listed in the Change Timeline with one-click undo. It uses your own AI provider's API keys, so your data and spend stay in your account.

Read more in Build a test once with AI, then run it as MXML and Improvements to the AI Assistant, both on the release page.