What do you think?
Rate this book
How AI Tests Software: Agentic Testing, Evidence, and Release Confidence
Testing is changing. Start doing the new work.
AI can inspect screenshots, logs, and source code. It can operate an application, execute a test from intent, investigate failures, and help a team decide whether to ship. The opportunity is much bigger than generating another brittle test script.
In How AI Tests Software, Jason Arbon takes you from a first useful AI check to an AI-first quality workflow. Learn how
Find and corroborate problems across screenshots, logs, network traffic, code, and data.Execute interactive tests from portable intent rather than fixed choreography.Use source context, risk analysis, personas, and model judges to ask better testing questions.Coordinate specialists through a test harness that preserves state, evidence, and learning.Turn results and missing evidence into a defensible release-confidence discussion.Prepare for personalized, dynamic software and a changing human role in testing.Practical examples, prompts, and personal stories connect the techniques to real testing work. Written primarily for software engineers building with AI, and for software testers, engineering leaders, and people building the next generation of testing tools.
Jason Arbon is a coauthor of How Google Tests Software and the author of Testing AI.
AI can inspect screenshots, logs, and source code. It can operate an application, execute a test from intent, investigate failures, and help a team decide whether to ship. The opportunity is much bigger than generating another brittle test script.
In How AI Tests Software, Jason Arbon takes you from a first useful AI check to an AI-first quality workflow. Learn how
Find and corroborate problems across screenshots, logs, network traffic, code, and data.Execute interactive tests from portable intent rather than fixed choreography.Use source context, risk analysis, personas, and model judges to ask better testing questions.Coordinate specialists through a test harness that preserves state, evidence, and learning.Turn results and missing evidence into a defensible release-confidence discussion.Prepare for personalized, dynamic software and a changing human role in testing.Practical examples, prompts, and personal stories connect the techniques to real testing work. Written primarily for software engineers building with AI, and for software testers, engineering leaders, and people building the next generation of testing tools.
Jason Arbon is a coauthor of How Google Tests Software and the author of Testing AI.
954 pages, Kindle Edition
Published October 6, 2026
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
No one has reviewed this book yet.