Jonathon Wright: Generative AI: Turning Testers into Superhero’s
summary
Claims a concrete productivity boost of 20–35% productivity gain and shows an implemented ingestion pipeline that turns unstructured docs into a searchable knowledge layer using RAG/graph techniques and a vector DB. Demonstrations use UFO and xLAM large action/vision models and a free cy.ai agent platform; the stack runs 22 models in experiments, often two in parallel, outputs chained automation (Python wins for autotests) and reports the agent finds real security and accessibility issues while grading sites.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 3:34AI in software testing
- 8:27AI augmented testing
- 15:30AI augmented testing today
- 19:02AI-powered testing solutions
- 26:30Prompt engineering and domain models
- 31:10Summary
- 31:52Q&A
related talks
41mAI-Augmented Testing: How Generative AI, Prompt Eng Turn Testers Into Superheroes
36mUnleashing Generative AI: Improving Developer Productivity in SRE
01h 07mNew Methods of Working with AI.
27mBuilding AI applications: Successes and Lessons
29mImpact of #GenerativeAI in Development and #SoftwareTesting
30mBuilding Reliable AI Agents: An Open Source Approach To Evaluation and Observability
33mOperationalizing GenAI Applications with DevOps Practices
27mBuilding Generative AI features