JoeBot (TestGuild)Joe Colantonio, Founder of TestGuild

🤖AI Agents in QA How to Keep Up with AI Driven Dev Velocity

17 Jun 2026 · 1 min

Watch on YouTube

0:58

In this talk, the speaker emphasizes that AI agents, such as large language models, require rich contextual information to perform effectively in quality assurance and development workflows. Without context, their answers are limited to the prompt they receive. To address this, the team constructs a knowledge graph that models the deployed application, capturing user journeys, UI screenshots, textual descriptions, extracted domain facts, and ingested documentation like API specifications. This graph serves as a structured repository of application knowledge that AI agents can query, enabling them to understand requirements, changes over time, and how different parts of the system interrelate.

Chapters

And in order for AI to be able to function in a similar manner, it needs the context. So without context, it's just like, everybody knows this now, right? Like, depending on what you give ChatGPT, the better your answer is going to be. So it's all about like understanding the application and the requirements and the changes over time. And the way for us to tackle that problem has been to build a knowledge graph. The knowledge graph is essentially then a representation about about the deployed application, how the different user journeys kind of connect and how you get to different parts, also with screenshots and descriptions and things in there. And then also extracted facts and understanding about the domain and the application and how you do different things. You can also ingest documentation, for example, or API specifications and things like this that could be relevant for the agent to know about, which will also then attach to this other knowledge that we have in the knowledge graph.