About This Session
LLMs are surprisingly good at generating dashboard configuration. They're also completely blind to the result. Give an LLM a framework and a prompt, and it will confidently produce overlapping widgets, charts that return no data, and visualisations that technically render but tell you nothing. It has no spatial awareness, no access to the realised data, and no sense of whether the picture it's describing is honest. AG Studio fixes this by giving the model a set of client-side senses it otherwise lacks. This talk is about what that architecture looks like, why it matters, and what it means for anyone building AI-assisted interfaces.
Topics
- Agents
- Agentic AI
- Business Intelligence
- Generative AI (GenAI)
- Multi-Agent Systems