Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Google ADK: Debugging to PR
This talk covers using Agentic AI workflows with Google ADK and code integration to automate debugging, moving from an alert to a Pull Request quickly.
At Oodle AI, we are reimagining Observability with the help of Agentic AI workflows. In this talk, I will go over:
- Our approach for AI-assisted debugging to provide you relevant insights on an alert. This workflow involves coordinating multiple agents using Google ADK along with tools specifically designed for providing relevant information to Agents. Integration with Cursor/Claude Code to go from a firing alert to a PR becomes possible.
- Using ideas from WebMCP to enable users to perform day to day tasks like creating grafana dashboards, creating alerts, exploring metrics using prompts.
I plan to give a short demo + go over implementation ideas for above.
Related projects
Prompt To Production - Copilots in UI Development
Abu Dhabi
Learn how to leverage AI copilots for consistent and efficient web development, maximizing their potential for modern UI…
RAGBuilder by Krux AI
Bengaluru
Learn how RAGBuilder automatically optimizes chunking, embedding models, and other RAG parameters, evaluates configurations on test data, and…
RAGBuilder by Krux AI
Bengaluru
Learn how to tune chunking strategies, sizes, and other RAG parameters, evaluate configurations on a test set, and…
Agent for Automatic Investigation in Production Issues
Bengaluru
The talk demonstrates an AI agent that analyzes multi-tool data to recommend debugging strategies for production issues, highlighting…
A Simple production Ready RAG pipeline
Dublin
This talk demonstrates a production-ready Retrieval-Augmented Generation (RAG) pipeline using Qdrant, covering data ingestion, cleaning, and inference steps…
AI agents to conduct recruiting interviews
Bengaluru
This talk explores building modular AI agents that conduct dynamic, unbiased recruiting interviews using LLMs and cognitive architectures…