Evaluating AI Agents
Topic: Evaluating AI Agents Learn from industry practitioners, researchers, and experts on the latest and greatest on evaluations frameworks and tools to bring AI Agents to production
Activities tracked
3
Agentic AI + Evals Theme: Mosaic AI Framework, DSPy and Evals Hashtag: #LondonAgenticAI
π Date: Thursday, 18th November 2025 π Time: 6:00 pm β 8:30 pm πVenue: 11-14 Windmill St, London W1T 2JG
By registering, I understand Databricks will process my personal information in accordance with our Privacy Policy and agree to Databricks sharing my personal information with co-sponsor(s) of the event to use in accordance with their privacy policy. I may update my preferences at any time.You need to sign up with your full name and email for building security and separate form to prepare your badge.
Important: Only 150 seats available. Registration is required, π Here is form . For security reasons, only invited guests on the official list will be granted access. Walk-ins will not be allowed.
About the Event London Agentic AI Meetup #3! π
This session dives into Mosaic AI Framework from Databricks, followed by the talk on analogy of DSPy with LLVM project and panel discussion on evaluating AI agents. Audience can come up with their questions on AI Agent Evaluation.
Youβll learn:
π€ Talks
Punet Jain: Sr. Specialist Solutions Architect - Databricks Title: Mosaic AI Agent Framework
Abstract: Explore the suite of tooling in Databricks that enables you to build, evaluate, and deploy production-quality Al applications with monitoring and governance, and this session will include customer stories illustrating real-world impact.
Eito Miyamura: Co-Founder - EdisonWatch Title: DSPy: The LLVM for Context Engineering
Abstract: Prompt engineering/optimising manually is like writing assembly code; if you're a pro, you get the most amount of control and max performance with manually adapting Prompt, but DSPy provides the higher-level abstraction DSL for the functions the LLM-based system is supposed to carry out before getting onto the bare metal (the LLM). Get smaller, cleaner code with DSPy. (And auto-optimization as a bonus)
π€ Panel
Topic: Evaluating AI Agents Learn from industry practitioners, researchers, and experts on the latest and greatest on evaluations frameworks and tools to bring AI Agents to production
Panel Moderator β’β Sultan Al Awar : Solutions Architect at Databricks
Panelists β’β β Kyra Wullfert - Specialist Solutions Architect at Databricks β’β β β Sangram Reddy - Head of AI at IntentHQ β’β Jacques Verre - Head of Product at CometML
Agenda
6:00 β 6:30 PM : Drinks & Networking Guests arrive, informal networking, and refreshments. 6:30 β 6:40 PM : Welcome & Opening Remark 6:40 β 7:00 PM : Talk 1: Mosaic AI Framework Speaker: Puneet Jain 7:00 β 7:20 PM: Talk 2: DSpy and Analogies with LLVM Speaker: Eito Miyamura 7:20 β 8:10 PM β Panel Discussion: Evaluating AI Agents + Audience Q&A 8:10 - 8:30 PM: Closing Remark & Walk to Pub for more networking 8:30 -Till Late : Networking in the "Rising Sun" Pub (46 Tottenham Ct Rd, London W1T 2EL)
Sponsor: This meetup is proudly sponsored by Databricks
A huge thank you to Databricks for providing both the venue and food for our community.
Why Attend? If youβre building with Agentic AI and need to learn about the Agent Evaluation strategies, experiences and insights. This meetup will be a great fit.
Sessions & talks
Showing 1β3 of 3 Β· Newest first
Topic: Evaluating AI Agents Learn from industry practitioners, researchers, and experts on the latest and greatest on evaluations frameworks and tools to bring AI Agents to production
Abstract: Prompt engineering/optimising manually is like writing assembly code; if you're a pro, you get the most amount of control and max performance with manually adapting Prompt, but DSPy provides the higher-level abstraction DSL for the functions the LLM-based system is supposed to carry out before getting onto the bare metal (the LLM). Get smaller, cleaner code with DSPy. (And auto-optimization as a bonus)
Abstract: Explore the suite of tooling in Databricks that enables you to build, evaluate, and deploy production-quality AI applications with monitoring and governance, and this session will include customer stories illustrating real-world impact.