Jan 14 - MCP, Agents and Skills Meetup

Join our virtual meetup to hear talks from experts on cutting-edge topics across AI, ML, and computer vision.

Date, Time and Location

Jan 14, 2027
9:00 AM - 11:00 AM PST
Online. Register for the Zoom!

From Demo to Production: Testing, Scaling and Securing AI Agents with Spring AI

Your agent works perfectly in the demo. Then in production it gives a wrong answer and nobody can tell why, token costs spike, it slows to a crawl under load, and it calls a tool the user was never allowed to use. Building an agent is the easy part; the real work is running it like any other production service: tested, observable, scalable and secure.

Spring AI lets you do that with the Spring idioms and tooling you already know. This code-first session grows one example step by step. We start with a simple ChatClient, add advisors, memory and RAG, comparing the options Spring AI offers for each, and then let the agent act through tool calling and MCP.

Then come the production questions:

• Testing: we catch regressions with LLM-as-judge evaluators and typed decision models like Jev for fast, cheap verdicts.
• Observability: we add Micrometer traces, logs and token usage across model and tool calls.
• Scaling: we compare options for handling more concurrent users, from self-hosting to a managed runtime such as Amazon Bedrock AgentCore.
• Security: we use Spring Security to authenticate users and make sure only the MCP tools they're allowed to use ever get called. You'll leave with reusable Spring patterns for agents that reason and act, and the discipline to test, observe, scale and secure them in production.

About the Speaker

Andrei Shakirin is a Solutions Architect at Amazon Web Services and a former Pivotal Labs engineer, specializing in the design of highly scalable systems and generative AI applications. He is an active committer to several Spring and Apache open-source projects, contributor into MCP java SDK and a regular speaker at technical conferences.

From Model Evals to System Evals: Evaluating Agents, Harnesses, and the Evaluators Themselves

Every team shipping agents is quietly standing up two systems: the agent harness that plans, retrieves, calls tools, and edits code — and the evaluation harness that decides whether any of it can be trusted. Most teams only evaluate the first one's final output.

That is not enough. An agent can produce a correct answer through an unreliable, wasteful, or out-of-policy execution path, and outcome-only checks will pass it. This talk argues for evaluating the whole agent system: execution trajectories — tool correctness, evidence and grounding, state handling, policy compliance, and efficiency — alongside final outcomes, using deterministic specification checks an agent cannot game, model-based judges, and human-calibrated benchmarks.

We separate capability evaluations from regression evaluations so harness or model changes can be gated in CI. Then we turn the lens around: the evaluators themselves need evaluating — LLM judge calibration, disagreement analysis, and where human review still belongs.

Attendees leave with a production checklist for gating agent, model, and harness changes on system-level evidence instead of final answers.

About the Speaker

Dipen Chawla is an AI engineer and researcher working on agentic AI systems and their evaluation, including agent memory and clinical diagnostic reasoning work at Microsoft, and data platform engineering at Walmart and S&P Global.

Leading an Army of AI Agents

Our AI coding agents now pick up tasks, follow team playbooks, open pull requests and wait for review. This firsthand engineering case study follows more than ten agents running in parallel and shows how briefs, shared context and verification loops keep their work reviewable.
It covers the failure modes too: confident wrong turns, incomplete verification, review bottlenecks and the attention required from human leaders.
Attendees will learn a practical task-to-PR workflow, how to make trust conditional on evidence, and which measures expose the costs hidden by faster output. The focus is on agent workflow and operating discipline, with concrete engineering examples rather than a product pitch.

About the Speaker

John Adib is a London-based engineering manager at Zapp, a former CTO and two-time founder with 18+ years of software experience.

Agents in Action: Putting AI Agents to Work on Visual AI Data

What should an AI agent remember, and what should it forget? In this talk, we’ll explore the Voxel51 agent through the lens of memory, examining how retaining the right context and incorporating feedback can help agents improve over time. Through examples from visual AI workflows, we’ll discuss what’s worth remembering, from dataset context and user preferences to corrections and successful approaches, and when to update or discard information that becomes outdated. We’ll also explore how feedback and evaluation can help us determine whether an agent is making better decisions, offering practical insights for building agents that become more useful with experience.

About the Speaker

Adonai Vera is a Machine Learning Engineer and DevRel at Voxel51 with over 7 years of experience building computer vision and machine learning models using TensorFlow, Docker, and OpenCV.