MCP/Agents/Skills Meetup - October 8, 2026

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

Multi‑agent systems are powerful but choosing the wrong interaction pattern can quickly lead to fragile, slow, or expensive AI systems.

In this talk, we explore the core multi‑agent design patterns enabled by ADK, including sequential, parallel, and more advanced coordination models. Rather than focusing on tools alone, we’ll look at how to think architecturally about agent collaboration.

You’ll learn:

- When sequential agents are the right choice and when they become a bottleneck
- How parallel agents improve speed and coverage (and the trade‑offs they introduce)
- Common failure modes in poorly designed agent interactions
- Practical criteria for choosing the right pattern based on task, latency, and reliability

By the end of the session, you’ll have a clear mental model for designing multi‑agent systems that are intentional, scalable, and production‑ready.

In this flash demo, Adonai will show some of the agent workflows the Voxel51 team has been building, and how you can put agents to work on your own visual AI data with Voxel51. Expect a quick, hands-on look at what's possible today and how to try it yourself.

Garbage Inn. Is garbage out? This is true. For many input and output processes. In biological life and in computer systems, and equally true when working with LLM’s. The better the prompt, the better the context, the better the focus, And the better the contextual awareness, the better the quality of the output the LLM’s generates.

This is the governance, art and practice of what we like to call agentic engineering, something I've been practicing over the last year.

This session presents architectural patterns for running agentic localization pipelines under constraints such as data residency. Using a localization workflow as the example, we show how constrained multi-stage systems route content, generate translations, and apply quality evaluation while keeping high-sensitivity processing inside the customer boundary.

Key Takeaways

- Architectural patterns for deploying constrained agentic pipelines in customer-controlled or air-gapped environments
- How multi-stage systems automate localization while preserving human review where required
- Design practices for domain-aware model choice, risk-tiered controls, and auditability in regulated workflows