
Welcome to the AI meetup in Boston (September Edition), in collaboration with
Agenda:
* 5:30pm~6:20pm: Checkin, Food and Networking
* 6:20pm~6:30pm: Welcome/community update
* 6:30pm~8:00pm: Tech talks and Q&A
* 8:00pm: Open discussion & Mixer
Tech Talk: Building Better Software Faster with Gemini
Speaker: Vadim Kacherov (Google)
Abstract: In this session, we will explore how Gemini is designed to turbocharge the Software Development Lifecycle (SDLC) by empowering enterprise AI adoption. We'll show you how it directly improves both software quality and delivery performance. You'll see how Gemini enhances code quality, ensuring better maintainability and consistency through its deep codebase awareness and enterprise context. Furthermore, we'll demonstrate how Gemini boosts overall SDLC performance—covering everything from planning through to production—by implementing powerful automation in both development and operations, leveraging productivity-enhancing tools like the Gemini CLI to significantly streamline developer workflows.
Tech Talk: Your Copilot is my insider - 0 click attacks for Agentic AI
Speakers: Steven Harper (Zenity)
Abstract: Compromising a well-protected enterprise used to require careful planning, proper resources, and the ability to execute. Not anymore! Enter AI. AI is happy to let you operate on its users' behalf. Persistence? Self-replicate through corp docs. Data harvesting? AI is the ultimate data hoarder. Exfil? Just render an image. No credentials required, no phishing, no social engineering, no human-in-the-loop.
Tech Talk: Observability and Evaluation of AI Agents
Speakers: Abby Morgan (Comet)
Abstract: Observability for AI systems is far more challenging than for traditional software. Large Language Models (LLMs) are inherently non-deterministic, often producing multiple equally valid outputs for the same task. In open-ended domains like summarization, reasoning, or content generation, there may be no single "ground truth," and common metrics such as relevance or coherence remain subjective—making standard evaluation methods insufficient.
The complexity increases with AI Agents, which frequently chain multiple LLMs with external tools. These systems can fail silently, propagate errors, and create tangled behaviors that are difficult to monitor or debug. This session will explore the unique challenges of evaluating and observing both LLMs and AI Agents. I'll share practical approaches for measuring performance, identifying hidden failure modes, and improving reliability, along with best practices for building trustworthy agentic systems.
Speakers/Topics:
Stay tuned as we are updating speakers and schedules.
If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: Submit Topics
Sponsors and Partners:
We are actively seeking sponsors to support our community. Whether it is by offering venue spaces, providing food/drink, or cash sponsorship. Sponsors will not only speak at the meetups, receive prominent recognition, but also gain exposure to our extensive membership base of 10,000+ AI developers in Boston and 500K+ worldwide.
Venue:
Microsoft New England – 1 Memorial Drive, Cambridge, MA 02142
Community Partners:
Contact us if you are interested in partnership.
- Microsoft: Microsoft’s mission is to empower every person and every organization on the planet to achieve more. Every day, the innovative technology we create here takes that mission to new and exciting places and impacts the lives of millions of people around the world.
Local and Global AI Community on Discord
Join us on discord for local and global AI tech community:
- Events chat: chat and connect with speakers and global and local attendees;
- Learning AI: events, learning materials, study groups;
- Startups: innovation, projects collaborations, founders/co-founders;
- Jobs and Careers: job openings, post resumes, hiring managers