AI Native Dev: Practical Agentic Engineering
AI Native Dev is back in New York for an evening meetup focused on where AI-native development is headed right now.
We’re keeping the format simple: a couple of sharp sessions and plenty of space to chat with other builders working with agents, workflows, and new development patterns.
We’ll kick things off with a look at Continuous AI, how agents can run alongside your development process, making informed decisions, opening PRs, and moving work forward without constant prompting. Then we’ll dive into Spec-Driven Development, exploring how clear human-readable specs can give coding agents the structure they need to produce more consistent, reusable work.
Expect an easygoing evening, good discussions, and a chance to learn from folks who are experimenting with these ideas every day.
🙌 Kindly hosted by Microsoft NYC
Program
6:00pm – Doors open
6:30 - Kick off and message from our partners
6:45 – Talks (~3 × 20 min)
Continuous AI & AI Agentic Workflows - Nitya Narasimhan, PhD
Specs as Context: giving your coding agents 20–20 vision - Simon Maple
Architectural Amnesia in the Age of Agentic AI - Tracy Bannon
7:45 – Networking
9:00 – Wrap-up
Session details:
AI Agents are transforming software development and boosting developer productivity. Today, we achieve this interactively using tools like GitHub Copilot via the IDE (VS Code Agent Mode) or Terminal (Copilot CLI). But what it they could work on your behalf continuously in the background without you having to ask?
In this talk, we’ll look at work being done by our colleagues at GitHub Next and Microsoft Research on a concept called Continuous AI that is powered by AI Agentic Workflows. We’ll look at what kinds of tasks this is good for, show examples of these workflows in action, and give you an intuitive sense for how you can apply these tools and concepts to your own projects. The work is not a product - but rather, an experimental platform for learning and exploring the possibilities of agentic AI in automating and managing repository actions. Learn more about the project here.
Nitya Narasimhan, PhD - Senior Cloud Advocate (AI) at Microsoft
Nitya Narasimhan is a PhD and Polymath with 25+ years of research & engineering experience across industry, academia and startups. Her interests and experience span distributed & ubiquitous computing, mobile & web application development, and Cloud & AI solution enablement. She is a Senior AI Advocate at Microsoft where she is “developer 0” for the Microsoft Foundry platform, building content and experiences to empower developer communities to build AI solutions more effectively on Azure. You can find here online @nitya (Twitter), #in/nityan (LinkedIn) & nitya (GitHub)
Coding agents have come a long way, but relying on vibes, prompts, and prototypes quickly hits a wall. What starts as productive soon becomes unmanageable: fragile hacks, copy-pasted prompts, and inconsistent outputs that resist collaboration and refactoring.
This session introduces new ways of developing with agents, including a Spec Driven Development approach that guides agents with human-readable specifications that capture intent, structure, and rules. You’ll see how moving beyond freestyle prompting enables better reuse, stronger tests-as-guardrails, and smoother transitions when frameworks or requirements change.
Simon Maple - Developer Relations at Tessl
Simon Maple is the Head of Developer Relations at Tessl, and AI Native Dev co-host. Previously, Simon was the Field CTO, and VP Developer Relations at Snyk, ZeroTurnaround, and IBM. He became a Java Champion in 2014, JavaOne Rockstar speaker in 2014 and 2017, Duke’s Choice award winner, Virtual JUG founder and organiser, and London Java Community co-leader.
Linkedin: https://www.linkedin.com/in/simonmaple/
Twitter: https://x.com/sjmaple
Modern AI is no longer just assisting us, it’s acting with us. As teams rush to adopt agentic AI, many are discovering an unexpected side effect: architectural amnesia. Critical decisions disappear into prompts, autonomy scales faster than oversight, and systems quietly accumulate new forms of identity, lineage, and validation debt. In this fast session, we’ll unpack the realities behind these hidden risks and shows why governance is not bureaucracy — it’s scaffolding. Drawing on extensive experience across government and industry, I will discuss practical ways to keep control while unlocking the power of AI agents. Expect hard truths, pragmatic guidance, and a clear path to responsible, resilient AI-augmented engineering.
Tracy (“Trac”) Bannon - Software Architect and Researcher @The MITRE Corporation, Host & Journalist of "Real Technologists Podcast", DevOps Ambassador
Passionate Software Architect and Change Agent who writes, speaks, teaches, and practices my craft every day. As an accomplished software architect, engineer, and researcher, I've worked across commercial and government clients. Understanding complex problems and working to deliver value at speed is what drives me. I focus on bringing leading-edge techniques to modern software practices including applying AI/ML/Generative AI to the full software development lifecycle.
As a long-time advocate for diversity in technology, I am helping to narrow the diversity gaps as a mentor, sponsor, volunteer, and friend.
Linkedin: https://www.linkedin.com/in/tracylbannon/
Twitter: https://x.com/TracyBannon
Github: https://github.com/tracybannon
This event is brought to you as part of the AI Native Dev Community. Consider subscribing to the Mailing List, Podcast, and join our Discord Community