The One About AI x SWE

AI is changing more than how code gets written. What changes across the rest of the software engineering stack?

Join practitioners as they share how they're rethinking developer environments, platforms, tooling, and engineering practices as AI becomes part of how software gets built and shipped.

More info to come soon, keep a lookout! 👀

More About The Sharings

Mitchell Tan (Product, Cognition) will share on “Building Devin with Devin: How Cloud Agents 10x'ed Engineering Velocity at Cognition.”

Most coding agents help individual engineers write code faster. Cloud agents shift the model from assistance to delegation: each gets its own machine, tools, and credentials to take ownership of engineering outcomes end to end. What becomes possible when every engineer has an entire team of agents working in parallel?

At Cognition, the company behind Devin, over 90% of the code is now written by Devin itself. Mitchell will take you behind the scenes of how Cognition scaled engineering output using autonomous cloud agents, including live demos and lessons learned. (Technical Level: 200)

Alex Chng (Lead Product Manager, GovTech) will share on “Developer Productivity for the AI Native.”

As developers start working alongside increasingly autonomous coding agents, the development environment around them needs to change too. How do you support longer-running agentic workflows, multiple models, and emerging tools without compromising security, governance, or developer experience?

Alex will share how GovTech has been building and evolving developer tooling for an AI-native engineering environment. Through case studies and demos, explore the architecture behind their agentic setup, how they build alongside engineers as their workflows change, and the engineering trade-offs involved in balancing developer experience with meaningful control. (Technical Level: 200)

Najib Ninaba (Platform Engineering Head, AI Singapore) will share on “Agentic Engineering at AI Singapore: Learning at the Edge, Bringing It Home.”

What happens when you start treating coding agents like jobs on a compute cluster? Drawing on his experience building large-scale systems, Najib will share how he's been experimenting with running coding agents in parallel, with scheduling, isolation, and evidence for every change.

Through his work building Orchard, an open-source platform for running local LLMs on Apple Silicon, he'll unpack the engineering practices that have held up, from specs-first development and validation gates to managing agent autonomy. Hear how his team is bringing these lessons into AI Singapore's developer platforms, including model access, LiteLLM gateways, internal tooling, and agent-assisted assessments, alongside what hasn't worked and what they're still figuring out. (Technical Level: 200)

​​Organised with: AI Singapore

AI Singapore (AISG) is Singapore's national programme in artificial intelligence, launched by the National Research Foundation (NRF) to anchor deep national capabilities in AI. Hosted at NTU and NUS, AI Singapore brings together Singapore-based research institutions and the vibrant ecosystem of AI start-ups and companies to perform user-inspired research, grow knowledge, create tools, and develop the talent to power Singapore's AI efforts.

More About The Speakers

Mitchell Tan is part of the Product team at Cognition, working on Devin, an AI software engineering agent. A two-time founder, he previously built Kondo, a productivity tool for LinkedIn, and Beluga, a tech recruitment startup. His background spans product, growth, and startup building, including time at HeadsUp, which was acquired by Hightouch. He graduated from Yale University with a BA/MA in History.

Alex Chng is a product manager in GovTech focused on making software engineering faster, simpler, and more enjoyable for developers. He works on platforms such as Airbase and Airlift, helping teams ship applications and work with emerging AI-powered development tools without getting buried in infrastructure complexity. He enjoys turning messy engineering problems into products people actually want to use—and is mildly obsessed with finding the fastest path from “this could be useful” to “it’s in production.”

Najib Ninaba is a Senior Associate Director at Nanyang Technological University, Head of Platforms Engineering at AI Singapore, and a hands-on builder of tools for agent-assisted development. His work sits at the intersection of platform architecture, operational ownership, and the engineering systems that help teams deliver reliably.

More About The Series

AI Wednesdays is Lorong AI’s weekly gathering, bringing together practitioners, researchers and innovators for technical discussions on research insights, product development and engineering practices.

Get involved: Learn more about Lorong AI | Speaker Sign-up | WhatsApp Community | LinkedIn | X