The One About Agents and Inference (ft. Groq & OCBC AI Lab)

​From planning and reasoning to execution and optimization, Agentic AI is redefining what’s possible in autonomous workflows. Join us to hear more from our speakers on the frameworks, runtime performance considerations, and scalability strategies that separate proof-of-concept agents from production-grade systems.

​More About the Sharings

• ​Wilson Ng (Data Scientist, GovTech’s AI Practice) will share insights on Agentic AI in the government sector. His talk will cover the fundamentals of Agentic AI, practical examples of its applications within government, and guidance on how to get started with implementing agentic AI. Check out their Primer here. (Technical Level: 100)

• ​Steve Gao will present on agentic workflow design and how the AnyGen team developed a self-propelling system to evaluate end-to-end agent performance. He will demonstrate this through AnyGen, an AI-powered agentic tool designed to innovate workplace AI by delivering ready-to-ship deliverables to users. Steve’s presentation will include practical use cases and interactive engagements with the audience. Participants are encouraged to sign up prior to the presentation at AnyGen.io to explore use cases and create their own artifacts. The first user to create an artifact will receive a prize. (Technical Level: 100)

• ​Yichao Jin (Data Science Executive Director, OCBC) will be sharing more on how OCBC adopted Agentic AI into its private banking client onboarding process to generate real-world impact for banking industry. He will share the use case, the challenges, and solutions, as well as the lessons learnt from the implementations of an Agent AI in production. (Technical Level: 200)

• ​Andrew Tan (Solution Architect, Groq) will be sharing more about how Groq is enabling fast multi-step agents across common agentic frameworks, and also for coding workflows. He will also share more about throughtput benchmarking and openbench, a new tool that Groq has open-sourced to run common benchmarks, as well as new functionality coming to the Groq playground. (Technical Level: 200)

​More About the Speakers

• ​Wilson Ng is a Data Scientist at GovTech’s AI Practice, specializing in enhancing AI performance with a focus on LLMs. His focus spans agentic AI, fine-tuning techniques, and retrieval-augmented generation (RAG).

• ​Steve Gao is a Co-founder of AnyGen, a workplace AI tool designed to deliver ready-to-ship results to users. A strong advocate for build-in-public methodologies and Agile development cycles, Steve’s background includes a early role at ByteDance’s Seed Lab. As one of the initial team members, he contributed significantly to the training of Doubao/Seed models, with primary involvement in LLM post-training and performance evaluation. He was also instrumental in the launch of ByteDance’s first international chatbot product, Cici.

• ​Yichao Jin is the Data Science Executive Director at OCBC Group Data Office - AI Lab, with a PhD degree in Machine Learning and AI from NTU obtained in 2015. He authored over 30 journal and conference publications in this research area, and his decade of industry experience served as a trusted guide for applying AI to a variety of real-world products.

• ​Andrew is a AI Solutions Architect at Groq, where he helps developers, startups, and enterprises design systems to take advantage of fast LLM inference. His experience includes building production-ready GenAI use cases for customer care and value management, with a focus on platform enablement and governance.

​​_Psst…Interested in becoming a speaker for this session? Sign up_ here__!