Recorded on
with Aishwarya Srinivasan, Arvind Narayanamurthy
Codex can do far more than generate code—but only when it has the right context, tools, and feedback loops. This session shows how to delegate bigger tasks, let Codex validate its own work, and review results efficiently, so teams can move faster without lowering their standards.
Connect Codex to your standards, tools, and knowledge so it can handle real tasks with less hand-holding.
Use tests, linters, browsers, and screenshots to help Codex catch mistakes and keep working independently.
Build review workflows that make agent output faster to verify, easier to trust, and ready for your team.
Codex can do far more than generate code—but only when it has the right context, tools, and feedback loops. This session shows how to delegate bigger tasks, let Codex validate its own work, and review results efficiently, so teams can move faster without lowering their standards.
Developer Experience @ OpenAI · OpenAI
Jason Liu is a developer, educator, and AI builder currently working on Developer Experience at OpenAI. He is also the creator of Instructor , one of the most widely used open-source libraries for extracting reliable, structured outputs from LLMs. His work focuses on making AI systems easier to build, debug, and ship, with a strong emphasis on practical developer workflows, agents, and production-ready AI applications.
Hosted by Aishwarya Srinivasan and Arvind Narayanamurthy.
AI Advisor / AI Educator
Aishwarya Srinivasan is the Co-Founder of The Gen Academy and a Developer Relations Lead at Nebius. Her experience spans Fireworks AI, Microsoft for Startups, Google Cloud and IBM, where she worked with developers and businesses on practical AI and machine-learning solutions. She holds a postgraduate degree in Data Science from Columbia University and teaches AI engineering, applied machine learning, generative AI and LLMOps.
Founder @ The Gen Academy | AI Solutions Architect | Ex - Adobe, Microsoft, IBM
Arvind brings a cross-company perspective on AI at scale, built across Microsoft, IBM, and Adobe, where he led data science teams and developed production-grade machine-learning solutions. He has built and deployed enterprise AI systems and focuses on translating AI concepts into practical, production-ready solutions. He holds a Master's from Carnegie Mellon University.
