Code review in the AI era
AI makes code cheaper to produce. That makes review, verification, and engineering judgment more important, not less.
Writing & Speaking
Ideas from building AI systems inside real constraints.
I write and speak about the places where AI meets engineering judgment: code review, evaluation, developer workflows, product constraints, and business execution.
Current talks
Useful for AI, product, and engineering leadership rooms.
These are not abstract trend talks. They are practical strategy sessions rooted in production work, early-stage company constraints, and the realities of building with LLMs.
From demo to workflow
Why AI prototypes often fail to become useful systems, and what production teams need to design around instead.
Evals for operators
How founders, product leaders, and engineering teams can use evaluation without turning it into theater.
What AI changes about engineering leadership
As output volume rises, leaders need new instincts around quality, ownership, feedback loops, and team leverage.
Selected writing
Curated essays
The archive is intentionally small. I would rather keep a few pieces that support the public thesis than maintain a long list of unfinished placeholders.
From Vibecoded Project to OpenAI: Why the OpenClaw Move Matters
What the OpenClaw story suggests about long-running agents, and why autonomy only becomes useful when it is shaped by workflows, constraints, and feedback loops.
6 min read
AI Consulting: Lessons from a Year of Thinking, Talking, and Building
Lessons from a year of AI consulting conversations: why trust, framing, and business understanding matter as much as the technical solution.
10 min read
Speaker kit
Short bios for organizers
Short bio
Gaurav Pooniwala is a founding engineer at Cubic, building AI code review systems for complex codebases. His work focuses on production AI systems, evaluation, developer workflows, and the shift from AI demos to dependable products.
Longer bio
Gaurav Pooniwala is a production AI operator and founding engineer at Cubic. His career spans deep learning research at Samsung R&D, generative video systems at Rephrase AI before its acquisition by Adobe, agentic workflow products at startups, and current work on AI code review. He is interested in the systems, evaluation practices, and leadership judgment required to make AI useful inside real organizations.
Start a conversation
For talks, panels, podcasts, workshops, essays, or thoughtful operator conversations, send a note with the context and audience.