Shama Keskar
3X founding CTO · Building AI you can actually ship · Author, The Trust Layer (In-progress)
Seattle, Washington, United States
Actions
Shama Keskar is a three-time founding CTO. But that is not where the story started.
She got into tech through the back door 🙂 Physics graduate. No CS degree. First job in the United States was cashier at a Big 5 sporting goods store in Silicon Valley. Broke into Google in 2004 as a QA engineer.
Then spent the next 15+ years scaling engineering across Google, LinkedIn, and Amazon – leading quality for Google's Online Advertising platform (scope: ~98% of company revenue), pioneering Alexa automation, launching Amazon Go and Amazon One as Amazon's first physical retail launches. Grew teams from 4 to 50+ engineers.
In 2021 she went founding CTO. And has not stopped since – Nickelytics (edge AI + computer vision for autonomous outdoor advertising), SignAI (real-time bidirectional ASL/English AI interpreter prototype demoed to Microsoft), and most recently co-founder & founding CTO of an AI-native fashion wholesale platform where she built the production document extraction system that hit 96% accuracy across live paying merchants.
Currently writing her first book The Trust Layer – building AI systems you can actually ship. Her thesis is simple – generation is solved, trust is the product. She writes about it publicly on Substack and speaks on it wherever engineering leaders will let her.
The through-line from QA engineer at Google to three-time founding CTO has always been the same – care about the boring engineering work everyone else skips. Evals, reliability, trust architecture, et al. Ship things that actually work in production.
Based in Seattle. Available for keynotes, panels, closed-door founder sessions, and technical deep-dives.
Links
Area of Expertise
Topics
Transactional Agentic Execution: Rollback Mechanics
Everyone can build an agent that passes a 5-step demo. But 35 steps into refactoring a real codebase, non-determinism catches up with you: tool calls fail, local state gets corrupted, and the agent burns thousands of tokens trying to patch code built on a broken premise. Standard retry loops don't fix this, they just compound context pollution until the run collapses.
In this talk, we stop treating agent execution like a simple prompt loop and start treating it like a database engine. We'll dive into the architecture of Transactional Agentic Workflows, bringing atomic execution, AST-aware snapshotting, and deterministic git/context rollbacks to long-horizon AI systems.
We will unpack:
Atomic Execution Units: Wrapping multi-file agent edits into rollback-safe, isolated transactions.
AST-Level Checkpointing: Using tree-sitter state graphs to checkpoint clean code states before an agent branches into complex refactoring.
Context Pruning & Rewind Mechanics: How to strip failed execution paths from prompt history without losing the diagnostic error signature.
Orchestrator-Worker Circuit Breakers: Detecting infinite fix loops early and triggering hard state rewinds before workspace corruption occurs.
You'll leave with a battle-tested architectural framework for building long-horizon agents that can recover gracefully from catastrophic failures in real-world, messy codebases.
Shama Keskar
3X founding CTO · Building AI you can actually ship · Author, The Trust Layer (In-progress)
Seattle, Washington, United States
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top