Observed Signal · Sep 9, 2026 · Podcast Episode · Source: The Pragmatic Engineer · Impact: 2/5 · Sentiment: Positive
OpenAI's Tibo Sottiaux Discusses Codex Build in Podcast
In a Pragmatic Engineer podcast episode, OpenAI's Tibo Sottiaux discusses the development of Codex, an AI coding agent. He explains the choice of Rust for performance and scalability, the open-source approach, and the decision to support multiple AI models. Sottiaux shares insights on how AI agents are transforming software development, including lower costs for code changes, automated code reviews, and faster re-architecting. He also recounts his experience at Google with a canceled project and his move to OpenAI, drawn by the small team behind ChatGPT. The episode covers the evolution of the Codex harness, its integration with OpenAI systems, and predictions for cloud development environments.
Insightful podcast about AI coding agents, relevant for adtech developers using AI tools, but not directly about advertising or marketing.
Track OpenAI Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Tibo Sottiaux heads the Core Products & Platform org at OpenAI, which includes Codex.
- Codex is built in Rust, chosen for performance and security.
- Codex is open-source and supports models from multiple providers.
- The Codex team at OpenAI uses Codex across the entire software development lifecycle.
- Sottiaux previously worked at Google on a project in the Ads organization that was canceled.
Connected Companies & Entities
7 Entities mapped“Tibo Sottiaux is one of the engineers who created Codex, and today, he heads up the Core Products & Platform org at OpenAI which also includ...”
“While at Google in London, Tibo spent two enjoyable years working on a project in the Ads organization – right up until a VP flew in from Ca...”
“While at Google in London, Tibo spent two enjoyable years working on a project in the Ads organization – right up until a VP flew in from Ca...”
“Claude Code can only be used with Anthropic’s models, whereas Codex is usable with any model, not just OpenAI’s....”
“Mentioned as a user of turbopuffer....”
“Mentioned as a user of turbopuffer....”
“Mentioned as a user of turbopuffer....”
Ontology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
How OpenAI Built Codex and Its Agentic Stack
This deep-dive describes how OpenAI designed, built and operates Codex — a multi-agent coding assistant used by over one million developers weekly. The piece covers product launches (a macOS Codex desktop app and a Rust-based Codex CLI), the shipment of GPT-5.3‑Codex, architecture choices (agent loop state machine, sandboxing, compaction of long contexts), engineering practices (tiered AI-driven code review, AGENTS.md, skills), and developer workflows where Codex generates the majority of its own code. The team reports high release cadence, heavy internal dogfooding and parallel agent workflows for engineers. Safety and sandbox defaults, open sourcing of core agent and CLI, and research practices (using current models to train next models, evals, A/B testing) are highlighted. The article examines how agentic tooling is reshaping software engineering roles and processes at OpenAI.
OpenAI Codex Interview: Leadership Shift After GPT‑5.5
Nate interviewed Tibo, who leads Codex at OpenAI, about the practical impact of OpenAI’s late‑April releases (Codex and GPT‑5.5). The discussion argues the models are now capable enough that the bottleneck for shipping AI-enabled products has moved from model capability and developer workflows to corporate leadership and governance. Nate gives an anecdote of a non‑engineer shipping a full‑stack app using GitHub and Codex, illustrating the widened surface area of who can deliver software. The article frames the problem as five leadership 'chairs' that must develop new instincts to assign human judgment around agentic systems; companies that build these layers will gain a durable advantage, while over‑ or under‑restricting agents creates operational risk. The full episode is behind a Substack paywall.
OpenAI Codex Lead on AI-First Product Work
Andrew Ambrosino, who leads development of the Codex desktop app at OpenAI, describes how generative AI has reshaped product work in an interview published in Lenny’s newsletter. He says nearly 100% of OpenAI employees use Codex weekly and outlines product-team changes driven by AI: collapsed roles (but not role elimination), a "zone defense" model for product managers, and a renewed premium on professional "taste." Ambrosino also discussed launch timing—arguing the app would have failed if released in November rather than February—how he uses Codex in his workflows, and a vision for a unified "home base" that coordinates ChatGPT, Codex, and existing tools. The piece includes sponsor mentions and links to related resources and interviews. Publication date: 2026-06-28.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.