Tests in spec and avoiding brittle tests

What does it take to make AI work inside engineering teams?

This high-stakes compilation episode with Ian Thomas (Meta), Wesley Reisz (ThoughtWorks), Sepehr Khosravi (Coinbase), and David Stein (ServiceTitan) goes inside the engineering rooms of the world's most sophisticated tech organisations to uncover how they're moving past AI hype into AI-native production.

On the docket:
• How Meta achieved 80% weekly AI adoption through grassroots community building instead of top-down mandates
• Why ThoughtWorks uses the RIPPER-5 framework to structure AI workflows and prevent agents from jumping straight to code
• When Coinbase engineers use Cursor versus Claude Code and why sub-agents are critical for managing context without bloat
• How ServiceTitan migrated 247 legacy metrics in three weeks using self-healing validation loops and standardized agent tasks

If you're trying to make AI useful inside your team, this episode shows exactly what matters.

Connect with us here:

Ian Thomas: https://www.linkedin.com/in/anatomic/?originalSubdomain=uk
Wesley Reisz: https://www.linkedin.com/in/wesreisz/
Sepehr Khosravi: https://www.linkedin.com/in/sepehrkhosravi/
David Stein: https://www.linkedin.com/in/steindavidj/
Simon Maple: https://www.linkedin.com/in/simonmaple/
Tessl: https://www.linkedin.com/company/tesslio/
AI Native Dev: https://www.linkedin.com/showcase/ai-native-dev/

Resources:

AI Scouts - https://aiscouts.org/
Thoughtworks’ knowledge base insights - https://www.thoughtworks.com/en-sg/insights/blog/generative-ai/deep-kernel-level-AI-RCA-with-MCP
Check out Birgitta Böckeler’s full EP - https://youtu.be/uYmSco0s6Xo?si=FIK293aJXu3sxvt6
Cursor’s community forum - https://forum.cursor.com/t/i-created-an-amazing-mode-called-riper-5-mode-fixes-claude-3-7-drastically/

Join the AI Native Dev Community on Discord: https://tessl.co/4ghikjh

Ask us questions: podcast@tessl.io