AI Transforms Engineering Workflows: From Code Generation to Meeting Prep

May 11, 2026 · Lenny's Podcast
🎧 PodShort 47 min squeezed to 3 AI SprinklerAS Sales Tech
Episode artwork
Ryan Nystrom
Engineering Manager at Notion
Lenny's Podcast
47 min squeezed to 3
Full episode from Lenny's Podcast
Quotable Moments

I literally don't know what I'm doing here. You got to explain it like I'm a five-year-old.

Ryan NystromEngineering Manager at Notion
00:01

Your AI, your agent is never gonna complain when you ask it to do this 5 minutes before the meeting starts.

Claire VoProduct Leader and AI Obsessive (Host)
00:53
Key Insights
  • AI agents can automate meeting pre-reads by compiling updates from various sources (Slack, tasks, PRs) within the last 24 hours, ensuring team members focus on decisions and problems during meetings instead of rote status updates.
  • AI can generate code directly from detailed markdown specifications, including verification loops and test cases, significantly accelerating development and shifting engineers' focus towards systems thinking and architecture.
  • AI can monitor and improve CI/CD pipeline speeds by providing real-time metrics and insights, leading to faster signal reception, increased engineer confidence in making changes, and higher development velocity.
  • Automating tedious tasks like meeting prep, status reporting, and code generation through AI leads to a more relaxed, fun, and productive work environment, allowing engineers and managers to focus on more creative and impactful work.
  • AI agents can help engineering managers run more effective teams by automating information gathering, facilitating focused discussions, and enabling managers to be more hands-on with coding rather than just administrative tasks.
  • AI-generated meeting summaries and pre-reads ensure that all team members, including introverts who might not speak up in meetings, have their contributions and progress highlighted, fostering a more inclusive and informed environment.
  • The current era demands a focus on hard skills related to AI and automation (how to write code, how to leverage new tools), as AI handles repetitive tasks, freeing up human capacity for higher-level problem-solving and architectural thinking.
  • AI models can be instructed to defend their generated code or decisions, allowing engineers to challenge outputs and receive detailed justifications, promoting a more rigorous review process.
Metrics Mentioned
  • Up to 13% (Improvement in CI test speeds for Notion's Tab Block feature.)
  • 1300 agent PRs per week (Number of Pull Requests generated by AI agents at Stripe.)

RevBots.ai View:

  • AI Sprinkler stage: AI bolted onto existing workflows improves efficiency but lacks full integration.
  • Automating meeting prep and code generation reduces manual effort, freeing time for higher-level tasks.
  • AI-driven CI/CD optimization highlights the potential for AI to enhance technical operations.
  • The focus on hard AI skills underscores the need for teams to adapt to AI-driven workflows.
🎧Full Episode:Lenny's Podcast →