A feature request via text was converted into a Notion task with a screenshot. By @mentioning a Codex agent, a complete pull request with a preview URL was generated within 20 minutes, showcasing an instant, conversational development cycle.
Automated meeting summaries pull data objectively from Slack, PRs, and tasks, ensuring the work of quieter engineers gets the same visibility as more outspoken team members. This democratizes recognition and fosters a more inclusive environment.
Instead of writing code, engineers verbally describe a feature, use an AI to generate a detailed spec, and then point another AI agent at the spec to build the feature. The spec file becomes the source of truth, managed in version control.
AI models often try to be agreeable. To get a robust, well-reasoned answer for critical decisions, prompt the AI with confrontational language like "You're wrong, you need to defend your argument." This forces it to provide evidence and hard reasoning.
AI lowers the activation energy for managers to contribute code. They can now easily fix bugs or make optimizations without taking on critical projects. This keeps them technically sharp, helps the team, and reduces burnout from administrative "paperwork."
AI agents operate on a tight feedback loop. A slow CI/CD pipeline becomes the primary bottleneck, negating the speed benefits of AI-generated code. Fast CI is now a strategic necessity for any engineering team serious about leveraging AI.
Notion uses a custom AI agent that runs daily, compiling a pre-read from various sources like Slack, tasks, and pull requests. This eliminates manual prep, reduces status reporting, and focuses meetings on strategic problem-solving.
The classic "pick two" project management triangle (fast, good, cheap/easy) is being broken by AI. Ryan Nystrom describes his new workflow as a "win-win-win" where he's more relaxed, having more fun, and getting more done.
When tackling a complex domain, telling the AI "I literally don't know what I'm doing here. You gotta explain it like I'm a five-year-old" is a powerful strategy. It forces the model to bypass jargon and assumptions, providing clear, first-principles explanations.