Automate intelligence gathering by having an AI process transcripts, newsletters, and bookmarks. Instruct it to cluster related information and explicitly summarize what is "new, novel, and contrarian," saving you from information overload and highlighting key signals.
Instead of direct API calls, build Model-Controlled Program (MCP) servers. They act as better guardrails for the AI, allowing it to interact with external data more effectively and even suggest novel use cases based on API documentation.
Treat your personal software as malleable. Instead of enduring friction, describe your pain point to an AI and have it build a solution, like a custom web UI or Kanban board, in hours. This shifts the paradigm from using to co-creating tools.
Move beyond using AI as an assistant and program it to be a critical sparring partner. Pendo's Field CPO had his AI analyze his codebase and brutally call him out for building a system for himself, not for others, forcing a strategic realignment.
Build a system where new data from meetings or intel is automatically appended to existing project or person-specific files. This creates "living files" that compound in value, giving the AI richer, ever-improving context over time, unlike stateless chatbots.
Instead of telling an AI what to do, reverse the prompt. Describe your role, daily friction, and pain points, then ask the AI to devise solutions. This leverages the AI's creativity to generate novel approaches you might not have considered.
When prompting, especially with voice, use emotional and ambitious language. Pushing the AI to make something "brilliantly serendipitous" can elicit more creative responses, particularly from advanced models. This human-like interaction can improve output quality.
Create an AI-driven system to manage your career. An MCP server can scan meeting transcripts and work artifacts for evidence of progress against annual goals, identify skill gaps, and even generate a "promotion readiness score," connecting long-term ambitions to daily work.
While `claude.md` files can guide AI behavior, they aren't always adhered to. Use Claude Code's "session start hooks" instead. They guarantee that critical context like goals, tasks, and past mistakes is injected into every new chat, making the AI more reliable.
For internal tools, consider trusting the AI's first draft of a Product Requirements Document (PRD) without deep review. The AI can often infer edge cases and requirements from the system's context, allowing you to move directly to building, a practice dubbed "vibe CPOing."