Instead of relying on engineers to remember documented procedures (e.g., pre-commit checklists), encode these processes into custom AI skills. This turns static best-practice documents into automated, executable tools that enforce standards and reduce toil.

Shopify built "Tangent," an auto-research system that runs experiments, analyzes results, and modifies pipelines to maximize a goal. This has democratized ML development, with a Product Manager becoming the tool's top user, effectively cutting out the ML engineer for many optimization tasks.

Don't just save good prompts; codify entire successful back-and-forth conversations into reusable "skills" within AI platforms like Claude. This automates complex, multi-step tasks like content repurposing with a single command, saving significant time.

The initial version of Codex was a powerful but hard-to-adopt cloud agent. The key growth unlock was meeting developers in their existing workflows with an IDE extension. This provided an intuitive on-ramp, building trust before introducing more advanced, asynchronous delegation features.

Anthropic is developing a system called "CASH" to automate growth work. It uses Claude to identify opportunities, build features (like copy changes), test them, and analyze results. The system is already delivering results comparable to a junior PM and is expected to handle increasingly complex experiments.

The key value of Codex for a growth PM at OpenAI wasn't just viewing a single dashboard, but building a unified web app that pulls from multiple scattered sources (Databricks, Tableau). This combines data synthesis with a TLDR summary, overcoming cognitive overload.

To scale AI usage beyond engineering, GitHub avoids complex new UIs. Instead, they provide a command-line interface (CLI) and shared "skills" (scripts) even to non-technical staff. This allows everyone to run powerful automations and access company context from disparate sources without changing their existing workflows.

Using plain-English rule files in tools like Cursor, data teams can create reusable AI agents that automate the entire A/B test write-up process. The agent can fetch data from an experimentation platform, pull context from Notion, analyze results, and generate a standardized report automatically.

Data from OpenAI reveals a massive and growing productivity gap. Engineers who actively use the AI coding assistant Codex are opening 70% more pull requests than their peers, indicating a significant boost in efficiency and a widening skill divide.