To maximize leverage, reframe every SDLC component—docs, tests, review agents—as a way to 'prompt inject' non-functional requirements into the agent. This approach teases out expert knowledge from engineers' heads and makes it part of the automated system, guided by the agent's mistakes.

Static playbooks quickly become outdated. Create a dynamic 'living playbook' by having an AI agent continuously synthesize information from recent projects. It can analyze Google Docs, Slack conversations, and call notes to distill the most current best practices, ensuring your team always uses the latest version.

Establish a powerful feedback loop where the AI agent analyzes your notes to find inefficiencies, proposes a solution as a new custom command, and then immediately writes the code for that command upon your approval. The system becomes self-improving, building its own upgrades.

Effective AI planning isn't a one-shot command. It's an iterative exploration to understand system limitations, edge cases, and what you actually want. Use the agent to generate explainers (e.g., on Whisper's failure modes) to eliminate blind spots before committing to a complex workflow.

Like a product requirements document (PRD), an AI skill and its evaluation (eval) are never 'done.' As you use the system, you'll learn new things. Continually ask the AI to update its own instructions to build increasingly effective automations over time.

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.

To successfully steer autonomous coding agents, specifications must be exhaustive. They need to go beyond feature requirements to include service boundaries, data models, documented "gotchas" from legacy systems, and even operational and security requirements.

The best AI results come from iterative refinement. After an initial build, continue conversing with the agent to tweak outputs. Tell it to adjust sentence structure or writing style and redeploy. This continuous feedback loop is key to improving performance.

A powerful technique for creating robust software plans is to use AI as an adversarial partner. After drafting a specification, prompt an AI to "tear it apart" by identifying underspecified or inconsistent points. Iterate on this process until the AI's feedback becomes niche, indicating a solid spec.