Instead of typing structured prompts, the most effective way to onboard an agent is to use "ramble mode." Simply record a long, stream-of-consciousness voice note explaining your needs, context, and goals. The AI can parse this high-bandwidth, unstructured data to build a comprehensive understanding of its role.

A powerful AI workflow involves two stages. First, use a standard LLM like Claude for brainstorming and generating text-based plans. Then, package that context and move the project to a coding-focused AI like Claude Code to build the actual software or digital asset, such as a landing page.

To gain a macro perspective, Melanie Perkins does an "AI walk." She goes for a walk and dictates all her thoughts on her phone using a notes app. Later, she uses AI to summarize the brain dump, helping her filter ideas, identify action items, and think more strategically.

Instead of typing, dictating prompts for AI coding tools allows for faster and more detailed instructions. Speaking your thought process naturally includes more context and nuance, which leads to better results from the AI. Tools like Whisperflow are optimized with developer terminology for higher accuracy.

Advanced speech-to-text apps like Whisperflow enable a new workflow: go for a walk, ramble your thoughts on a topic, and then feed the raw transcript to another AI to structure it into a polished blog post or book chapter, decoupling writing from a desk.

To get the best results from AI code generation platforms, first use a conversational LLM like Claude to brainstorm and write a detailed product spec. This two-step process—spec generation then code generation—improves the final output and reduces costly iterations with the coding agent.

A powerful but unintuitive AI development pattern is to give a model a vague goal and let it attempt a full implementation. This "throwaway" draft, with its mistakes and unexpected choices, provides crucial insights for writing a much more accurate plan for the final version.

Shift away from the traditional model of drafting content yourself and asking AI for edits. Instead, leverage the AI's near-infinite output capacity to generate a wide range of initial ideas or drafts. This allows you to quickly identify patterns, discard unworkable concepts, and focus your energy on high-level refinement rather than initial creation.

Leverage Large Language Models (LLMs) to overcome the 'blank page' problem in strategy development. Use them as a conversational partner to organize scattered thoughts, build a narrative, and refine your ideas before presenting them to stakeholders or the wider team.