---
title: "Not Prompts, Blueprints"
description: "The more I use AI, the more I return to paper. Strategic planning upstream unlocks autonomous execution downstream."
categories: ["productivity","AI"]
keywords: ["AI workflow planning","Claude productivity","AI agent automation","paper planning AI","agentic workflows","AI micromanagement","autonomous AI tasks"]
ai_summary: "Planning AI workflows on paper before execution eliminates the prompt-response bottleneck. Modern models can now hold complex multi-step tasks, enabling users to sketch decision branches \u0026 walk away while agents run in the background."
date: 2026-03-04
lastmod: 2026-07-17
canonical_url: https://www.tomtunguz.com/filling-the-queue-for-ai/
author: "Tomasz Tunguz"
---


I hate to micromanage & I've been micromanaging AI.

A few months ago, I'd use Claude for a familiar workflow : capturing notes from a meeting, drafting a follow-up email, updating the CRM, writing the investment memo. Micromanagement at 10x speed. The agent would finish a step, then wait. I'd scan the output, type the next instruction, wait again. Prompt, response, prompt, response. I was the bottleneck in my own system.

A year ago, this was necessary. The models couldn't hold a complex task in their heads. Now they can.

But this leverage requires planning. Now I sketch the workflow before I touch the machine. I anticipate the decision branches : what if the company isn't in the CRM? What if the website is down or the call transcript isn't available? I flag the gaps before the agent encounters them.

This morning's notebook page :

{{< email_image src="nekqeumvbxxqgnzvojw7" alt="Handwritten workflow blueprint on graph paper showing parallel agent tasks with decision branches" width="362" height="527" >}}

I took a photo & shared it with Claude & walked away. Workflows as images work beautifully.

The agents run in the background. The memo sat in my inbox, formatted, sourced, ready to send.

Not prompts. Blueprints.