UseAgentBEFORE YOU RUN
Know the job and the reviewer.
This playbook is for solo founders and very small teams with more recurring work than dedicated owners.
TARGET OUTCOME
A short roster of focused agents, each attached to a real deliverable and a clear review point.
Bring these inputs
Better source material makes the result easier to review and safer to reuse.
- A list of repeated founder tasks
- Documents each task relies on
- The consequence of a wrong answer
- A weekly review calendar
COPYABLE STARTER
Start with this prompt.
Replace bracketed details, attach the source material, and keep the limits until your team has reviewed a few runs.
Prepare my founder desk for tomorrow using only the material supplied. Create four sections: customers needing attention, product decisions, pipeline follow-ups, and operational risks. For each item, show the source, proposed next action, and whether I need to decide, review, or simply know. Do not contact anyone or change any system.
THE PLAYBOOK
Move from context to a reviewed result.
- 01
List recurring outputs
Start with documents and decisions you already produce, such as a pipeline brief or customer follow-up queue.
- 02
Split jobs by context
Give support, research, engineering, and operations separate jobs when their sources and review criteria differ.
- 03
Create one review desk
Ask each run to return the same decision labels so you can scan what needs attention.
- 04
Automate stable inputs
Put collection and drafting on a routine after several clean manual runs. Keep external actions for review.
DELIVERABLES
What the run should produce
- Agent roster by job
- Founder decision desk
- Reusable task prompts
- Weekly review cadence
HUMAN REVIEW
Check this before it leaves the team
- Each agent has one clear owner
- High-consequence work stays review-gated
- Repeated context lives in knowledge
- Routines have useful failure states
Keep exploring this workflow