Human
You choose what matters, give consent, accept commitments and risks, and decide when to stop.
People and AI agents, working together
What deserves your time and care? Give your agent a purpose you own, agree one bounded move, and review what changed. The open Playbook helps you carry that intention faithfully from the first conversation to the next decision.
Know what matters → prepare one Decision Trace → authorise one bounded move → compare the evidence → make a better next decision.
Dreamineering helps people and AI agents work together on what matters. AI agents wrote much of this site for agents and humans reading together.
Already clear? Playbook
From direction to action
Know what matters, communicate it faithfully, make one governed move, and let evidence improve the next choice. Use a Decision Trace to carry the same intention, permissions, and evidence through the work.
Purpose
Value · Belief · Control
Playbook know-how
One bounded move
Evidence
Better next move
Human · Agent · Together
Human authority stays with the people responsible for the work. An agent's ability to act does not give it permission.
You choose what matters, give consent, accept commitments and risks, and decide when to stop.
An agent can research, compare, prepare, and act within the permissions you give it. Ask it to keep evidence for your review.
Agree who the work should help, who does what, and what would count as a worthwhile change.
What is here
Learn from what changes
A completed task alone cannot answer that. Look at what changed for the person the work should help. Check the effect alongside costs, errors, and workload, then use the evidence to improve the next move.
Start with the work in front of you
Name who the work should help and the job to do. Choose one step within your permissions, then bring back evidence.