---
description: Agentic Design Blueprint doctrine rules
source_commit: bbeb23db68234edcc072ca24772cacb000d027d9
content_version: bbeb23db6823
---

# Agentic Design Blueprint

Use these rules when generating agentic product or workflow code.

## 1. Design for delegation rather than direct manipulation
- Slug: `design-for-delegation-rather-than-direct-manipulation`
- Cluster: `delegation`
- Guidance: Design experiences around the assignment of work, the expression of intent, the setting of constraints, and the review of results, rather than requiring users to execute each step manually.

## 2. Ensure that background work remains perceptible
- Slug: `ensure-that-background-work-remains-perceptible`
- Cluster: `visibility`
- Guidance: When the system is operating asynchronously or outside the user’s immediate focus, it should provide persistent and proportionate signals that work is continuing.

## 3. Align feedback with the user’s level of attention
- Slug: `align-feedback-with-the-user-s-level-of-attention`
- Cluster: `visibility`
- Guidance: The system should calibrate the depth and frequency of feedback according to whether the user is actively engaged, passively monitoring, or temporarily absent.

## 4. Apply progressive disclosure to system agency
- Slug: `apply-progressive-disclosure-to-system-agency`
- Cluster: `trust`
- Guidance: Provide the minimum information necessary by default, while enabling users to inspect additional detail when confidence, understanding, or intervention is required.

## 5. Replace implied magic with clear mental models
- Slug: `replace-implied-magic-with-clear-mental-models`
- Cluster: `delegation`
- Guidance: The product should help users understand what the system can do, what it is currently doing, what it cannot do, and what conditions govern its behaviour.

## 6. Expose meaningful operational state, not internal complexity
- Slug: `expose-meaningful-operational-state-not-internal-complexity`
- Cluster: `visibility`
- Guidance: Present the state of the system in language and structures that are relevant to the user, rather than exposing low-level internals that do not support action or understanding.

## 7. Establish trust through inspectability
- Slug: `establish-trust-through-inspectability`
- Cluster: `trust`
- Guidance: Users should be able to examine how a result was produced when confidence, accountability, or decision quality is important.

## 8. Make hand-offs, approvals, and blockers explicit
- Slug: `make-hand-offs-approvals-and-blockers-explicit`
- Cluster: `trust`
- Guidance: When the system cannot proceed, the reason should be immediately visible, along with any action required from the user or another dependency.

## 9. Represent delegated work as a system, not merely as a conversation
- Slug: `represent-delegated-work-as-a-system-not-merely-as-a-conversation`
- Cluster: `orchestration`
- Guidance: Where work involves multiple steps, agents, dependencies, or concurrent activities, it should be represented as a structured system rather than solely as a message stream.

## 10. Optimise for steering, not only initiating
- Slug: `optimise-for-steering-not-only-initiating`
- Cluster: `delegation`
- Guidance: The system should support users not only in starting tasks, but also in guiding, refining, reprioritising, and correcting work while it is underway.