Concepts¶
Understanding the core ideas behind rp1 helps you get the most out of its workflows. These concept guides explain the "why" behind rp1's design decisions.
-
Constitutional Prompting
Learn how rp1 encodes expert knowledge into AI-executable workflows for consistent, single-pass execution.
-
Knowledge-Aware Agents
Discover how agents understand your codebase before writing code, respecting your patterns and architecture.
-
Skill-Agent Pattern
Understand the architecture where skills (SKILL.md) delegate to autonomous agents.
-
Map-Reduce Workflows
See how rp1 parallelizes work for knowledge base generation and PR reviews.
-
Stateless Agents
Learn how resumable interview workflows use file-based state for robustness.
-
Builder-Reviewer Agents
Learn how adversarial cooperation between builder and reviewer agents ensures reliable code implementation.
-
Eval System
Understand how content-addressable attestation ensures prompt changes are tested and traceable.
-
SKILL.md Format
The canonical format specification for all rp1 invocable prompts, replacing the legacy command format.
-
WebUI Interaction
Navigate the rp1 WebUI with keyboard shortcuts, a command palette, and vim-style navigation.
-
State Machines
Declarative workflow state management via co-located Mermaid state diagrams for validated transitions and dashboard visibility.
Quick Overview¶
| Concept | What It Is | Why It Matters |
|---|---|---|
| Constitutional Prompting | Expert knowledge encoded in prompts | No iteration loops, consistent output |
| Knowledge-Aware Agents | Agents that understand your codebase | Output fits your architecture |
| Skill-Agent Pattern | Skills delegate to agents | Clean, reusable workflows |
| Map-Reduce Workflows | Parallel processing pattern | Fast KB and PR analysis |
| Stateless Agents | Resumable interview workflows | Robust, transparent state |
| Builder-Reviewer Agents | Adversarial agent cooperation | Higher quality, reliable code |
| Eval System | Content-addressable attestation | Deterministic, traceable releases |
| SKILL.md Format | Canonical format for all rp1 prompts | Single source of truth, cross-platform |
| WebUI Interaction | Keyboard-first WebUI navigation | Fast navigation without a mouse |
| State Machines | Declarative workflow state management | Validated transitions, automatic dashboard visibility |
Where to Start¶
New to rp1? Start with Constitutional Prompting to understand rp1's core philosophy.
Want context-aware output? Read Knowledge-Aware Agents to learn about the knowledge base.
Curious about architecture? See Skill-Agent Pattern for the technical design.
Need performance? Check Map-Reduce Workflows for parallelization patterns.
Building resumable workflows? See Stateless Agents for interrupt-safe interview patterns.
Want reliable implementations? See Builder-Reviewer Agents for adversarial cooperation.
Building evals for prompts? See Eval System for content-addressable attestation.
Migrating commands to skills? See SKILL.md Format for the canonical format specification.
Using the WebUI? See WebUI Interaction for keyboard shortcuts and the command palette.
Adding workflow tracking to a skill? See State Machines for the declarative state management pattern.