# About the Agent Centric Development Cycle

## Overview

The Agent Centric Development Cycle (AC/DC) is Sonar’s framework for building software in an AI-driven world, where agents generate most of the code and humans govern quality.\
It defines a continuous 4-stage loop for every AI-generated change:

**Guide → Generate → Verify → Solve**

* **Guide** provides project context to agents before code generation.
* **Generate** is where the AI agent writes code.
* **Verify** analyzes the generated code.
* **Solve** fixes issues found during verification.

This workflow helps agents produce code that aligns more closely with project standards, catches issues earlier, and shortens the review-to-fix cycle.

The diagram below shows where AC/DC features fit in this cycle.

```mermaid
%%{init: {'theme': 'base', 'themeVariables': {
  'primaryColor': '#E6F2FF',
  'primaryBorderColor': '#126ED3',
  'primaryTextColor': '#111827',
  'clusterBkg': 'rgba(18,110,211,0.06)',
  'clusterBorder': '#126ED3',
  'lineColor': '#126ED3'
}}}%%
flowchart LR
  %% Phases laid out left-to-right, details descending within each phase

  subgraph GuidePhase["Guide"]
    direction TB
    CA["Context Augmentation
---
Project-specific context before generation"]
  end

  subgraph GeneratePhase["Generate"]
    direction TB
    GEN_DESC["
Agent generates or updates code
using guided context and constraints"]
  end

  subgraph VerifyPhase["Verify"]
    direction TB
    AA["Agentic Analysis
---
Analyzes code with full CI context"]
    ACR["AI Code Review
---
Inline comments, summaries,
walkthroughs, diagrams on PRs"]
  end

  subgraph SolvePhase["Solve"]
    direction TB
    RA["Remediation Agent
---
Fixes PR & backlog issues,
re-analyzes fixes"]
    CF["AI CodeFix
---
Generates fixes for individual SonarQube issues"]
  end

  %% Left-to-right flow between phases
  CA --> GEN_DESC
  GEN_DESC --> AA
  GEN_DESC --> ACR
  AA --> RA
  ACR --> RA

  %% Loop back when code has issues (Verify → Generate)
  AA -->|Code has issues| GEN_DESC
```

## Guide

Context Augmentation provides project-specific context—coding guidelines, architectural information, and codebase context—to the AI agent before code generation. This reduces avoidable violations and inconsistent code patterns.

## Generate

Your AI agent generates or updates code using the context and constraints gathered in the Guide phase.

## Verify

Agentic Analysis analyzes generated code during the agent workflow. The agent can use the analysis results to refine the code before review. This surfaces quality and security issues before they reach pull request review or CI.

AI Code Review posts inline review comments, change summaries, and on-demand walkthroughs and architecture diagrams directly on pull requests.

## Solve

The Remediation Agent generates fix suggestions for issues found in pull requests and in the backlog. AI CodeFix generates fix suggestions for individual issues detected by SonarQube. This reduces manual rework and supports incremental cleanup of existing issues.

## Get started

See [Features](/agent-centric-development-cycle/features/context-augmentation.md) for product details and [How-to guides](/agent-centric-development-cycle/how-to-guides/guide-agents-with-context.md) for setup and usage.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.sonarsource.com/agent-centric-development-cycle/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.