Core Workflow

Each session is called a topic:

1. Create a topic and select an ACP-compatible agent
2. Type a request + mention code with @ClassName or attach a screenshot
3. The AI works autonomously (task decomposition, code changes, tests)
4. When the AI needs approval, it pauses and asks in the chat
5. Respond with pulldown selection — the AI resumes
6. Topic status is always visible in the sidebar

AI GUI Tools Are Going Mainstream

Dedicated GUI tools for AI coding agents are becoming standard:

• Claude Desktop — Claude with tools, MCP, and file access
• Codex Desktop — OpenAI's autonomous coding environment
• Cursor / Windsurf — AI-native editors

These tools lower the barrier for interacting with AI agents beyond simple chat.

The Shift: IDE → Multi-Agent Delegation

The AI can now handle entire feature-level tasks, not just line completions.

Tools are evolving: the UI is no longer "editor + chat" — it's session orchestration.

Why Pharo Needs This Too

Pharo developers should be able to leverage the same paradigm:

• Rich live environment — classes, methods, and runtime are right there
• pharo-acp already provides ACP client support for multiple agents
• Multiple projects can run in parallel in one image

Key Advantages Over Generic Tools

Installation — Pharo Side

Open a Playground in a Pharo 12+ image and evaluate:

Metacello new
    baseline: 'AgenticBrowser';
    repository: 'github://mumez/pharo-agentic-browser:main/src';
    load.

Then open the browser:

AgenticBrowser open.

Installation — Agent Side

Any ACP-compatible agent - preset list:

Also supported: OpenCode, Kilo Code, and more

Recommended: Install smalltalk-dev-plugin in your agent for better Smalltalk

Creating a Topic

1. Click + New Topic
2. Enter a title and select an agent
3. (Optional) Set an existing project directory
4. Click Create — topic appears in the left sidebar
5. (Optional) Right-click → Set Target Packages... to configure tracked packages

Topic State Icons

Icon	State	Meaning
	working	AI is actively running
?	waitingForHuman	AI needs approval
●	endTurn	Turn completed
✓	goalAchieved	Goal reached

Human-in-the-Loop

When the AI requests permission:

• Status changes to ? (waitingForHuman)
• Send button becomes Confirm
• Cancel button becomes Deny

Respond by clicking the button — the AI resumes seamlessly.

Code Mentions

Reference Pharo classes or methods directly in the chat:

@QueryClass @DBAdapter>>connect please refactor this

AgenticBrowser resolves each @mention to its Tonel source and attaches it as an ACP text resource — no copy-paste needed.

Drag and Drop

• Drag a class from the System Browser → inserts @ClassName
• Drag a method from the System Browser → inserts @ClassName>>methodName

Screen Captures

Click the [ ] button to attach a screenshot:

1. Click the button — cursor becomes a crosshair
2. Drag to select the area
3. A mention like @sc-20260528-001.png is inserted in the input
4. Send — the PNG is attached as an image resource to the prompt

Files are saved to <agenticBrowserRoot>/screenshots/sc-YYYYMMDD-NNN.png.

Goal Setting

Right-click a topic → Set Goal... to enter a completion condition:

all tests pass

AgenticBrowser sends a goal prompt to the AI:

Goal has been set: all tests pass. When the goal is achieved, summarize and report in result-<topic-id>.md. Keep retrying until the goal is achieved.

When result-<topic-id>.md is created, the topic transitions to ✓ (#goalAchieved).

Goal Achievement Hooks

Two hooks fire when a goal is reached:

Announcement

topic announcer
    when: AbTopicGoalAchieved
    do: [:ann | Transcript crShow: ann topic title , ' achieved: ' , ann goal result].

Callback Block

topic whenGoalAchieved: [:goal | Transcript crShow: goal result].

Integrate goal events into your own automation workflows.

Session Persistence

Topics are automatically saved to ab-topics.fuel using Pharo's Fuel serializer — they survive image restarts.

Manual save/restore:

AbTopicManager save.
AbTopicManager load.

Per-topic state (settings, status, conversation) is fully persisted.

Adding MCP Servers

Place mcp.json in your AgenticBrowser root directory:

{
  "mcpServers": {
    "my-server": {
      "command": "uvx",
      "args": ["my-server-package"],
      "env": {"API_KEY": "value"}
    }
  }
}

• Built-in smalltalk-interop and smalltalk-validator servers are auto-merged by default
• Set useDefaultMcpServers: false to use only your own mcp.json

Adding Custom Agents

From a Playground

AbSettings default codingAgents: (AbSettings default codingAgents copyWith:
    {'name' -> 'my-agent'.
    'command' -> #('my-agent' '--acp')} asDictionary).
AbSettings save.

Or edit ab-settings.json directly

The agent appears as a preset in the New Topic dialog on next open.

Global Settings

Settings can also be configured per-topic via right-click → Edit Settings...

Summary

pharo-agentic-browser brings the multi-agent delegation paradigm to Pharo:

• Native GUI — manage multiple AI sessions without leaving your image
• Agent-agnostic — any ACP-compatible agent works
• Rich context — code mentions, drag-and-drop, screen captures
• Human-in-the-loop — conversational approval, no interruption dialogs
• Goal-driven — set completion conditions, hook into results
• Extensible — custom MCP servers and agents with minimal configuration