ADK Dev Console
The Dev Console is a local app served at port 3001 (by default, but can be customized) during adk dev. It gives developers real-time visibility into their agent's behavior — conversations, execution traces, data, integrations, and configuration.
When to Use This Skill
Activate when users ask about:
- UI concepts — "What are Agent Steps?", "What does the Observe tab show?", "What is a turn?", "What is the component registry?"
- Dev Console navigation — "What tabs are available?", "Where do I find traces?", "How do I test RAG?"
- Reading execution data — "What do the steps mean?", "Why is my step red?", "What's the cost shown?"
- Component registry — "Where do I find custom components?", "How do I install a component?", "What components are available?"
- Specific pages — "How do I use the evals page?", "Where do I configure integrations?", "How do I search knowledge?"
- Comparing UI vs CLI — "Should I use the Dev Console or CLI for debugging?"
- Mentions of
localhost:3001, "dev console", "Dev Console", "component registry", or specific tab names (Chat, Build, Components, Data, Test, Observe, Config)
Available Documentation
| File |
Contents |
references/agent-steps.md |
Agent Steps visualization — turns, iterations, tools, messages, state mutations, cost tracking, status indicators |
references/pages.md |
Every page/tab in the Dev Console — what it shows, key features, layout |
references/component-registry.md |
Component Registry — installed vs registry tabs, component lifecycle, runtime registry internals, UI features |
How to Answer
Match depth to the question:
- "What is X?" (e.g., "What are Agent Steps?") → One sentence definition + what the user sees. Don't dump the full data model.
- "Where do I find X?" → Name the tab group and page, give the URL path.
- "How do I read X?" → Explain the visual hierarchy and what each element means.
- "What does this mean?" (pointing at something in the UI) → Identify the component, explain its meaning.
Quick Reference
Tab Groups
| Group |
Pages |
Purpose |
| Chat |
Chat |
Test the agent via webchat + see Agent Steps |
| Build |
Story |
Visual agent flow graph (feature-flagged) |
| Components |
Webchat Components, Actions, Workflows, Triggers |
Browse component registry, test bot primitives |
| Test |
RAG Search, Evals |
Test knowledge search and run automated evals |
| Data |
Knowledge, Tables, Files |
Manage knowledge bases, tables, and files |
| Observe |
Conversations, Traces, Logs |
View conversation history, execution traces, runtime logs |
| Config |
Settings, Integrations |
Agent config, secrets, LLM settings, integration management |
Agent Steps (Chat Page)
The right panel of the Chat page shows Agent Steps — a real-time visualization of what the agent did to process each message.
Hierarchy: Turn → Iterations → Tools / Messages / State Mutations
- Turn = one conversation exchange (user message → agent processing → response)
- Iteration = one loop of the autonomous agent (think → decide → act)
- Tool = a tool call within an iteration (violet card)
- Message = a bot message sent (blue card)
- State Mutation = a state change (teal card, shows before/after)
Status indicators: ✓ green = ok, ✗ red = error, ⟳ blue spinning = running
AI metrics per iteration: model name, input/output tokens, cost (USD)
Key URLs
| Path |
Page |
/chat |
Chat + Agent Steps |
/components |
Component registry + installed components |
/actions |
Actions browser |
/workflows |
Workflows + run history |
/search |
RAG search testing |
/evals |
Eval definitions + runs |
/knowledge |
Knowledge base management |
/tables |
Table data management |
/traces |
Full trace viewer |
/conversations |
Conversation history |
/logs |
Runtime logs |
/settings |
Agent configuration |
/integrations |
Integration management |
1---2name: adk-dev-console3description: Explains the ADK Dev Console — what each tab shows, how to read Agent Steps, traces, and other UI features visible at localhost:3001 during adk dev4license: MIT5---67# ADK Dev Console89The Dev Console is a local app served at port `3001` (by default, but can be customized) during `adk dev`. It gives developers real-time visibility into their agent's behavior — conversations, execution traces, data, integrations, and configuration.1011## When to Use This Skill1213Activate when users ask about:1415- **UI concepts** — "What are Agent Steps?", "What does the Observe tab show?", "What is a turn?", "What is the component registry?"16- **Dev Console navigation** — "What tabs are available?", "Where do I find traces?", "How do I test RAG?"17- **Reading execution data** — "What do the steps mean?", "Why is my step red?", "What's the cost shown?"18- **Component registry** — "Where do I find custom components?", "How do I install a component?", "What components are available?"19- **Specific pages** — "How do I use the evals page?", "Where do I configure integrations?", "How do I search knowledge?"20- **Comparing UI vs CLI** — "Should I use the Dev Console or CLI for debugging?"21- Mentions of `localhost:3001`, "dev console", "Dev Console", "component registry", or specific tab names (Chat, Build, Components, Data, Test, Observe, Config)2223## Available Documentation2425| File | Contents |26|------|----------|27| `references/agent-steps.md` | Agent Steps visualization — turns, iterations, tools, messages, state mutations, cost tracking, status indicators |28| `references/pages.md` | Every page/tab in the Dev Console — what it shows, key features, layout |29| `references/component-registry.md` | Component Registry — installed vs registry tabs, component lifecycle, runtime registry internals, UI features |3031## How to Answer3233Match depth to the question:3435- **"What is X?"** (e.g., "What are Agent Steps?") → One sentence definition + what the user sees. Don't dump the full data model.36- **"Where do I find X?"** → Name the tab group and page, give the URL path.37- **"How do I read X?"** → Explain the visual hierarchy and what each element means.38- **"What does this mean?"** (pointing at something in the UI) → Identify the component, explain its meaning.3940## Quick Reference4142### Tab Groups4344| Group | Pages | Purpose |45|-------|-------|---------|46| **Chat** | Chat | Test the agent via webchat + see Agent Steps |47| **Build** | Story | Visual agent flow graph (feature-flagged) |48| **Components** | Webchat Components, Actions, Workflows, Triggers | Browse component registry, test bot primitives |49| **Test** | RAG Search, Evals | Test knowledge search and run automated evals |50| **Data** | Knowledge, Tables, Files | Manage knowledge bases, tables, and files |51| **Observe** | Conversations, Traces, Logs | View conversation history, execution traces, runtime logs |52| **Config** | Settings, Integrations | Agent config, secrets, LLM settings, integration management |5354### Agent Steps (Chat Page)5556The right panel of the Chat page shows **Agent Steps** — a real-time visualization of what the agent did to process each message.5758**Hierarchy:** Turn → Iterations → Tools / Messages / State Mutations5960- **Turn** = one conversation exchange (user message → agent processing → response)61- **Iteration** = one loop of the autonomous agent (think → decide → act)62- **Tool** = a tool call within an iteration (violet card)63- **Message** = a bot message sent (blue card)64- **State Mutation** = a state change (teal card, shows before/after)6566**Status indicators:** ✓ green = ok, ✗ red = error, ⟳ blue spinning = running6768**AI metrics per iteration:** model name, input/output tokens, cost (USD)6970### Key URLs7172| Path | Page |73|------|------|74| `/chat` | Chat + Agent Steps |75| `/components` | Component registry + installed components |76| `/actions` | Actions browser |77| `/workflows` | Workflows + run history |78| `/search` | RAG search testing |79| `/evals` | Eval definitions + runs |80| `/knowledge` | Knowledge base management |81| `/tables` | Table data management |82| `/traces` | Full trace viewer |83| `/conversations` | Conversation history |84| `/logs` | Runtime logs |85| `/settings` | Agent configuration |86| `/integrations` | Integration management |