~10 min read

Your First Agent Task

Use the AI assistant to find, install, and launch an app — entirely through natural language.

~10 minBeginnerYou'll build: An installed and running AI app, set up entirely by the agent

1. Open the Agent

Navigate to the Dashboard and click the sparkle icon, or select Agent from the sidebar. You'll see the agent hero screen:

What do you want to do today?

What would you like to do? Start typing or choose an example

Quick Actions

Find app
Install app
Edit image
Launch LLM agent
Debug App Issue
Generate video with ComfyUI

Choose an LLM model from the dropdown. Your last-used model is remembered automatically via CRDT sync.

No download needed for cloud API backends. For fully offline use: any Ollama model works — qwen3:4b (2.4 GB) is a good default.

Click Install app to pre-fill the prompt. Great for your first time.

Example Questions

Not sure what to ask? Try one of these:

  • "Can you install an app for me?"
  • "What are the most popular apps people run now?"
  • "Help me set up image generation"
  • "What models do I have downloaded?"
  • "Debug why my app crashed"
  • "Generate a manifest for my Python project"

2. Your First Prompt

Type your first request:

text
Find and install a local chatbot app

The status bar at the bottom turns pink and shows Thinking... with a clock icon. The agent is reasoning about your request.

What You Can Ask

What You TypeWhat the Agent DoesTools Called
"Install a chatbot"Searches catalog, picks best match, installslist_apps → install_app
"Find the best image gen for 8 GB"Checks GPU, searches apps, recommendsgpu_diagnose → list_apps → hardware_status
"Why is ComfyUI crashing?"Reads crash logs, checks GPU, diagnosesapp_diagnose → crash_log_debug → gpu_diagnose
"Edit my workflow to use a different model"Reads file, patches checkpoint referencefile_read → file_edit
"What models do I have?"Scans all model locationsmodel_list → hardware_status
"Package my Python app"Analyzes repo, generates manifestmanifest_generate

3. Watch It Work

As the agent works, you'll see several types of UI elements:

T

I'll search for chatbot apps available in the catalog...

  • Search app catalog for chatbot apps
  • Compare options and recommend best match
list_apps▸ expand

{"query": "chatbot", "tag": "llm"}

Found 3 apps: open-webui (4.5/5), sillytavern (4.3/5), text-generation-webui (4.1/5)

Thinking…

Open WebUI is the highest rated and most popular...

Status Bar

The status bar at the bottom cycles through states as the agent works:

  • Thinking — LLM is generating a response
  • Calling list_apps... — a tool is executing
  • Ready — waiting for your next message

25 of 32 tools are safe and auto-run (all read-only tools). You only see approval prompts for the 7 tools that modify your system.

How Tool Execution Works

Each tool call follows a 6-step flow:

  1. Your message enters the conversation
  2. The LLM reasons about what to do (Thought:)
  3. It selects a tool and provides arguments (Action: + Action Input:)
  4. Permission check — safe tools auto-run, others need your approval
  5. The tool executes with a timeout
  6. The result feeds back into the LLM as an Observation

This cycle repeats until the agent reaches a final answer or hits the 25-iteration limit.

4. Approve Actions

When the agent calls install_app, you'll see a permission modal with the tool name, full arguments, and a risk description. You choose Approve or Deny.

Safety Levels

Safe

25 tools — auto-run, no approval needed

list_apps, app_status, app_logs, gpu_diagnose, gpu_test_pytorch, model_list, model_info, hardware_status, file_read, list_files, search_files, search_code, workflow_analyze, manifest_validate, manifest_generate, manifest_fix, install_debug, model_manage, crash_log_debug, app_manifest_debug, app_diagnose, model_manifest_validate, model_manifest_generate, model_cache_diagnose, web_search

Confirm

7 tools — requires your approval before running

install_app, launch_app, stop_app, file_write, file_edit, run_command, model_download

Dangerous

run_command with destructive flags

rm, kill, chmod — extra caution advised

What to Check Before Approving

ToolWhat to Verify
file_writeFile path — is it writing where you expect?
file_editold_string and new_string — is the change correct?
run_commandFull command text — watch for rm, kill, curl to unknown URLs
install_appsource_url — is it a trusted repository?
launch_appapp_id, port, and env variables
model_downloadrepo_id — is it the model you want? Check disk space.

If You Deny

If you deny a tool call, the agent sees "User denied execution" as a tool result. It will continue reasoning and may try an alternative approach, or ask for your guidance. You can always say "try a different approach" or explain why you denied.

Always read run_command arguments before approving. The agent has shell access within the project directory.

5. Iterate & Explore

Example: Launch and Configure

Launch it

T

[launch_app {app_id: "open-webui"}]

Health check passed. Open WebUI is running at http://localhost:3000

What model is it using?

T

[app_status {app_id: "open-webui"}]

Connected to Ollama, using llama3.1:8b (4.7 GB)

Switch to something smaller

T

[hardware_status] → [model_list {filter: "gguf"}]

7.8 GB VRAM available. qwen3:4b (2.4 GB) is already downloaded — it fits well. I'll update the configuration.

Example: Debugging

ComfyUI won't start

T

[app_diagnose {app_id: "comfyui"}]

Process exited with code 1. Last crash: 2 min ago.

[app_logs {app_id: "comfyui", level: "error"}]

ModuleNotFoundError: No module named 'torch'

[install_debug {app_id: "comfyui"}]

Virtual environment exists but torch not installed.

[gpu_diagnose] → [run_command: pip install torch ...]

PyTorch was missing. I've reinstalled it with the correct GPU backend (CUDA 12.1).

Sessions persist via CRDT sync. Close the app, come back tomorrow — your conversation is preserved.

What's Safe to Explore

The agent can't break anything with read-only tools. Try these freely:

  • "What GPU do I have?" — runs gpu_diagnose
  • "List all my apps" — runs list_apps
  • "Show ComfyUI logs" — runs app_logs
  • "What models are downloaded?" — runs model_list
  • "Check if my manifest is valid" — runs manifest_validate
  • "How much disk space are models using?" — runs model_cache_diagnose

Anti-Patterns

  • Don't ask the agent to read a 10,000-line file — use specific line ranges or ask for specific sections
  • Don't approve run_command without reading the full command
  • Don't chain 10 requests in one message — the agent works better step by step

Key Takeaways

  • Local by default — conversations stay on your device with Ollama or llama.cpp
  • 32 tools total: 25 safe (auto-run) + 7 require confirmation
  • Safe tools run automatically — no approval needed for reading or searching
  • Always review tool arguments before approving writes and installs
  • Sessions persist in CRDT — close and resume anytime
  • For complex tasks, discuss before executing: ask "what would you do?" first