Refresh onboarding screenshots in docs
Update first-run onboarding docs for the welcome screen, in-chat model gate, Cloud/AI account/Local provider paths, and explicit main and utility model choices. Replace stale onboarding screenshots with optimized current assets and add gate, account, and local-provider captures.
Alessandro committed
Jul 2, 2026 at 16:01 UTC
50f80d57dc9b4e78b6a7ba0b1a3e36579b92cfa7
13 files changed
+46
-48
docs/README.md
+1
-1
@@ -13,7 +13,7 @@ docs focus on practical setup, screenshots, and user workflows.
13
14
- **[Quickstart Guide](quickstart.md):** Get up and running in 5 minutes with Agent Zero.
15
- **[Agent Zero Launcher](guides/launcher.md):** Use the desktop app to set up Docker, install Agent Zero, open Instances, or connect a remote Instance.
16
-- **[First-Run Onboarding](guides/onboarding.md):** Choose Cloud or Local, add a provider key, and select main and utility models.
16
+- **[First-Run Onboarding](guides/onboarding.md):** Choose Cloud, AI account, or Local access, then select main and utility models.
17
- **[Installation Guide](setup/installation.md):** A0 Launcher downloads, A0 Install, direct Docker, updates, and advanced Docker setup (includes [How to Update](setup/installation.md#how-to-update-agent-zero)).
18
- **[A0 CLI Connector](guides/a0-cli-connector.md):** Install the host connector for a running Agent Zero instance, use the command palette, and switch Browser modes.
19
- **[Self Update](guides/self-update.md):** How the in-app updater works (technical reference).
docs/guides/onboarding.md
+33
-36
@@ -1,62 +1,59 @@
1
# First-Run Onboarding
2
3
Use onboarding the first time you open Agent Zero, or any time the Web UI says
4
-your models still need setup. The wizard helps you pick a provider, add the
5
-needed key or connection, choose the main model, choose the utility model, and
6
-start chatting.
4
+your models still need setup. The wizard helps you pick Cloud, AI account, or
5
+Local access, configure a main model, choose a utility model, and start
6
+chatting.
7
8
-This example uses **Agent Zero API** with a fake demo key and
9
-`claude-opus-4-6`. Replace the demo key with your own key.
8
+This example uses **OpenRouter** with a masked demo key. Replace the demo key
9
+with your own key.
10
11
-## Choose Cloud Or Local
11
+## Open Onboarding
12
13
-Open the Web UI and click **Start Onboarding** from the welcome banner. On the
14
-first screen, choose whether Agent Zero should use a hosted provider or a local
15
-model server.
13
+Open the Web UI. The welcome screen can show account shortcuts, and the message
14
+composer is ready immediately.
15
17
-
16
+
17
19
-Choose **Cloud** when you want to use Agent Zero API, OpenRouter, Anthropic,
20
-OpenAI, Google, Venice, or another hosted provider. Choose **Local** when you
21
-want to connect to Ollama, LM Studio, or another model server running on your
22
-machine.
18
+If you send a message before models are configured, Agent Zero creates the chat,
19
+holds the message, and shows the model gate inside the conversation. Choose
20
+**Cloud provider**, **AI account**, or **Local model** to open onboarding.
21
24
-## Pick Agent Zero API
22
+
23
26
-On the Cloud provider screen, click **Agent Zero API**.
24
+## Choose A Provider Path
25
28
-
26
+Choose **Cloud** when you want to paste an API key for OpenRouter, OpenAI,
27
+Anthropic, Google, Venice, or another hosted provider.
28
30
-The ChatGPT/Codex account option is also available on this Cloud screen if you
31
-want to connect by device code instead of pasting a provider key.
29
+
30
33
-## Add The Key And Main Model
31
+Choose **Account** when you want to sign in with Codex/ChatGPT, GitHub Copilot,
32
+Google Cloud Gemini, or xAI Grok instead of pasting a provider key.
33
35
-Paste your Agent Zero API key in **API key**. The screenshot uses a fake example
36
-key, and the field is masked.
34
+
35
38
-Click the magnifier in **Main model** to open the model list, then choose
39
-`claude-opus-4-6`.
36
+Choose **Local** when you want to connect to Ollama, LM Studio, oMLX, llama.cpp,
37
+vLLM, or another model server running on your machine.
38
41
-
39
+
40
43
-After the model is selected, click **Choose utility model**.
41
+## Configure The Main Model
42
45
-
43
+For API-key providers, choose the main model and paste the provider key. The
44
+screenshot uses a masked demo key.
45
47
-## Choose The Utility Model
46
+
47
49
-The utility model handles supporting work such as summarizing, organizing
50
-memory, and other background tasks.
48
+After the main model is selected, click **Choose utility model**.
49
52
-Leave **Use same as Main Model** checked if you want both roles to use
53
-`claude-opus-4-6`.
50
+## Choose The Utility Model
51
55
-
52
+The utility model handles quick internal tasks such as summaries, naming, and
53
+memory. A small, fast, cheap model usually works best here. The wizard may
54
+prefill a utility provider and model, but it remains an explicit choice.
55
57
-You can also uncheck **Use same as Main Model** and choose a different utility
58
-provider and model. For example, you might keep a strong main model for chat and
59
-use a faster or cheaper model for utility tasks.
56
+
57
58
Click **Finish setup** when the utility model looks right.
59
docs/quickstart.md
+8
-7
@@ -62,18 +62,19 @@ For the full setup flow, host picker screenshots, command palette guidance, Brow
62
### Open the Web UI and complete onboarding
63
64
Open your browser and navigate to `http://localhost:<PORT>`. The Web UI will
65
-show the onboarding banner. Click **Start Onboarding** to choose Cloud or
66
-Local, add a provider key or account connection, and select your main and
67
-utility models.
65
+open on the welcome screen. If models still need setup, send a message or use
66
+the setup shortcuts to choose Cloud, AI account, or Local access, then select
67
+your main and utility models.
68
69
70
71
-For a screenshot walkthrough using **Agent Zero API** with
72
-`claude-opus-4-6`, see the [First-Run Onboarding guide](guides/onboarding.md).
71
+For a screenshot walkthrough using OpenRouter, see the
72
+[First-Run Onboarding guide](guides/onboarding.md).
73
74
> [!NOTE]
75
-> Agent Zero supports hosted providers and local models. You can use the same
76
-> provider for main and utility work, or choose separate providers for each.
75
+> Agent Zero supports hosted providers, account-backed providers, and local
76
+> models. Choose a strong main model for chat and a fast utility model for
77
+> internal tasks.
78
79
### Start your first chat
80
docs/res/usage/onboarding/onboarding-account-provider.png
Binary files /dev/null and b/docs/res/usage/onboarding/onboarding-account-provider.png differ
docs/res/usage/onboarding/onboarding-agent-zero-api-key-model.png
Binary files a/docs/res/usage/onboarding/onboarding-agent-zero-api-key-model.png and b/docs/res/usage/onboarding/onboarding-agent-zero-api-key-model.png differ
docs/res/usage/onboarding/onboarding-agent-zero-api-model-dropdown.png
Binary files a/docs/res/usage/onboarding/onboarding-agent-zero-api-model-dropdown.png and b/docs/res/usage/onboarding/onboarding-agent-zero-api-model-dropdown.png differ
docs/res/usage/onboarding/onboarding-cloud-provider.png
Binary files a/docs/res/usage/onboarding/onboarding-cloud-provider.png and b/docs/res/usage/onboarding/onboarding-cloud-provider.png differ
docs/res/usage/onboarding/onboarding-local-ollama-main.png
Binary files /dev/null and b/docs/res/usage/onboarding/onboarding-local-ollama-main.png differ
docs/res/usage/onboarding/onboarding-model-gate.png
Binary files /dev/null and b/docs/res/usage/onboarding/onboarding-model-gate.png differ
docs/res/usage/onboarding/onboarding-ready.png
Binary files a/docs/res/usage/onboarding/onboarding-ready.png and b/docs/res/usage/onboarding/onboarding-ready.png differ
docs/res/usage/onboarding/onboarding-start.png
Binary files a/docs/res/usage/onboarding/onboarding-start.png and b/docs/res/usage/onboarding/onboarding-start.png differ
docs/res/usage/onboarding/onboarding-utility-same-model.png
Binary files a/docs/res/usage/onboarding/onboarding-utility-same-model.png and b/docs/res/usage/onboarding/onboarding-utility-same-model.png differ
docs/setup/installation.md
+4
-4
@@ -401,10 +401,10 @@ docker run -p 0:80 -v /path/to/your/work_dir:/a0/usr agent0ai/agent-zero
401
402
## Step 3: Configure Agent Zero
403
404
-The UI will show a welcome banner when model setup is missing. Click
405
-**Start Onboarding** to choose Cloud or Local, add a provider key or account
406
-connection, and select your main and utility models. For the screenshot
407
-walkthrough, see the [First-Run Onboarding guide](../guides/onboarding.md).
404
+The UI opens on the welcome screen. If model setup is missing, send a message
405
+or use the setup shortcuts to choose Cloud, AI account, or Local access, then
406
+select your main and utility models. For the screenshot walkthrough, see the
407
+[First-Run Onboarding guide](../guides/onboarding.md).
408
409
### Settings Configuration
410