# Get the most out of SageOx (/docs/mobile/get-the-most)



SageOx is most useful as a habit, not a one-off. This guide walks the arc: connect the right surface, capture often, then put the context to work. Work through it in order.

<ScreenFrame caption="The arc at a glance: start in assistant-mode, code-mode, or capture-mode, then watch the context land in Team Context." />

1. Set up [#1-set-up]

Pick the setup path that matches how you actually work. Most people start in assistant-mode plus one of the recording surfaces. Code-mode with `ox` is for the subset of people whose AI coworker works inside a checked-out repo.

| If you mostly use                                                             | Start here                                        | Why                                                                                                                                                   |
| ----------------------------------------------------------------------------- | ------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- |
| ChatGPT, Claude Cowork, Claude Desktop, or another MCP-capable assistant      | Start in **assistant-mode** via [MCP](/docs/mcp)  | Best for most people. You get SageOx search, interactive cards, and shared context without needing a local repo checkout.                             |
| Web Console or Ox Dot for recording                                           | Start in **capture-mode**                         | Best when your goal is to capture discussions, voice notes, or in-room meetings. You do not need the `ox` CLI just to record and use SageOx.          |
| Claude Code, Codex CLI, Gemini CLI, Aider, or another repo-first coding agent | Start in **code-mode** with `ox login`, `ox init` | Best when your AI coworker works in a local repo and you want Team Context primed at session start, repo-aware features, and deeper coding workflows. |
| Both kinds of tools                                                           | Use both modes                                    | This is the highest-leverage setup for technical teams: assistant-mode for live lookup and cards, code-mode for repo-connected coding features.       |

<ScreenFrame caption="Three common setups: assistant-mode through MCP, capture-mode through the web console or Ox Dot, or code-mode where ox primes the repo session automatically." />

Repo-first setup with ox [#repo-first-setup-with-ox]

If you work in a coding tool that starts from a local repo, connect the repo once. Everyone who joins later inherits the same context.

<Terminal>
  <TerminalComment>
    Install, sign in, connect your repo
  </TerminalComment>

  <TerminalCommand>
    ox login
  </TerminalCommand>

  <TerminalCommand>
    ox init
  </TerminalCommand>
</Terminal>

That is enough for normal onboarding. If the repo setup seems off, `ox doctor` is the troubleshooting step, not the day-one requirement. See [Getting started](/docs/getting-started) for the full walkthrough.

Assistant-mode setup with MCP [#assistant-mode-setup-with-mcp]

If you are not working in a repo-first coding tool, start in assistant-mode:

* Use the [MCP overview](/docs/mcp) for the model and permissions.
* Use the [connect wizard](/connect/mcp) to connect your assistant.
* Use [Getting the most out of SageOx via MCP](/docs/mcp/getting-the-most) to learn the prompt patterns and interactive cards.

Capture-mode setup [#capture-mode-setup]

If your main job is to capture discussions rather than work in a coding repo, start with the recording surface that fits the moment:

* Use the [Console Recorder](/docs/context-capture/console) in the browser today.
* Use [Ox Dot](/docs/context-capture/ox-dot) for dedicated in-room capture.

2. Capture [#2-capture]

The context is only as rich as what you feed it. Record the conversations where decisions actually happen.

<ScreenFrame caption="Console Recorder capturing a design review, with the live level meter moving." />

* **Record discussions** — standups, design reviews, retros. Use the web [Console Recorder](/docs/context-capture/console) or [Ox Dot](/docs/context-capture/ox-dot) for in-room capture. Start with [your first discussion](/docs/mobile/record-first-discussion).
* **Import walkthroughs** — paste a Loom, Figma, or Cap link. See [video import](/docs/context-capture/video-import).
* **Narrate as you go** — transcript quality drives extraction quality. Silence produces no context.

3. Use the context [#3-use-the-context]

Capturing is half the value. The payoff is when your team — and your AI coworkers — read it back.

<ScreenFrame caption="Two ways the captured context comes back: assistant-mode searching SageOx live, and code-mode where ox primes the agent before work starts." />

If you use assistant-mode [#if-you-use-assistant-mode]

This is the right default for ChatGPT, Claude Cowork, Claude Desktop, and similar desktop assistants with tool calling support.

* Ask explicitly for SageOx: "Search SageOx for what we decided about X."
* Use the interactive cards when they appear; they are faster than reading a paragraph and then acting somewhere else.
* Keep the [MCP guide](/docs/mcp/getting-the-most) close until the prompting pattern becomes habit.

If you use code-mode [#if-you-use-code-mode]

This is still the deeper path when your AI coworker works inside a checked-out repo.

<Terminal>
  <TerminalComment>
    An AI coworker pulls in Team Context at session start
  </TerminalComment>

  <TerminalCommand>
    ox agent prime
  </TerminalCommand>
</Terminal>

After `ox init`, many coding tools run that automatically at session start. Re-run prime after clearing or compacting context. Ask question-shaped prompts in your editor — ox surfaces relevant prior decisions from your [Ledger](/docs/developers/how-it-works) on its own.

If your desktop tool supports both [#if-your-desktop-tool-supports-both]

In tools like Claude Cowork, the best setup is often both, especially if you ask questions in the desktop app and code in local repos:

* **Assistant-mode** over MCP for live SageOx search, bubble access, and interactive cards inside the assistant.
* **Code-mode** with `ox` in the repos you actively code in, because it unlocks the deeper repo-side features like priming, code indexing, and richer coding workflows.

<Callout type="info">
  The flywheel: every captured discussion enriches the context the next session consumes. The more you record, the smarter every session gets.
</Callout>

4. Advanced habits [#4-advanced-habits]

Once the basics are routine, go further.

For everyone [#for-everyone]

* **Cast a review to the room** — put a recording or live meeting on the TV. See [cast to a TV](/docs/mobile/cast-to-a-tv).
* **Capture short decisions early** — a two-minute voice note or hallway recap is often more valuable than waiting for a perfect formal meeting.

If you also code in repos [#if-you-also-code-in-repos]

* **Tend your Team Context** — edit `AGENTS.md` and `SOUL.md` directly. See [Team Context](/docs/features/team-context).
* **Index your code** — run `ox code index` so coworkers get semantic search across your repo.

What's next [#whats-next]

* [Record your first discussion](/docs/mobile/record-first-discussion) — start the capture habit.
* [Features overview](/docs/features) — what the context becomes.
* [Troubleshooting](/docs/mobile/troubleshooting) — when something doesn't go to plan.