# AI use cases for Endo (longsurf-ai/endo)

Repo: [longsurf-ai/endo](https://github.com/longsurf-ai/endo) | Use cases: 4 | Page: https://dedupedai.com/use-cases/longsurf-ai-endo/

Endo is a desktop chat app and harness that runs agents from Codex, Claude Code, Antigravity and Grok, and composes them into workflows and schedules.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Get a daily priorities summary on a schedule: https://dedupedai.com/use-cases/longsurf-ai-endo/schedule-daily-priorities-summary/
- Compare answers from Codex and Claude Code in one thread: https://dedupedai.com/use-cases/longsurf-ai-endo/compare-agents-in-one-thread/
- Fan a question out to several agents with best-of-n: https://dedupedai.com/use-cases/longsurf-ai-endo/fan-out-best-of-n-workflow/
- Add a typed Resource to the Endo app for your own data: https://dedupedai.com/use-cases/longsurf-ai-endo/add-resource-to-endo-app/

## How to get a daily priorities summary on a schedule with Endo

Repo: [longsurf-ai/endo](https://github.com/longsurf-ai/endo) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README

Have Endo run a standing prompt every weekday morning and read the result in chat.

**Who it is for:** A busy individual who starts each workday by reviewing their priorities and wants the summary ready before they log in.

**The problem:** Writing the same morning check-in prompt by hand every day takes time and is easy to skip.

**The outcome:** A recurring chat thread that produces the same priorities summary on a fixed schedule, viewable from the Schedule page.

### Steps

1. Download Endo for macOS (Apple Silicon) from the Quick start link and open the disk image to install it.
2. Open Endo and sign in to at least one provider, or use Settings → Models.
3. Ask Endo: Every weekday at 9 AM, summarize my priorities for the day.
4. Open the Schedule page and confirm the new schedule is listed with the right time.

### Prompt to paste into your agent

```text
In the Endo repo at longsurf-ai/endo, help me set up a weekday 9 AM schedule that summarizes <my priorities source>. Expected output: a schedule entry on the Schedule page with the prompt and cron timing. Verify the next run time shown matches 9 AM on a weekday.
```

### Caveat

Endo is at 0.1.x and the README says to expect breaking changes, so a schedule set up today may need to be recreated after an update.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/longsurf-ai-endo/schedule-daily-priorities-summary/

## How to compare answers from Codex and Claude Code in one thread with Endo

Repo: [longsurf-ai/endo](https://github.com/longsurf-ai/endo) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README

Ask one question, switch agents mid-thread, and dig into the answer that fits best.

**Who it is for:** A developer who has both Codex and Claude Code subscriptions and wants a second opinion without juggling two apps.

**The problem:** Each agent CLI keeps its own history, so comparing answers means copying context between tools by hand.

**The outcome:** One chat thread where each agent sees the full history, plus a focused Dig In on the strongest answer.

### Steps

1. Install Endo from the Quick start link, or clone the repo with `git clone https://github.com/longsurf-ai/endo.git`.
2. Sign in with your existing codex and claude logins, or set providers in Settings → Models.
3. Ask your question in a new thread, then switch the model to the other agent mid-thread.
4. Select the part of an answer you want to examine and choose Dig In to open a focused side conversation.

### Prompt to paste into your agent

```text
Using the longsurf-ai/endo repo, set up a chat where <my question> is answered first by Codex, then by Claude Code in the same thread. Expected output: two answers in one thread, with the second agent referring to the first. Verify that the Claude Code answer reflects the earlier history.
```

### Caveat

The README says Endo drives each provider through its own CLI, so you need working codex and claude logins on the same machine before the comparison runs.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/longsurf-ai-endo/compare-agents-in-one-thread/

## How to fan a question out to several agents with best-of-n with Endo

Repo: [longsurf-ai/endo](https://github.com/longsurf-ai/endo) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README

Run the shipped best-of-n workflow to collect and compare multiple agent answers.

**Who it is for:** A developer or analyst who needs the strongest of several drafts or answers and wants the calls to run in parallel.

**The problem:** Asking several agents by hand, one after another, is slow and makes it hard to see which answer wins.

**The outcome:** A Workflow card in chat that shows each agent call as it happens and returns the candidate answers from the run.

### Steps

1. Clone the repo with `git clone https://github.com/longsurf-ai/endo.git` and enter it with `cd endo`.
2. Install dependencies with `just install --frozen-lockfile`.
3. Start the desktop app with `just desktop`.
4. In chat, run /best-of-n on your question and watch the Workflow card show each call.
5. Open the workflow file in your workspace to change how many agents or phases it uses. (inferred, check the README)

### Prompt to paste into your agent

```text
In the longsurf-ai/endo repo, run the /best-of-n workflow on <my question> from the Endo chat. Expected output: a Workflow card listing each agent call and the candidate answers. Verify that calls from more than one provider appear before you accept a result.
```

### Caveat

The README names /best-of-n as a shipped workflow but does not describe its internals, so check the workflow file before relying on its exact behavior.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/longsurf-ai-endo/fan-out-best-of-n-workflow/

## How to add a typed Resource to the Endo app for your own data with Endo

Repo: [longsurf-ai/endo](https://github.com/longsurf-ai/endo) | Difficulty: Advanced | Time: 2 hours | Basis: From the README

Define one table and schema, then get an API, agent tools and live updates from it.

**Who it is for:** A developer extending Endo for a team or personal tool who needs agents and people to edit the same records under the same rules.

**The problem:** Wiring a new data type through the API, agent tools and UI by hand means keeping several definitions in sync.

**The outcome:** A new Resource with a Drizzle table and Effect Schema that exposes a typed API, agent tools and live updates.

### Steps

1. Clone the repo with `git clone https://github.com/longsurf-ai/endo.git` and enter it with `cd endo`.
2. Install dependencies with `just install --frozen-lockfile`.
3. Read the Adding a Resource section in docs/architecture/resource.md.
4. Define your table as a Drizzle table and an Effect Schema for the new resource.
5. Start the app with `just desktop` and confirm the new data appears through the typed API and agent tools.

### Prompt to paste into your agent

```text
In the longsurf-ai/endo repo, follow docs/architecture/resource.md to add a Resource for <my data type>, defined once as a Drizzle table and an Effect Schema. Expected output: the new resource exposed through the typed API and agent tools. Verify that an agent tool can read and write a record and that the change shows in the app.
```

### Caveat

The README calls Endo 0.1.x and warns of breaking changes, so a custom Resource may need changes after future updates.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/longsurf-ai-endo/add-resource-to-endo-app/