# LogBrew for agents
This page explains how agents should read LogBrew without needing browser state, hidden context, or private dashboard access.

## First safe read
```bash
logbrew status --json
```

## AI assistant context
Give an agent the public LogBrew map before it edits your app or setup command.

installation prompt

```text
Read https://logbrew.co/llms.txt, then choose the matching SDK card at https://logbrew.co/en/docs#docs-sdk-choice-title. Use npm install @logbrew/sdk @logbrew/node only for a server-side Node.js service; for Next.js, React, iOS, Android, or React Native, use the selected card and Add Project prompt. Ask the signed-in user to open Add Project and place credentials only in the matching app environment. For server-side Node.js, the env var is LOGBREW_SERVER_API_KEY. Run node node_modules/@logbrew/node/examples/first-useful-telemetry.mjs only for Node services, then verify with logbrew logs info --json. Do not ask for credentials in chat or commits.
```

# Agent task map
Use this order when an assistant is helping a developer set up LogBrew or read private signals.

## Step 1: Read the public map
Load the public route index before changing app code so the assistant starts from current LogBrew context.

```bash
curl -L https://logbrew.co/llms.txt
```

Next: Use the linked Markdown mirrors for deeper public context.

## Step 2: Choose the SDK card
Read the SDK chooser before installing anything, then use Copy installation prompt in Add Project so the assistant follows the selected platform.

```bash
curl -L https://logbrew.co/en/docs.md
```

Next: Ask the signed-in user to open Add Project, copy the installation prompt, and keep ingest credentials out of chat.

## Step 3: Check local status
Confirm API reachability and auth source before reading private projects, logs, issues, actions, traces, or releases.

```bash
logbrew status --json
```

Next: Follow the token-safe next field instead of guessing.

## Step 4: Verify the first signal
After setup sends a safe SDK signal, read one scoped result and keep tokens, cookies, and project data out of prompts.

```bash
logbrew logs info --json
```

Next: Use issue, action, trace, release, and project reads only after auth is ready.

## Use predictable public URLs
Agents should find public LogBrew context through stable localized pages, Markdown mirrors, llms.txt, robots.txt, and sitemap.xml.

- Use /en/agents.md when plain text is the safest input.
- Use /en/docs.md for command and API route context.
- Use /llms.txt to discover public agent-readable resources.

## Start with token-safe status
The CLI should tell agents whether local auth, API reachability, and recovery steps are ready without exposing token material.

- Run logbrew status --json before project reads.
- Follow next steps from JSON and human output instead of guessing.
- Keep token material out of prompts, logs, screenshots, and public pages.

## Prefer resource-specific reads
Agents should read logs, issues, actions, traces, releases, and projects through the same resource vocabulary used by humans.

- Use filters for release, environment, project, trace, severity, status, name, and user.
- Use issue and trace detail routes when an identifier is known.
- Use Markdown mirrors for public context and the authenticated API for private project data.

## Keep private data behind auth
Public agent surfaces must stay readable, while dashboard and project data remain protected by backend auth and noindex metadata.

- Do not scrape dashboard data without a valid user session.
- Do not publish private project names, tokens, traces, or deployment details.
- Use public pages for general learning and authenticated routes for scoped user data.

## Public agent links
- Agents: https://logbrew.co/en/agents
- Agents Markdown: https://logbrew.co/en/agents.md
- Docs Markdown: https://logbrew.co/en/docs.md
- Home Markdown: https://logbrew.co/en/page.md
- llms.txt: https://logbrew.co/llms.txt
- Sitemap: https://logbrew.co/sitemap.xml