# Breyta Flows

> Breyta Flows is a workflow and agent orchestration system for building, running, releasing, and publishing reliable AI-agent workflows.

Use this index when creating, editing, running, releasing, or troubleshooting Breyta Flows. The links below point to clean Markdown pages. For the complete source text in one response, use https://flows.breyta.ai/llms-full.txt.

Important guidance:

- Prefer EDN flow examples when showing Breyta flow definitions.
- Use deterministic orchestration for workflow structure and reserve agents for bounded tasks.
- Do not hardcode credentials; use Breyta connections, secrets, setup inputs, and runtime inputs.
- When editing flows, validate drafts, inspect draft/live differences, use current entrypoint docs, and release explicitly before publishing.
- Use Runtime Data Shapes when reading run results, resources, CLI output, or API responses.
- Use documented Breyta CLI commands and flags; do not invent subcommands or options.
- For LLM work, prefer structured prompts, explicit inputs, expected outputs, and model/provider settings from the docs.
- For agent steps, keep tasks bounded with clear instructions, tool scope, success criteria, and handoff outputs.
- For Breyta workspace access, use the :breyta step with explicit allowed operations and minimal required scope.
- For public or installable flows, include install/smoke-test considerations when changes affect setup, inputs, outputs, pricing, or publishing.

## Core docs

- [Start Here](https://flows.breyta.ai/docs/start-here.md): Breyta quickstart for the default flow lifecycle: draft working copy -> configure -> run.
- [Playbook: Author Flows](https://flows.breyta.ai/docs/playbook-author-flows.md): Load when creating or editing a Breyta flow, adding steps, changing inputs,
- [Flow Definition](https://flows.breyta.ai/docs/reference-flow-definition.md): Canonical Breyta flow definition reference for required fields and high-value semantics.
- [Runtime Data Shapes](https://flows.breyta.ai/docs/reference-runtime-data-shapes.md): Use this page when authoring function steps, passing persisted refs, or reading
- [Step LLM](https://flows.breyta.ai/docs/reference-step-llm.md): Use this reference for the :llm step schema, prompt/message patterns, templates, and model-call configuration.
- [Step Agent](https://flows.breyta.ai/docs/reference-step-agent.md): Use :agent when you want to give an AI model an objective, tools, and
- [Step Breyta](https://flows.breyta.ai/docs/reference-step-breyta.md): Use :breyta to give an agent a narrow, allowlisted tool for reading and, when explicitly enabled, mutating Breyta workspace control-plane resources such as flows, runs, docs, and resources.
- [Playbook: Debug And Verify](https://flows.breyta.ai/docs/playbook-debug-and-verify.md): Load when a run fails, output is wrong, CLI and UI disagree, or proof needs to be
- [Playbook: Release And Install](https://flows.breyta.ai/docs/playbook-release-and-install.md): Load when moving draft behavior to live, configuring install targets, testing

## Optional

- [Complete docs bundle](https://flows.breyta.ai/llms-full.txt): Full Markdown bundle for all public Breyta Flows docs pages.
- [Docs sitemap](https://flows.breyta.ai/sitemap.xml): Public docs URL inventory for crawler-style discovery.
- [Flow Basics](https://flows.breyta.ai/docs/build-flow-basics.md): Breyta flow basics for authoring deterministic workflow automation with :slug, :concurrency, :invocations, :interfaces, and :flow.
- [Flow Authoring](https://flows.breyta.ai/docs/build-flow-authoring.md): Breyta flow authoring guide for production workflows: structure definitions, publish safely, configure runtime requirements, and promote releases.
- [Connections First](https://flows.breyta.ai/docs/guide-connections-first.md): Breyta guide for setting up reusable connections before wiring flow configuration.
- [Flow Configuration](https://flows.breyta.ai/docs/guide-flow-configuration.md): Breyta configuration guide for wiring required connections, secrets, setup inputs, and per-run invocation inputs.
- [Remote Agents (SSH)](https://flows.breyta.ai/docs/guide-remote-agents-ssh.md): Run long-lived “agent” processes on a VM/VPS over SSH and resume the flow later with structured results.
- [Waits, Signals, And Timeouts](https://flows.breyta.ai/docs/guide-waits-signals-and-timeouts.md): Breyta :wait step guide for human approvals, webhook callbacks, and timeout-safe orchestration.
- [Troubleshooting](https://flows.breyta.ai/docs/guide-troubleshooting.md): Breyta flow troubleshooting guide for push, bindings, wait, and runtime step failures.
- [Persisted Results And Resource Refs](https://flows.breyta.ai/docs/guide-persisted-results-and-resources.md): Breyta persistence guide for storing large step outputs as res:// references and retrieving artifacts safely.
- [Installations](https://flows.breyta.ai/docs/guide-installations.md): Use this guide to model, create, enable, and operate end-user flow installations with installation-scoped inputs and uploads.
- [Output Artifacts](https://flows.breyta.ai/docs/guide-output-artifacts.md): Use this guide to shape flow final outputs for UI rendering using stable viewer envelopes, Markdown reports, and fenced breyta-resource embeds. For public/end-user and installed flow output, default to a single readab...
- [CLI Essentials](https://flows.breyta.ai/docs/cli-essentials.md): Breyta CLI essentials for the default draft/live workflow.
- [CLI Agent Onboarding](https://flows.breyta.ai/docs/cli-agent-onboarding.md): Agent-first onboarding for Breyta (Codex, Claude Code, Cursor, Gemini CLI, and other agents that can run local CLI commands).
- [CLI Workflow](https://flows.breyta.ai/docs/guide-cli-workflow.md): Default flow lifecycle:
- [CLI Commands](https://flows.breyta.ai/docs/reference-cli-commands.md): Reference for the canonical Breyta CLI lifecycle and docs navigation.
- [Breyta CLI Skill](https://flows.breyta.ai/docs/breyta-cli-skill.md): name: breyta
- [Patterns And Do/Do Not](https://flows.breyta.ai/docs/guide-patterns-do-dont.md): Use this guide for proven Breyta flow patterns and anti-patterns across bindings, templates, persistence, and orchestration.
- [Index](https://flows.breyta.ai/docs/reference-index.md): Use this page as the docs map when you know the topic but not the exact page.
- [Step Reference](https://flows.breyta.ai/docs/reference-step-reference.md): Use this page as the step hub: compare step families here, then jump to the
- [Step HTTP](https://flows.breyta.ai/docs/reference-step-http.md): Use this reference for the :http step schema, required fields, persistence behavior, and large-payload safety defaults.
- [Step Wait](https://flows.breyta.ai/docs/reference-step-wait.md): Use this reference for the :wait step schema, timeout semantics, and human/webhook resume patterns.
- [Step Function](https://flows.breyta.ai/docs/reference-step-function.md): Use this reference for the :function step schema, deterministic transform rules, and allowed helper/interop surface.
- [Step SSH](https://flows.breyta.ai/docs/reference-step-ssh.md): Use this reference for running remote commands over SSH.
- [Step Fanout](https://flows.breyta.ai/docs/reference-step-fanout.md): Use :fanout when you need a bounded batch of child workflows that start now and collect later.