Tutorials

Tutorials walk you through complete, end-to-end workflows using SOAT. Each one starts from scratch and demonstrates how the platform's building blocks fit together in a real scenario.

Before you begin

All tutorials assume:

• A running SOAT instance. Follow the Quick Start to bring the stack up.
• Familiarity with SOAT's core concepts. Read Key Concepts if you are new.
• The CLI installed, or the SDK set up in a TypeScript project.

---

📄️Tutorials

Tutorials walk you through complete, end-to-end workflows using SOAT. Each one starts from scratch and demonstrates how the platform's building blocks fit together in a real scenario.

📄️Permissions in Practice

This tutorial walks through a realistic permissions setup from scratch. You will:

📄️Chat with an LLM

This tutorial walks through the full flow of having a back-and-forth conversation with an LLM. You will:

📄️Connect Third-Party LLMs

This tutorial shows how to connect SOAT to hosted LLM providers such as xAI, OpenAI, Anthropic, and Amazon Bedrock. You will:

📄️Orchestrate a Sonnet

This tutorial shows how to build a poem pipeline with the Orchestrations module. Unlike Multi-Agent Sonnet with Nested Agent Calls, the agents here do not call one another. The orchestration graph invokes each agent directly, stores their outputs in typed state, assembles the final poem, and persists it through a SOAT tool.

📄️Agent SOAT Tools and Preset Parameters

This tutorial shows how to give an agent access to platform documents using soat tools — and how to use preset parameters to lock a tool to a specific document ID so the model never has to guess it.

📄️Conditional Branching in Orchestrations

This tutorial shows how to build a branching orchestration using condition nodes. When a run completes, every node that was not reached is recorded with status: "skipped" — giving you a complete execution trace regardless of which path ran.

📄️Multi-Agent Sonnet with Nested Agent Calls

This tutorial demonstrates how to build a nested-agent pipeline where one agent coordinates multiple sub-agents using SOAT tools. If you want the same sonnet workflow with the Orchestrations module calling each agent directly, see Orchestrate a Sonnet. This nested-agent pattern applies to any workflow that can be decomposed into sequential or parallel sub-tasks — content pipelines, data processing, multi-step analysis, code generation, report assembly, and more.

📄️Orchestration Control Flow: Delay, Poll, and Loop

This tutorial focuses on the control-flow nodes of the Orchestrations module — the ones that pace, wait, repeat, and branch a run rather than call an LLM. You will build one orchestration that uses, in order, a delay, a poll, a loop (which runs a sub-orchestration per item), and a condition that routes to a terminal transform.

📄️Debug Session, Generation, and Trace History

This tutorial teaches a practical debugging workflow for first-time SOAT users. You will build a traceable conversation and keep a deterministic mapping between:

📄️Agent with Persistent Memory

This tutorial shows how to give an agent a long-term memory that persists across sessions. You will:

📄️Deploy a Multi-Agent App with Agent Formation

This tutorial builds the same multi-agent orchestration pipeline from Multi-Agent Sonnet with Nested Agent Calls — an orchestrator agent that delegates sonnet stanzas to four specialized sub-agents — but deploys the entire system with a single Agent Formation template instead of many ordered API calls.

📄️Generating Embeddings

This tutorial shows how to use the SOAT Embeddings endpoint to convert text into numeric vectors and compute cosine similarity between them. You will:

📄️Agent over a Library of PDFs

This tutorial builds an agent that answers questions from a small library of PDF

📄️Ingest Images and Audio with Converters

Native file ingestion turns

📄️Review Panel: Check a Draft's Fundamentals and Tone

This tutorial builds a real editorial workflow: a writer agent produces a draft, then hands it to a review panel — two reviewers that check the fundamentals (factual accuracy and logical structure) and one reviewer that checks the voice and tone. A final synthesis pass weighs all three reviews into a single, actionable verdict the writer can act on.

📄️Create an Agent Squad

An agent squad is a team of agents plus the flow that coordinates them, deployed as a single Formation stack — see the Agent Squad example. This tutorial builds a small marketing content squad end to end: a researcher gathers facts, a writer and a reviewer work in parallel from those facts, a human reviewer approves the result, and only then does it "publish".

📄️Automate a Flow with Triggers

A Trigger binds a starter — manual, webhook, or