AI - Duraton

This page is for the code path - calling a model as a durable step by hand. To build an agent without code, start with Build your first agent. Duraton is where your AI agents run. They park on a human decision when the next move is risky, and wait as long as it takes. They pick up where they stopped after a crash, a restart, or a deploy - never redoing a model call that already finished. And every run keeps a record of what it did and what it cost. The mechanism is one idea applied to model calls: ctx.step.ai makes a call a durable step. It runs once, its result is recorded under the step id, and a retry after a crash returns the saved result instead of paying for the model again. Approvals, spend caps, guardrails, and streaming are all built on that same step record.

Keep your framework. Duraton goes underneath it: your code still decides what the agent does; Duraton makes sure it finishes, stops it before it overspends or acts without a person, and keeps the record. Wrap an existing model call with step.ai.wrap and nothing else changes.

const { text } = await ctx.step.ai.generate("classify", {
  model: "claude-opus-4-8",
  prompt: `Classify this ticket: ${subject}`,
});

What each page answers

You want	Read	The mechanism
”It must not act without a human on the risky stuff”	Approvals	`step.approval` parks the run holding no worker; approve, deny, or approve-with-edits resumes it at the exact checkpoint
”It must never run a tool call the model got wrong”	Guardrails	An automatic check on the arguments the model produced, before the tool runs; the verdict is a durable step
”My agent spends money and I can’t sleep”	Cost controls	`cap` halts before the call that would cross the ceiling; `tokenThrottle` spaces out runs that share a key
”The model is down and my agent just fails”	Cost controls	Fallback chains advance to the next candidate; the inference cache serves an identical deterministic call at zero spend
”My long agent dies halfway and starts over”	AI agents	One durable step per model turn and per tool call; the loop resumes at the last committed turn
”The conversation outgrows the context window”	Context management	A trimming strategy runs as a durable step, so a replay sees the same summary
”I want to see what it’s doing right now”	Streaming	Tokens stream live from the step and are replayable from token 0
”I need to show someone what the agent did, and what it cost”	AI observability	Token and cost rollups, sessions, and traces read from the durable journal

Your provider key stays with you

The model call happens in your runner, with your provider SDK and your key. Duraton records the call’s metadata (model, token counts, latency) and never receives your prompt, the response text, or your API key: apiKey is passed per call into the provider client and is never persisted by the SDK or sent to Duraton. Omit it and the provider SDK reads its conventional env var (ANTHROPIC_API_KEY).

This describes running your own code with the SDK. A no-code workflow has no runner of its own, so it resolves a key you add once under Credentials - still never persisted anywhere but that one encrypted record, and still resolved fresh for each call rather than held in memory between them.

export ANTHROPIC_API_KEY="sk-ant-..."

Where to start

AI quickstart

Add your first durable AI step, trigger it, and watch spend land in the console.

Agent kit

agent() and tool(): write an agent whose every turn and tool call is a durable step.

step.ai reference

Every option and return shape for generate, wrap, embed, and loop.

AI coding tools

Point Claude, Cursor, or any MCP client at these docs and at your project.

Start with code

Agent kit

AI

Durable runs

Integrations

TypeScript SDK

REST API

Protocol

AI

What each page answers

Your provider key stays with you

Where to start

AI quickstart

Agent kit

step.ai reference

AI coding tools

​What each page answers

​Your provider key stays with you

​Where to start

AI quickstart

Agent kit

step.ai reference

AI coding tools

What each page answers

Your provider key stays with you

Where to start