Inference

A workflow calls a model with agent(). Boardwalk is model-agnostic: it routesinference, it doesn't serve it. You can let Boardwalk pick a model with no API key, name a specific model, or point a call at your own provider and key.

Model is per call

The model is chosen on each agent() call, not on the workflow. meta declares no model and no provider. A workflow that does no model work names none, and one that calls three different models is just the obvious code:

const draft  = await agent("Write release notes from this diff: ...");
const review = await agent("Critique these notes harshly: ...", {
  model: "anthropic/claude-sonnet-4.5",
});

Managed inference

Call agent(prompt) with no options and Boardwalk fulfills it on the managed lane, with no API key and no model menu. Omit the model and the Auto lane picks one for you per request:

const summary = await agent("Summarize this thread for a busy exec: ...");

Managed inference is the default provider (named boardwalk). Boardwalk meters the tokens and bills your org. See Pricing for how a run is priced.

Pick a model

Pass model to choose one. It's an opaque <vendor>/<model> string: the vendor prefix names the model, never your credentials. Under the default provider, a named model is the managed lane serving that model (still no key of yours):

await agent(prompt, { model: "anthropic/claude-sonnet-4.5" });
await agent(prompt, { model: "openai/gpt-4o" });

The managed catalog is a curated list, not the whole internet of models. See the models page for every supported id and its live rate. An unknown id fails that one agent() call with a clear error; the rest of the run continues.

Bring your own provider

To use your own key (a vendor account or any OpenAI-compatible endpoint like vLLM, Together, a local Ollama, or Bedrock), name a provider other than boardwalk. Boardwalk never reaches for your key unless a call asks for it by provider name:

await agent(prompt, { model: "llama-3.3-70b", provider: "my-vllm" });

On Boardwalk, a provider is configured once in the dashboard (its base URL and which secret holds the key); the key lives in the secrets vault and is resolved per run, never exposed to the model loop. You pay that vendor directly. BYO keeps inference cost off Boardwalk's bill.

Across the three engines

The same agent() call resolves a little differently per engine, and nothing in your program changes:

• Boardwalk (deployed):the managed lane just works, no key. Named providers resolve from the org's configured providers and secrets.
• boardwalk dev: the default boardwalk provider reaches managed inference using your boardwalk login account. Logged out, name a provider with your own key instead, and the error tells you exactly what to set.
• Self-hosting: bring your own by default (declare providers + keys), or set BOARDWALK_API_KEY to use managed inference. See Self-hosting.

Structured output

Pass a schema (JSON Schema) and agent() resolves to a validated object instead of text. Pass the expected type for inference at the call site:

type Bug = { title: string; severity: "low" | "high" };

const bugs = await agent<Bug[]>("Find the bugs in this diff: ...", {
  schema: {
    type: "array",
    items: {
      type: "object",
      properties: {
        title: { type: "string" },
        severity: { type: "string", enum: ["low", "high"] },
      },
      required: ["title", "severity"],
    },
  },
});

See Writing workflows for agent() in context and the SDK reference for the full AgentOptions.