> ## Documentation Index
> Fetch the complete documentation index at: https://vetta.sh/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Naive docs

> The most efficient managed agent for long-horizon work. The highest intelligence per dollar, by design.

**Naive Managed Agents is a managed agent platform**: you define an [agent](https://vetta.sh/docs/capabilities/agent.md) — model, prompt, tools, skills, budget — and run it as [sessions](https://vetta.sh/docs/concepts/sessions.md) that work for hours, pause at storage cost, and finish without a person in the loop. You pay per finished task, in real dollars, priced before each call runs.

> [!NOTE]
>
> **Two layers, one stack.** Naive Managed Agents is the autonomous-company infrastructure — the harness, the managed runtime, sessions, budgets, tools. Naive **blueprints** are the layer on top: the templates a whole company is installed from, and the [studio](https://app.usenaive.ai) you run it in. These pages are the Managed Agents reference.

> [!NOTE]
>
> **Why you'll see `vetta`.** Naive's API, SDK and CLI use the name `vetta` in their identifiers: `api.vetta.sh`, the `Vetta-Version` header, `@usenaive-sdk/vetta`, `@usenaive-sdk/vetta-cli` and the `vetta` command. They're the same product. The CLI also installs a `naive` command that runs the same commands (`naive login` is `vetta login`).

Everything is built around one number: **the most intelligence per dollar spent** — the same model on different stacks varies several-fold in cost per completed task ([benchmarks](https://usenaive.ai/blogs/introducing-naive-managed-agents)).

![Naive Managed Agents — managed agents infrastructure: any model and provider, skills, and tools in; harness, runtime, orchestration, and self-improvement inside; run and interact through the Web Studio, API, CLI, and SDK](https://mintcdn.com/vetta/Lby8hzUEjDwI2o6a/images/architecture-overview.png?fit=max\&auto=format\&n=Lby8hzUEjDwI2o6a\&q=85\&s=9698e189bb8189f7fdcbdda775751c1f)

Any model, your skills, and your tools go in; Managed Agents' runtime does the work; and you run and interact through the [Web Studio](https://app.usenaive.ai), the [API](https://vetta.sh/docs/api/overview.md), the [CLI](https://vetta.sh/docs/cli/overview.md), or the [SDK](https://vetta.sh/docs/sdk/typescript.md).

## Create an agent, run a session

```typescript TypeScript theme={"system"}
import { createClient } from "@usenaive-sdk/vetta";

const vetta = createClient({ baseUrl: "https://api.vetta.sh", apiKey: process.env.VETTA_API_KEY! });

const agent = await vetta.agents.create({
  name: "triage",
  model: "z-ai/glm-5.3-flash",
  system: "You are a concise triage agent.",
  budget: { cap_micro_usd: 50_000_000, max_task_micro_usd: 5_000_000, period: "month" },
});

const session = await vetta.sessions.create({
  agent_id: agent.id,
  message: "Summarize what changed in main overnight.",
});

for await (const event of vetta.stream(session.id)) {
  console.log(event.type);
}
```

```bash CLI theme={"system"}
npm i -g @usenaive-sdk/vetta-cli && vetta login --api-key sk_...

AGENT=$(vetta agent create --name triage --model z-ai/glm-5.3-flash \
  --budget-usd 50 --max-task-usd 5 --budget-period month \
  --system "You are a concise triage agent." | jq -r .id)

SID=$(vetta session create --agent "$AGENT" \
  --message "Summarize what changed in main overnight." | jq -r .id)

vetta session stream --session "$SID"
```

## The pillars, as objects

Everything you touch maps to primitives you create and version — familiar on day one.

> [card] [Agent](https://vetta.sh/docs/capabilities/agent.md)
>
> A reusable, versioned config: model, harness, prompt, tools, skills, budget.

> [card] [Session](https://vetta.sh/docs/concepts/sessions.md)
>
> One directly-controlled run of an agent — send input, stream output, interrupt, resume.

> [card] [Events](https://vetta.sh/docs/concepts/events-and-streaming.md)
>
> A resumable stream of everything the agent does, keyed by sequence number.

> [card] [Computer](https://vetta.sh/docs/capabilities/computer.md)
>
> A disposable sandbox with a filesystem, shell, and optional browser — paused when idle.

> [card] [Skills](https://vetta.sh/docs/capabilities/skills.md)
>
> Persisted, versioned expertise loaded with progressive disclosure.

> [card] [Files](https://vetta.sh/docs/capabilities/files.md)
>
> Durable, organization-scoped storage for the artifacts a session produces.

## How Naive Managed Agents earns the highest ROI per dollar

Four independent levers, all cutting dollars per finished task without cutting quality.

## Available today & what's next

Available now: agents, sessions, the durable runtime, completion windows, budgets, the computer, skills, files, cron, webhooks, real-USD billing, [identity](https://vetta.sh/docs/capabilities/identity.md) (personas, domains, email, SMS, connections, the vault) — plus [web search and fetch, image and video generation](https://vetta.sh/docs/capabilities/tools.md#built-in-tools), the [Messages-format model proxy](https://vetta.sh/docs/api/proxy.md), [observability](https://vetta.sh/docs/capabilities/observability.md), [structured outputs](https://vetta.sh/docs/capabilities/structured-outputs.md), [audit logs](https://vetta.sh/docs/api/audit-logs.md), and [teams](https://vetta.sh/docs/capabilities/team.md) — a coordinator with a version-pinned roster, delegation, and a shared board.

> [card] [Quickstart](https://vetta.sh/docs/quickstart.md)
>
> Create an agent, run it, and read the meter in under five minutes.

> [card] [How Managed Agents works](https://vetta.sh/docs/how-managed-agents-is-built.md)
>
> Harness, runtime, tools — what each layer is, and which one you pick.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.