# Build an agent

> Assemble a Menace Voice agent programmatically with the SDK and save it as a draft

The SDK mirrors the node-and-edge model of the [Voice Agent Builder](/voice-agent/introduction). You create a `Workflow`, add nodes (`startCall`, `agentNode`, `endCall`, …) with `add()`, connect them with `edge()`, and persist the result via `save_workflow`.

## Prerequisites

- A Menace Voice [API key](/configurations/api-keys) exported as `DOGRAH_API_KEY`
- An existing agent ID to save drafts against (create one in the Menace Voice UI or via [`POST /api/v1/workflow/create`](/api-reference/agents/create-from-template))

## Build and save

The example below builds a three-node loan-qualification agent and saves it as a **new draft version** on an existing agent. Your published agent keeps serving calls until you explicitly publish the draft.

<CodeGroup>
```python Python
from dograh_sdk import DograhClient, Workflow

with DograhClient(api_key="YOUR_API_KEY") as client:
    wf = Workflow(client=client, name="loan_qualification")

    greeting = wf.add(
        type="startCall",
        name="greeting",
        prompt="You are Sarah from Acme Loans. Greet the caller warmly.",
    )
    qualify = wf.add(
        type="agentNode",
        name="qualify",
        prompt="Ask about loan amount, purpose, and monthly income.",
    )
    done = wf.add(
        type="endCall",
        name="done",
        prompt="Thank them and end the call politely.",
    )

    wf.edge(greeting, qualify, label="interested", condition="Caller wants to continue.")
    wf.edge(qualify, done, label="done", condition="All qualification questions answered.")

    client.save_workflow(workflow_id=123, workflow=wf)
```
```typescript TypeScript
import { DograhClient, Workflow } from "@dograh/sdk";

const client = new DograhClient({ apiKey: "YOUR_API_KEY" });
const wf = new Workflow({ client, name: "loan_qualification" });

const greeting = await wf.add({
    type: "startCall",
    name: "greeting",
    prompt: "You are Sarah from Acme Loans. Greet the caller warmly.",
});
const qualify = await wf.add({
    type: "agentNode",
    name: "qualify",
    prompt: "Ask about loan amount, purpose, and monthly income.",
});
const done = await wf.add({
    type: "endCall",
    name: "done",
    prompt: "Thank them and end the call politely.",
});

wf.edge(greeting, qualify, { label: "interested", condition: "Caller wants to continue." });
wf.edge(qualify, done, { label: "done", condition: "All qualification questions answered." });

await client.saveWorkflow(123, wf);
```
</CodeGroup>

## Edit an existing agent

Load an agent into an editable `Workflow`, mutate it, then save:

<CodeGroup>
```python Python
wf = client.load_workflow(workflow_id=123)
wf.name = "loan_qualification_v2"
client.save_workflow(workflow_id=123, workflow=wf)
```
```typescript TypeScript
const wf = await client.loadWorkflow(123);
wf.name = "loan_qualification_v2";
await client.saveWorkflow(123, wf);
```
</CodeGroup>

## Discover node types

Each node's `type` string and required fields come from the backend's node-spec catalog. Fetch it at runtime to validate what you can build:

<CodeGroup>
```python Python
types = client.list_node_types()
for spec in types.node_types:
    print(spec.name, [p.name for p in spec.properties])
```
```typescript TypeScript
const types = await client.listNodeTypes();
for (const spec of types.node_types) {
    console.log(spec.name, spec.properties.map(p => p.name));
}
```
</CodeGroup>

<Note>
For a full description of each node type and its fields, see the [Nodes](/voice-agent/start-call) section of the Voice Agent Builder docs.
</Note>