# Common Workflows

Short examples for the loops agents usually need: discover state, prepare content, confirm the action, then track the result.

Canonical: /docs/workflows.md

## Discover workspace state

**CLI**
```bash
reelsfarm agent status
reelsfarm social connected --agent
reelsfarm assets list --category products --agent
reelsfarm posts list --status SCHEDULED --agent
```

**SDK**
```ts
const account = await rf.account.get();
const connected = await rf.social.listConnected();
const products = await rf.assets.list("products", { limit: 10 });
const posts = await rf.posts.list({ status: "SCHEDULED", limit: 10 });
```

## Generate an avatar

**CLI**
```bash
reelsfarm avatars generate \
  --prompt "Creator selfie style, bright room, holding a phone" \
  --model nano-banana-pro \
  --agent

reelsfarm confirm conf_123 --agent
```

**SDK**
```ts
const preparedOrJob = await rf.avatars.generate({
  prompt: "Creator selfie style, bright room, holding a phone",
  model: "nano-banana-pro",
});

if ("wait" in preparedOrJob) {
  const result = await preparedOrJob.wait();
}
```

## Generate slideshow text

**CLI**
```bash
reelsfarm slideshows generate-text \
  --prompt "Summer serum launch for TikTok" \
  --slide-count 6 \
  --agent
```

**SDK**
```ts
const slideshowText = await rf.slideshows.generateText({
  prompt: "Summer serum launch for TikTok",
  slideCount: 6,
});
```

## Generate a product scene

**SDK**
```ts
const scene = await rf.productScenes.generate({
  avatarUrl: "https://example.com/avatar.png",
  productImageUrl: "https://example.com/product.png",
  prompt: "Natural UGC kitchen counter shot, creator holding the product",
});
```

Product scene generation prepares an async Product Studio composition. Confirm the prepared action, then poll the product scene job status or wait through the SDK job wrapper.

## Schedule content

**CLI**
```bash
reelsfarm posts schedule \
  --content-type SLIDESHOW \
  --content-id sl_123 \
  --when 2026-07-01T15:00:00Z \
  --platforms tiktok:conn_123 \
  --caption "Launch day" \
  --agent

reelsfarm confirm conf_123 --agent
```

**SDK**
```ts
const prepared = await rf.posts.schedule({
  contentType: "SLIDESHOW",
  contentId: "sl_123",
  scheduledFor: "2026-07-01T15:00:00Z",
  caption: "Launch day",
  platforms: [{ platform: "TIKTOK", connectionId: "conn_123" }],
});
```

## Create an automation

**CLI**
```bash
reelsfarm automations create \
  --json-definition '{"name":"Daily TikTok","status":"PAUSED","targetConnectionId":"conn_123","schedule":{"slots":[{"days":["mon"],"timeLocal":"09:00"}]},"content":{"topic":"mindset","slidesCount":5}}' \
  --agent
```

Automation creation defaults to a prepared action. Keep new automations paused until the user has reviewed content rules, account target, and schedule.

## Track the result

**CLI**
```bash
reelsfarm posts status --id post_123 --agent
reelsfarm events recent --limit 20 --agent
```

**SDK**
```ts
const status = await rf.posts.getStatus("post_123");
const events = await rf.events.recent({ limit: 20 });
```