> ## Documentation Index
> Fetch the complete documentation index at: https://reel25.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Content Radar to Analysis Pipeline

> Discover trending content, analyze it with AI, and organize into folders

End-to-end workflow: search for content → analyze top performers → organize everything.

**Total credit cost:** \~115 credits | **Time:** \~5 minutes

## Step 1 — Discover content with Radar

```python theme={null}
import requests
import time

API = 'https://api.reel25.com/api/v1'
headers = {'Authorization': 'Bearer reel25_sk_...', 'Content-Type': 'application/json'}

# Start search (100 credits)
search = requests.post(f'{API}/radar/search', headers=headers, json={
    'query': 'SaaS product demo videos showing screen recordings of productivity tools',
    'platform': 'tiktok',
    'depth': 'standard',
})
search_id = search.json()['data']['searchId']

# Poll until complete
while True:
    result = requests.get(f'{API}/radar/search/{search_id}', headers=headers).json()
    if result['data']['status'] in ('completed', 'failed'):
        break
    time.sleep(5)

videos = result['data']['videos']
print(f"Found {len(videos)} videos, intent: {result['data']['detectedIntent']}")
```

## Step 2 — Track the top performers

```python theme={null}
# Free — track top 15 by composite score (already sorted)
top_urls = [v['url'] for v in videos[:15]]

tracked = requests.post(f'{API}/videos/bulk-track', headers=headers, json={
    'urls': top_urls,
})
print(f"Tracked: {len(tracked.json()['data'])} videos")
```

## Step 3 — Analyze top 3 videos with AI

```python theme={null}
# 5 credits each = 15 credits total
for video in videos[:3]:
    video_id = video['platformVideoId']
    # Find the tracked video ID
    # ... trigger analysis
    analysis = requests.post(
        f'{API}/video-analysis/{video_id}/analyze',
        headers=headers,
    )
    print(f"Analysis queued for {video_id}")

# Wait for analyses to complete
time.sleep(30)

# Fetch results
for video in videos[:3]:
    result = requests.get(
        f'{API}/video-analysis/{video["platformVideoId"]}',
        headers=headers,
    ).json()

    if result['data'] and result['data']['status'] == 'completed':
        d = result['data']
        print(f"\nVideo: {video['description'][:60]}")
        print(f"  Hook: {d.get('hookStyle')} — {d.get('hookPhrase')}")
        print(f"  Format: {d.get('format')}")
        print(f"  UGC Fit: {d.get('ugcFit')} ({d.get('ugcConfidence')}%)")
```

## Step 4 — Organize into a folder

```python theme={null}
# Free
folder = requests.post(f'{API}/folders', headers=headers, json={
    'name': 'SaaS Demos — Best Performers',
})
folder_id = folder.json()['data']['id']

# Add tracked video IDs to folder
# video_ids = [list of tracked video UUIDs]
# requests.post(f'{API}/folders/{folder_id}/videos', headers=headers, json={
#     'video_ids': video_ids,
# })
```

## What you get

After this workflow you have:

* **Discovered content** ranked by relevance + engagement
* **AI analysis** showing hooks, formats, CTAs, and UGC fit
* **Organized folder** for ongoing reference
* **Performance tracking** — metrics update automatically for tracked videos


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