Video enhancement for agentic workflows

BetterVideo as an agent tool

In agentic frameworks, tools are functions the agent can call. BetterVideo exposes three operations:

• enhance_video(url, resolution) — Submit a video for enhancement
• get_job_status(job_id) — Check if processing is complete
• get_download_url(job_id) — Get a time-limited download link

Wrap these in your framework's tool interface and the agent can decide when to use them.

Framework integration patterns

LangChain / LangGraph

from langchain.tools import Tool

@tool
def enhance_video(video_url: str) -> str:
    """Enhance video quality. Use when video is blurry, noisy, or low-resolution."""
    # Call BetterVideo API
    job = bettervideo.submit(video_url)
    job.wait()
    return job.download_url

OpenAI function calling

functions = [{
    "name": "enhance_video",
    "description": "Improve video quality (upscale, sharpen, denoise)",
    "parameters": {
        "type": "object",
        "properties": {
            "video_url": {"type": "string"},
            "resolution": {"type": "string", "enum": ["1080p", "4k"]}
        }
    }
}]

Handling asynchronous processing

Video enhancement takes time (30-120 seconds typically). Two patterns for agents:

Polling

Submit job, then poll status until complete. Simple, but blocks the agent.

Webhook + state management

Submit job with webhook URL, continue other work, resume when notified. More complex, but scales better.

For most agents, polling is fine — the enhancement time is similar to the thinking time for complex reasoning.

One API call — curl, Python & Node

Submit a video by URL, then poll GET /v1/jobs/{id} until done (or receive a signed webhook), and fetch a time-limited download link:

curl -X POST https://api.bettervideo.io/v1/jobs \
  -H "Authorization: Bearer YOUR_KEY" -H "Content-Type: application/json" \
  -d '{"video_url":"https://.../clip.mp4","resolution":"1080p"}'

import requests
r = requests.post("https://api.bettervideo.io/v1/jobs",
    headers={"Authorization": "Bearer YOUR_KEY"},
    json={"video_url": "https://.../clip.mp4", "resolution": "1080p"})
job = r.json()  # poll GET /v1/jobs/{job['id']} until status == "done"

const res = await fetch("https://api.bettervideo.io/v1/jobs", {
  method: "POST",
  headers: { "Authorization": "Bearer YOUR_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({ video_url: "https://.../clip.mp4", resolution: "1080p" })
});
const job = await res.json();

Privacy is the default, not an upgrade

• Never trained on. Pre-trained, fixed-weight models — your frames are enhanced and returned, never used to train AI.
• Never sold or shared. No third parties, no data brokers, no "anonymized" resale.
• Auto-deleted. Files self-delete (default 30 days), or delete any job instantly with one call.
• Proof on the Secure tier. Every deletion can return a signed deletion certificate, with a full audit log.