canonical: https://jentic.com/apis/contentsweep.ai/contentsweep

# Content Sweep Agent API

The Content Sweep Agent API records copyright authority and runs takedown enforcement for registered works. Rights holders register original works, record revocable scoped delegations, request expiring quotes, and queue asynchronous enforcement operations whose evidence, cases, and takedown packets can be read back. Prepaid credits meter usage, webhook receivers are registered with a signing secret returned once, and a simulated sandbox lets a caller rehearse the flow before live activation.

## For AI agents

Register copyright works and rights holders, record scoped enforcement authority, queue takedown operations, and read back evidence and packets. Most calls use a bearer API key; a Stripe-Signature apiKey header secures the provider billing webhook.

## Scope

Does not handle visual search, media capture, or guaranteed content removal. Use for recording copyright authority and queuing takedown enforcement only.

## Capabilities

- Register original works and partner-managed rights holders
- Record revocable, scoped enforcement authority through delegations
- Create expiring quotes and reserve prepaid credits for asynchronous enforcement operations
- Read immutable evidence, cases, and takedown packets for an operation
- Register webhook receivers and replay recorded events
- Rehearse the enforcement flow in a simulated sandbox before live activation

## Use cases

### Copyright Registration and Authority

A rights holder's agent registers original works and records a revocable, scoped delegation that authorizes enforcement on their behalf. Authority is recorded explicitly and can be revoked irreversibly, so the chain of permission behind every later takedown is auditable.

Example prompt: Call POST /rights-holders to create the holder, POST /works to register the work, then POST /delegations to record scoped authority

### Queued Takedown Enforcement

An agent prices an enforcement action with an expiring quote, reserves the quoted maximum in prepaid credits, and queues an asynchronous operation. It then polls the operation and reads the immutable evidence and takedown packet once the work completes.

Example prompt: Call POST /quotes for a price, POST /operations to reserve and queue the work, then GET `/operations/{id}` to poll completion

### AI Agent Integration via Jentic

An AI agent reaches the Content Sweep Agent API through Jentic without handling the bearer key or the signing secrets itself. It searches by intent, receives the matching operation and its input schema, and executes the call with the credential injected at run time, rehearsing in the sandbox before any live, credit-spending action.

Example prompt: Search Jentic for 'register a copyright work', load the operation schema, and execute it with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/rights-holders` | Create a partner-managed rights holder |
| POST | `/works` | Register an original work |
| POST | `/delegations` | Record revocable scoped authority |
| POST | `/quotes` | Create an expiring quote |
| POST | `/operations` | Reserve a quote and queue asynchronous work |
| GET | `/operations/{id}` | Poll a queued operation |
| GET | `/evidence/{id}` | Export immutable evidence metadata and hash |
| POST | `/webhooks` | Register a webhook receiver |

## Key resources

- **Rights and Works** — Register rights holders, works, and scoped delegations
- **Enforcement** — Quote, queue, and poll takedown operations and read their evidence and packets
- **Billing** — Read the rate card, balance, and ledger and purchase prepaid credits
- **Events and Webhooks** — Register receivers, read delivery attempts, and replay recorded events

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 62 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 93 / 100
  - Developer Experience & Jentic Compatibility: 75 / 100
  - AI-Readiness & Agent Experience: 40 / 100
  - Agent Usability: 94 / 100
  - Security: 55 / 100
  - AI Discoverability: 59 / 100
- **View full report:** https://jentic.com/apis/contentsweep.ai/contentsweep/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring Content Sweep by hand means sending its bearer API key, handling expiring quotes and prepaid credit reservations, and storing the webhook signing secret that is returned only once. Through Jentic you install once, import Content Sweep from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** A rule can confine your agent to the operations it needs, such as registering works and reading evidence, because the credit-spending and irreversible actions are separate operations you choose to include or leave out. Revoking a delegation or purchasing credits stays off the agent's reach unless you grant it.
- **Credential handling:** Your Content Sweep key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'register a copyright work' or 'queue a takedown', and Jentic returns the matching Content Sweep operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **ModerateContent** — Automated content classification for images and text
- **OpenAI** — Moderation and language models for analyzing flagged material

## FAQ

### What authentication does the Content Sweep Agent API use?

Most operations authenticate with a bearer API key in the Authorization header per the OpenAPI spec, and a short scoped access token can be exchanged for 15-minute use. A separate apiKey scheme, the Stripe-Signature header, secures the provider billing webhook, and several discovery endpoints such as capabilities and pricing are public. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time.

### Can I queue a takedown enforcement action with the Content Sweep Agent API?

Yes. Create an expiring quote, reserve the quoted maximum in prepaid credits with the operations endpoint, and poll the operation until the evidence and takedown packet are ready. Enforcement requires an appointed delegation, so the authority behind each action is recorded first.

### Does the Content Sweep Agent API offer a sandbox before live use?

Yes. The sandbox is simulated and lets an agent rehearse the enrollment and enforcement flow without spending credits, while actual operations use real quotes. Live capabilities depend on account activation, so an agent can validate its logic before switching to the accountable live organization.

### How do I register a work through Jentic with the Content Sweep Agent API?

Search Jentic for 'register a copyright work', and it returns the Content Sweep work-registration operation with its input schema. Load the schema and execute POST /works with the credential injected at run time. To run it on your own infrastructure, install Jentic One from its GitHub repo.

### Can I limit what my agent is allowed to do with the Content Sweep Agent API?

Yes. Write a rule that allows only the operations the agent needs, for example registering works and reading evidence, so credit-spending actions like reserving an enforcement operation or purchasing credits are left out unless you add them. Each call runs through your own instance and is logged for review.