canonical: https://jentic.com/apis/netvyne.com/netvyne

# Netvyne API

Jentic publishes the only available OpenAPI specification for Netvyne API, keeping it validated and agent-ready. Netvyne is a content moderation service that scores user-generated comments and other text for safety, with category-level instructions and webhook delivery for asynchronous moderation results. The five-endpoint surface covers categories listing, comment submission, moderation instructions, webhook configuration, and a demo webhook for integration testing.

## For AI agents

Submit user-generated comments for moderation, configure webhooks for results, and manage Netvyne moderation categories.

## Scope

Does not handle image or video moderation, identity verification, or account banning - use for text comment moderation and webhook-driven verdict delivery only.

## Capabilities

- Submit a user comment for safety classification
- List the moderation categories available on the account
- Register a webhook to receive moderation verdicts asynchronously
- Fetch the moderation instructions guiding the classifier
- Trigger a demo webhook delivery to verify integration plumbing

## Use cases

### User-Generated Content Moderation

Send every comment posted on a community or marketplace platform to Netvyne for safety classification. The platform receives the verdict via webhook and can hide, hold for review, or publish based on the category and confidence returned.

Example prompt: POST a new comment 'this is a sample post' to /comments and capture the comment id returned for downstream webhook correlation.

### Moderation Webhook Setup

Register a webhook so Netvyne pushes moderation results back to the platform asynchronously, then run a demo webhook delivery to verify the integration end-to-end before production traffic flips on.

Example prompt: POST a webhook target https://app.example.com/netvyne-webhook to /webhooks, then call /demo_webhook to fire a test delivery and confirm the platform received it.

### Category and Rules Inspection

Pull the active moderation categories and instructions used by the classifier for review by trust and safety teams. Useful before tuning thresholds or onboarding to a new community context that has different content norms.

Example prompt: Fetch /categories and /instructions and present a side-by-side summary of each category and the active rule applied to it.

### AI Agent Trust and Safety Assistant

Let an AI agent decide whether a flagged comment should be auto-deleted or escalated to a human reviewer by submitting it through Netvyne and reading the categorical verdict. Saves moderator time on clear-cut cases while preserving human review for borderline content.

Example prompt: Submit comment text to /comments, wait for the webhook verdict, and decide between auto-delete, hold-for-review, or publish based on the returned category.

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/categories` | List moderation categories |
| POST | `/comments` | Submit a comment for moderation |
| GET | `/instructions` | Get the active moderation instructions |
| POST | `/webhooks` | Register a moderation result webhook |
| POST | `/demo_webhook` | Trigger a demo webhook delivery |

## Key resources

- **Categories** — Moderation categories configured for the account
- **Comments** — Submitted comments awaiting or holding moderation verdicts
- **Instructions** — Moderation rules and instructions guiding the classifier
- **Webhooks** — Callback targets that receive asynchronous moderation results
- **Demo Webhook** — Test endpoint for verifying webhook delivery

## Why Jentic

- **Setup:** Wiring the Netvyne API by hand means setting its Authorization API key header, targeting the api.netvyne.com/v1 host, and shaping comment submission and webhook registration calls yourself. Through Jentic you install once, import Netvyne from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** Netvyne submits comments and webhook config from the request body, so limit the agent to the operations it needs, such as moderating a comment or reading categories, and leave out the ones it should not run.
- **Credential handling:** Your Netvyne API 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 'moderate a user comment' or 'register a verdict webhook', and Jentic returns the matching Netvyne operation with its parameter schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **OpenAI Moderation API** — OpenAI offers a free, broad-purpose moderation classifier on top of its own model stack.
- **Drift API** — Drift captures user-generated chat that needs to be moderated before it lands in a public thread.
- **SendGrid Mail API** — SendGrid Mail notifies moderators by email when Netvyne flags a comment for human review.

## FAQ

### Why is there no official OpenAPI spec for the Netvyne API?

Netvyne does not publish an OpenAPI specification on its developer site. Jentic generates and maintains this spec so that AI agents and developers can call Netvyne API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.

### What authentication does the Netvyne API use?

Netvyne uses an API key passed as a Bearer token on the Authorization header. Through Jentic the key is stored encrypted in the vault and never enters the agent's prompt context.

### Can I submit a comment for moderation through the Netvyne API?

Yes. POST /comments accepts the comment text and returns an identifier. The moderation verdict is delivered asynchronously to the webhook URL you registered via POST /webhooks.

### What are the rate limits for the Netvyne API?

Netvyne does not publish a fixed public rate limit; throughput depends on your account tier. For high-volume moderation traffic, batch submissions and confirm peak limits with the Netvyne team.

### How do I test webhook delivery through Jentic?

Run jentic.search('trigger netvyne demo webhook'), load the matching operation, and execute POST /demo_webhook. Jentic returns the demo dispatch result so the agent can verify the platform-side webhook handler before flipping production traffic on.

### Does the Netvyne API moderate images or video?

This OpenAPI surface focuses on text comment moderation - categories, comments, instructions, and webhooks. Image and video moderation, if available, would require a separate Netvyne product surface.

### Can I limit what my agent is allowed to do with the Netvyne API?

Yes. Because you run Jentic One yourself, your own rules decide which Netvyne operations and credentials the agent may use. Since comment text and webhook targets come from the request body, you can allow only the calls the agent needs, such as submitting a comment to POST /comments or reading categories from GET /categories, while leaving out registering webhooks via POST /webhooks or triggering POST /demo_webhook. Only the operations you approve are ever exposed to the agent.