Jev live chat moderation

Review live chat against your channel rules

Try messages under rules for harassment, cross-stream relays and unsolicited gameplay instructions. Compare allowable reactions with violations and ambiguous context before choosing a moderation action.

Review one message against the channel rulesLive API
Try an example

Original synthetic chat text; no real viewer or account is evaluated.

Source: Workflow inspiration on X

Source and example scope

Independent channel-policy example. No stream connection, hiding, blurring or account moderation action.

Channel: no unsolicited gameplay instructions or cross-stream relays.

Decision rules and labels
AllowUnsolicited instructionsCross-stream relayHarassmentNeeds review
A real response from the Jev API

Edit any input to explore a different decision. No request is sent until you run it.

Your next decision

Not run yet

Choose an example or write your own input, then run it to see the ranked choices.

Results are not stored by this site. Your submitted text is processed by the API provider.

The decision

A channel policy gives the labels meaning.

The example channel is a spoiler-free game stream that does not want unsolicited gameplay instructions or updates relayed from another live stream. Those preferences are part of this demo policy. They are not presented as universal platform rules, and a different channel could choose different boundaries.

Jev receives a message and the supplied context, then chooses one of five labels. An ordinary reaction or genuine question can be allowed. A command directing the next move is classified separately from a report about another streamer. A direct personal insult has its own category. Unclear quotations and competing categories stay in Needs review.

The X source describes a streaming-comment filter with separate categories and display actions. This page implements only an independently authored text-classification exercise. Twitch's developer documentation offers a useful separation: held messages can be reviewed before a moderator approves or denies them. Our demo returns a label; it does not connect to Twitch or another streaming service.

Conceptual game-stream messages routed to ordinary conversation and a moderator review tray.
AI-generated concept illustration of chat triage; not a platform interface or real viewer conversation.
How it works

Review chat in four explicit steps.

Classify the message, then decide what to do with it.

  1. Illustration of adding the text or evidence for a decision

    Write the channel policy

    Define unwanted instructions, relays and targeted insults, plus an option for unclear cases.

  2. Illustration of defining a question and its allowed choices

    Preserve relevant context

    Include whether advice was requested and enough surrounding text to understand a quotation.

  3. Illustration of sending one input and comparing the returned choices

    Inspect the category

    Compare ordinary questions with unwanted commands and ambiguous messages. Keep the probability distribution with the label.

  4. Illustration of reviewing a result and an uncertain item before using it

    Let moderation own the action

    Use the label to organize review. Hiding, blurring, warning or banning needs separate application logic and human oversight.

Our API test

Six messages, including a close review boundary.

Six messages, including a close review boundary.
Original chat messageObserved labelLeading probability
Positive reactionAllow100%
Genuine questionAllow99%
Unrequested movesUnsolicited instructions100%
Other stream relayCross-stream relay97%
Targeted insultHarassment100%
Ambiguous quotationNeeds review57%

Six live Jev requests on September 27, 2026. The ambiguous quotation split between Needs review (57%) and Harassment (42%), illustrating why a leading label is not certainty. Synthetic functional checks, not an accuracy benchmark.Verified

Understand the results

The instructions sample explicitly says advice was not requested

The instructions sample explicitly says advice was not requested.

Read the example notes

Change that context to say the streamer asked for guidance, then reconsider whether the message violates your rule. If the policy does not explain requested advice clearly enough, revise it before trusting the result. Context is part of the decision, not decoration.

The quotation sample repeats an insult without telling us who is being quoted or why

The quotation sample repeats an insult without telling us who is being quoted or why.

Read the example notes

It might be reporting an incident, endorsing an insult or describing something unrelated. This example sends it for review rather than inventing the missing conversation. In a real queue, preserve the surrounding messages so a moderator can resolve it.

Using the result in your application

Download observed-chat.json and run-choice-sample.mjs into a private Node.js project.

Read the example notes

Tested setup: Node.js 24.18.0 and @typesafe-ai/sdk 0.6.0. Run npm init -y and npm install @typesafe-ai/sdk@0.6.0. Set TYPESAFE_API_KEY privately, then run node run-choice-sample.mjs observed-chat.json quote. The runner sends one request without retries.

Source and example scope

The fixture preserves every exact message, policy, choice and recorded distribution.

Read the example notes

The Node output contains the selected ID, elapsed time and fresh provider result. Small differences between runs are possible. These six synthetic checks illustrate the policy; they do not estimate moderation accuracy, replace channel moderators or reproduce the source filter's speed.

One live request

Replay one chat decision from Node.js.

View the code example
run-choice-sample.mjs
import { readFile } from 'node:fs/promises';
import { choice, TypeSafeClient } from '@typesafe-ai/sdk';

// Run one selected sample. There are no retries or automatic batch requests.
const [file, sampleId] = process.argv.slice(2);
if (!file || !sampleId || !process.env.TYPESAFE_API_KEY) {
  throw new Error('Set TYPESAFE_API_KEY, then run: node run-choice-sample.mjs FIXTURE.json SAMPLE_ID');
}
const raw = await readFile(file, 'utf8');
if (Buffer.byteLength(raw) > 1_000_000) throw new Error('Fixture is too large');
/** @type {{samples: Array<{id: string, request: {context: string, question: string, choices: string[]}}>}} */
const fixture = JSON.parse(raw);
const matches = fixture.samples.filter(sample => sample.id === sampleId);
if (matches.length !== 1) throw new Error('Select exactly one existing sample ID');
const { context, question, choices } = matches[0].request;
if (typeof context !== 'string' || typeof question !== 'string' || context.length > 12000
  || question.length > 500 || !Array.isArray(choices) || choices.length < 2 || choices.length > 12
  || choices.some(label => typeof label !== 'string' || !label || label.length > 120)
  || new Set(choices).size !== choices.length) throw new Error('Invalid sample request');
const client = new TypeSafeClient({ logLevel: 'off' });
const start = performance.now();
try {
  const result = await client.systemOne({ model: 'jev-latest', state: { context, question, choices },
    questions: { decision: choice(question, Object.fromEntries(choices.map(label => [label, null]))) } },
    { timeout: 10000, retry: { maxRetries: 0 } });
  console.log(JSON.stringify({ sampleId, elapsedMs: Math.round(performance.now() - start), result }, null, 2));
} catch {
  console.error('The API request failed. No retry was sent; check your account and network privately.');
  process.exitCode = 1;
}
Scope of this demo

What this example helps you test.

Supplied choices

What you can test

  • Testing explicit channel-specific text rules
  • Separating questions from unrequested gameplay commands
  • Keeping ambiguous quotations in a review queue
Application responsibilities

What this demo does not do

  • Enforcing every platform rule or detecting all harmful content
  • Inferring unseen chat history or viewer intent
  • Automatically hiding messages or banning accounts
Example FAQ

Questions before you use the result.

Understand the choices, the source and what a live result means.

Are these universal streaming-platform rules?

No. No unsolicited gameplay instructions and no cross-stream relays are this example channel's preferences. Write rules appropriate to your community.

Why keep instructions and relays separate?

They describe different reasons a channel might review a message. Separate labels let moderators see which local rule may apply.

Will an ordinary question be hidden?

This demo does not hide anything. Under the stated policy, a genuine question without another violation is Allow.

How are quoted insults handled?

A quotation without enough context goes to Needs review. A moderator needs the surrounding conversation before deciding what the quotation means.

Does this replace an existing moderation system?

No. It is a small text-classification demonstration, with no platform integration and no measured coverage of a full moderation policy.

Test your own decision

Try another input here or build a different Choice question in the Playground.