What exactly triggers the escalation to a video call?

A message showing frustration or asking for a real person triggers an offer to start a video call; Jev supplies the sentiment and frustration level behind the decision.

What does the employee see on their dashboard?

A card with the sentiment, frustration level, and last user message plus an Answer call button that joins the employee to the video call.

Which credentials do I need before running it?

A Vonage API key and secret for the video application plus a TypeSafe AI key; the Codespaces setup script prompts for both during provisioning.

Is this a production-ready support agent?

No. It is a fake AI support agent plus employee page showing one escalation path with signaling, intended as a developer starting point.

How do I run it without a local setup?

Use GitHub Codespaces: fork the repository, click the Code button, open the Codespaces tab, and create a codespace on main. The environment loads and the setup script configures the Vonage application automatically.

Where do I find the running app and the dashboard?

After setup the terminal prints a URL you can click, or use the Ports tab and open the Forwarded Address. The fake AI support agent is the main page, and a Go to Employee Dashboard link at the top opens the employee view.

What does each service do in the flow?

Jev analyzes the chat messages and returns the sentiment and frustration level that decide whether to escalate or let the AI agent reply. Vonage Video API Signaling sends the notification to the employee dashboard, where the Answer call button joins the employee to the call.

CommunityJev Agents & MCP

Demo Video Javascript Jev Starter

Demo pairing Vonage Video API with Jev: chat sentiment and frustration scoring offers a video call and pings an employee dashboard.

See highlights

Open github.com

Stars: 0
Language: JavaScript
License: APACHE-2.0
Published by: Community
Author: Vonage-Community
Last verified: Oct 2026

Vonage-Community/demo-video-javascript-jev-starter

Organization repository on GitHub

View on GitHub

This application is intended to showcase to developers a possible use case of Vonage Video API and TypeSafe AI to create an AI support agent that quickly detects if a user is getting frustrated and start a video call with a Human agent.

Forks: 2
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

This application is intended to showcase to developers a possible use case of Vonage Video API and TypeSafe AI to create an AI support agent that quickly detects if a user is getting frustrated and start a video call with a Human agent. The Vonage Video API Signaling is used to send notifications to the Employees' dashboard. TypeSafe AI's Jev analyzes the user's chat messages and determines the sentiment and frustration level that is used to create an escalation to video call or pass the message to the AI agent.

Quoted from the project's README. Read the full README.

Tagscommunity github

Works forJev for Tool calling

Used inJev for Software & DevTools

Languages: JavaScript

Highlights

Jev analyzes chat messages for sentiment and frustration to decide between AI reply and human video escalation.
Vonage Video signaling notifies the employee dashboard of new escalation requests.
Employee card shows sentiment, frustration level, last message, and an Answer call action.
Codespaces one-click setup with guided Vonage application and API key provisioning.

Watch out

Demo scaffold needing your own Vonage and TypeSafe keys; video billing and limits follow your accounts. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

jev-mcp

MCP server that exposes Jev classify, score, yes-no check, risk gate, and multi-question decide tools to coding agents through one Jev call per tool.

Jev Agents & MCP#community#github

Community

codaaiteam/jev-mcpJavaScript

jevmap

Codebase mapper that indexes a repo into small units without AI, then asks Jev which units matter for a plain-language task and returns ranked files with line numbers and probabilities.

Jev Agents & MCP#community#github

Community

aegsrl7/jevmapJavaScript

jev-enhanced-plugin

Agent plugin adding typed Jev judgment packs to six existing coding skills for Codex, Claude Code, and Oh My Pi, without changing their procedures.

Jev Agents & MCP#community#github

Community

JiaWeiXie/jev-enhanced-pluginJavaScript

quicksilver

118

A Claude Code skill that moves bulk judgment off Claude and onto Jev. You filter files, classify items, rank candidates or locate lines, and it returns typed verdicts, a shortlist with borderline markers, and a receipt of the tokens Claude did not read.

Jev Agents & MCP#community#jevbest

Community

UditAkhourii/quicksilverJavaScript

jev-sift

MCP server that screens files, public webpages, or inline text against a query and returns compact relevance probabilities, so the main agent opens only promising items.

Jev Agents & MCP#community#jevbest#catalog-import

Community

kbhuw/jev-siftJavaScript

eutrya

Standalone terminal agent that puts Jev inside its planning loop, proposing text-model steps and scoring candidates against independent rubrics before a deterministic policy executes one.

Jev Agents & MCP#community#jevbest#catalog-import

Community

hellozenstrategist-lab/eutryaJavaScript

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai