Support & conversation — page 5

No project description available.

AI chat moderation for Minecraft (Paper/Folia) and Hytale servers, powered by TypeSafe's Jev model. Works with the TypeSafe API or Cloudflare AI Gateway.

Note Triage for WooCommerce: a WordPress plugin that sorts customer order notes (gift message, delivery instruction, question, complaint, fraud signal) with TypeSafe's Jev model and flags the urgent ones for staff.

Sorts a WordPress.org plugin's support threads into bugs, how-to questions, feature requests, conflicts, praise and spam, and lists the ones waiting for the author's reply, using TypeSafe's Jev model.

voice assistant that drives your desktop

A simple Python train station assistant built with Jev that uses natural-language input and Noul confidence scoring to route users based on whether they have lost something.

Talk to your Mac. It does the thing. A voice assistant for macOS that acts instead of searching.

粘贴聊天，分析互动模式 — 关系场景、十个互动维度与一份关系解读

Experimental macOS menu-bar assistant using TypeSafe Jev to recommend Codex models from drafts.

A live support reply co-pilot built on TypeSafe AI's Jev model, evaluating tone, commitment risk, escalation, and predicted satisfaction in one parallel call while you type. Deployed on Cloudways Velocity.

Learn TypeSafe's Jev model by building a support ticket triage app, step by step

LangChain + Jev (TypeSafe) tutorial: a support-ops agent whose small decisions (triage, model routing, tool guarding, evals) are made by Jev. Real run outputs included.

demo of conversation analysis using jev with LLM fallback

Multi-tenant RAG assistant for the SaleQue CRM: cited answers on PostgreSQL and pgvector with Row Level Security, Claude and OpenAI behind one adapter, Jev lead scoring. Reference build.

Kişisel kripto & hisse yatırım araştırma asistanı: backtest, walk-forward, istatistiksel anlamlılık, paper trading, TypeSafe Jev entegrasyonu. Yatırım tavsiyesi değildir.

Anonymous, share-card-first dating-chat evaluator: upload a screenshot, ask Jev for the read, and get the tea. Built on Next.js, Neon (Lakebase Postgres + Object Storage), and Vercel.

A Jev decision layer for Customer Success — 22 typed decisions per inbound message, 14 per account, 10 per outbound draft. Zero dependencies, 38 tests, runs offline.

TypeSafe's Jev, a judgment model that was never trained to write, made to chat one word at a time. Browser-only, bring your own OpenRouter key.

A small demo showing a cheaper way to route support tickets.

Ticket router built on TypeSafe's Jev, the companion code for a DataCamp tutorial. Six typed questions in one call, routing policy in plain Python.

Kev decision models, with MiniCPM5 base support (fork of jaredpalmer/kev)

Thunderbird add-on that flags phishing mail impersonating Japanese organizations. Optional TypeSafe Jev support.

Home Assistant integration: TypeSafe Jev decides what each room needs; deterministic code acts, with phone confirmation for risky devices.

Multi-agent customer support API where the LLMs write the text and a typed decision model makes the decisions. Jev (TypeSafe System One) handles routing, response evaluation and retry/escalation; FastAPI + Ollama. Includes a 60-ticket benchmark against LLM free-text and structured-JSON baselines.