Urgent.News

What's breaking now, across thousands of outlets.

AI

Building a Zendesk replacement with AI: 24 checks and 21 spec gaps

The short answer Yes, for a small team answering support email. We gave Claude, working in Type, our Help Desk blueprint and had it follow the four phase prompts in order. The final build passed 24 of 24 acceptance checks in one browser run on a fresh database, with 64 automated tests . It handles tickets from email and a web form, Zendesk's six statuses and lifecycle rules, public replies and…

The short answer is yes, a small team can replace Zendesk with an AI-built solution. The developer used Claude to follow four phases of prompts and the final build passed all 24 acceptance checks in one run. The app handles email and web form tickets, Zendesk statuses and lifecycle rules, public replies, internal notes, threading, first-response targets, canned replies, weekly reports, CSV export and data deletion.

However, there were 21 gaps in the specification that needed interpretation. The build cost is not free, as it requires hosting, a database, an email provider, and development time, which could be a few hundred dollars a year for a small team.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

ContextBridge — Switch AI Models Without Losing Your Context

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built I built ContextBridge , a Chrome extension that helps you switch between AI models without losing…

  • ContextBridge Chrome extension preserves AI conversation context
  • Captures messages from ChatGPT, Claude, Gemini for Ollama models
  • Enables seamless handoff to open-weight models like Gemma 3 (4B)

GPT-4o Is Retiring From the API: What to Do Before January 14, 2027

Originally published at: https://toolpilotpro.com/gpt-4o-retirement-api-shutdown GPT-4o Is Retiring From the API: What to Do Before January 14, 2027 If your product calls GPT-4o, the clock is ticking.

  • GPT-4o API model retiring on January 14, 2027
  • Developers must migrate before shutdown date
  • gpt-6-luna model replacement provided

The Real Cost of Running LLMs On-Premise (It's Not What You Think)

GPU bills, hallucinations, and the dream of free AI inference. A full TCO breakdown including the 40 hours of debugging nobody talks about.

  • On-premise GPU costs $58–73/month, compared to $180–240/month cloud API
  • Time spent debugging adds non-monetary cost to on-premise inference
  • Breakeven point at 3–4 months for $500–600 GPU vs. $180–240/month cloud API

More from Saturday 17 October →