Urgent.News

What's breaking now, across thousands of outlets.

AI

I Built a Support-to-Engineering Pipeline with 3 AI Agents and 2 Human Approvals on Switch

Every software company loses days at the same hand-off. A customer writes "I think I was overcharged." Support can't tell if it's a bug, so they paste it into an engineering channel. Engineering asks for the order details again, someone eventually reproduces it, fixes it, gets it reviewed and merges it, and nobody tells support, so the customer never hears back. The work takes minutes. The…

Flip the Switch Hackathon led to the creation of Support-to-Ship Bridge, which connects two teams using three AI agents and two human approvals. This pipeline automates the process of resolving customer support tickets by having the AI agents reproduce the issue, fix it, and obtain approval from the engineering team. The two human approvals involve merging the fix into the codebase and sending a refund to the customer.

All steps are completed within the chat application, using Switch infrastructure that integrates AI agents into existing team chat platforms like Slack, Teams, Discord, Telegram, or Mattermost. The system is open-source and can be set up locally without requiring Slack admin rights.

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

I masked a dataset for an LLM and kept every checksum valid — here's the approach

Sharing data with an LLM is a data-leak problem with an extra twist: the model is a reader, not a database. If you scrub a spreadsheet with *** , the model has nothing to reason about. If you replace every cell with random noise, joins break and the analysis collapses.

  • Fake values maintain original data structure
  • HMAC-SHA256 used for deterministic fake value generation
  • Original values restorable with secure secret

More from Saturday 7 November →