Changelog

In-Chat Agent Editor & Per-Conversation Thinking Level

Each AI agent conversation now has its own Thinking Level control, letting you choose how much reasoning the agent applies before responding — from Off (direct answers, no reasoning) to High (deep reasoning, slowest). Au

Each AI agent conversation now has its own Thinking Level control, letting you choose how much reasoning the agent applies before responding — from Off (direct answers, no reasoning) to High (deep reasoning, slowest). Auto uses the agent's default, so you only need to override it when a specific chat calls for faster or more thorough answers.

Operate on one system.

Talk to our team about consolidating your stack onto erxes. 30-minute walkthrough, custom to your org.