Changelog

Agent Thinking in Timeline: See Your AI's Reasoning Process

You can now peek inside your agent's mind and follow its reasoning process directly in the timeline view!

Agent Thinking in Timeline brings transparency to your AI workflows by displaying the agent's thought process before tool calls and after failed attempts. This feature helps you understand how your agents make decisions, troubleshoot issues, and build more reliable AI systems.

➡️ View reasoning steps - See how your agent breaks down complex problems

➡️ Track decision paths - Follow the logical progression that leads to specific actions

➡️ Identify recovery strategies - Observe how agents handle and recover from failed tool calls

➡️ Debug more effectively - Pinpoint exactly where and why an agent might be struggling

➡️ Build trust through transparency - Understand exactly how your AI reaches its conclusions

With Agent Thinking in Timeline, you gain unprecedented visibility into your AI's cognitive process, making it easier to refine prompts, improve workflows, and create more reliable agent-based solutions.

To access this feature, go to your Agent's Advanced settings and look for the "Language Model" section with Thinking/Reasoning Configuration options.

Currently supported models include Anthropic Claude 3.7/4.0 Sonnet/Opus and Gemini 2.5 models, with OpenAI o-series models coming soon.