Three focused improvements that cut through the noise: better visibility into what your agents are doing, smarter knowledge organization, and faster agent discovery. Everything you need to work with confidence.

Watch your agent work in real-time

Interpretability in Chat shows you exactly what your agent is doing as it happens. See the workflow, skill chains, API calls, and how inputs flow through each step. No more waiting for the agent to finish, you watch the progress unfold.

• View agent workflow and skill execution step-by-step

• See how inputs are processed and used

• Watch API calls and data flow in real-time

• Understand what your agent is doing at each moment

This gives you better visibility and confidence in your agents' decisions, without waiting for completion.

Add shared knowledge to your projects

You can now attach knowledge sources directly to projects. Every chat within that project automatically has access to the same centralized knowledge, giving everyone context without duplication.

• Attach knowledge sources to projects

• All project chats access shared knowledge automatically

• Better context for team collaboration

• No need to manually add knowledge to each chat

Find it at: Project settings → Knowledge → Add knowledge sources

Pin your best agents for the whole team

Workspace admins can now pin agents to the Chat home screen. Your team sees your most-used agents right away : no searching, no hunting.

• Pin agents to Chat home for easy discovery

• Help your team find the right agent instantly

• Organize your enterprise agent shelf

• Available to all workspace members

Find it at: Admin settings → Pin agents to Chat home

Improvements

LLM configuration now has its own dedicated menu. No more digging through mixed settings, everything related to your model is in one place.

Find it at: Agent configuration → LLM settings

Get started now

Start by pinning your most-used agents, then explore the Chat selector to see how fast you can switch between AI models. Watch the interpretability panel next time you run a complex task, you'll see exactly how your agent thinks.