Citations you can trace, answers you can trust

Source-traced citations

When an Agent cites data, news, or a file in its answer, you'll now see it underlined. Hover or tap on it and you'll get the full picture: where the information came from, when it was last updated, which tool pulled it, and the exact snippet behind it. So instead of wondering where a number came from, you can just check for yourself. It's a big step up in how transparent and trustworthy each answer feels.

More flexible model selection

Your chat sessions and Schedules now remember whichever model you picked last, so starting a new session won't reset your choice. And when you set up a Schedule, you can run it on whatever model you prefer. Just pick it from the dropdown, or tell Driven in the chat.

Agent Settings upgrade

• A new Agent Profile summary gives you a clearer sense of your Agent's style and how it approaches investing (existing Agents need one profile refresh before the summary shows up).
• All the settings now live in one place, so renaming your Agent, changing its avatar, and managing Channel connections are no longer scattered around.
• You can now choose how much effort each task gets, with three depths to pick from freely: Light, Medium, and High.

Polish & Fixes

• We've smoothed out the conversation flow: attachment cards look cleaner and timestamps make more sense at a glance.
• Answers are more reliable too. We've tightened the standards for real-time data, external facts, and cited figures, so the Agent is far less likely to fill in a number from memory or repeat a stale result.
• Share pages are easier to read now, with a scroll-position indicator and a button to jump back to the bottom.
• We fixed a bug where interrupted or unfinished Schedules could be marked as successful. Now a failure is clearly flagged as one.