Ask questions over your own trades, then preserve the useful insights

The app stores typed and voice turns in the same durable threads, allows renaming and deleting conversations, and supports both normal chat and streaming progress updates. Ask “Give me a summary of what happened in this chat” to recap the full thread, including older turns outside the normal recent-message window.

Each completed exchange contributes to a cumulative thread summary and a searchable conversation episode. Relevant earlier exchanges are recalled with bounded semantic and text search, so phrases such as “go back to what I said earlier” work in both Tutor chat and Live voice. Useful preferences, goals, corrections, strategies, decisions, and unresolved topics may also carry across conversations.

Typed chat and Live voice can use the same guarded read tools for trades, positions, tracking, analytics, insights, notes, emotions, goals, accounts, playbooks, backtests, reports, achievements, Community, Mentor Mode, notifications, workspace metadata, Economic Calendar, Market News, eligible Market Monitor analysis, product documentation, and current web facts. The assistant must complete required lookups before making user-specific or time-sensitive claims.

Open Settings → AI memory to turn automatic saving or proactive recall on or off, search memories, correct their wording, pin important context, forget one item, or clear everything. You can also say “Remember that…” or “Forget…” in either chat or voice. Security credentials, payment secrets, and incidental chatter are excluded from automatic memory.

Saved memories retain a link to their source conversation. Forgetting a memory leaves its transcript intact; deleting a thread removes its transcript, thread summary, searchable episodes, queued indexing work, and any memory supported only by that thread.

The backend builds a user learning state from trades, AI feedback, and other signals so the tutor can adapt over time.

Insights surface recurring themes and can be marked read individually or in bulk.

Message feedback is tracked so the system can measure what worked and what failed in the AI responses.