Release Notes

Cross-organization admin isolation. Admin users are now restricted to managing users within their own organization. Platform-wide operations require super-admin privileges.

Open redirect prevention. OAuth flows now validate redirect URLs before navigation.

Financial anomaly detection. New dashboard section surfaces NOI drift, CapEx irregularities, and rent anomalies across your portfolio automatically.

Rent reconciliation dashboard. Compare lease data against actual payments to identify escalation compliance gaps.

API Reference documentation. Complete reference for 50+ API endpoints with request/response examples. View API docs.

Help Center expanded to 22 FAQs. New answers covering AI agents, data export, dashboard, critical dates, conversation sharing, and templates.

Morning briefing. Time-aware greetings, portfolio health score, and quick-action buttons to jump directly into chat with prefilled queries.

AI answer accuracy. Reduced false hallucination warnings on calculated financial figures — derived amounts (occupancy rates, pro rata calculations, weighted averages) are now correctly recognized.

Search precision. Tenant name matching now uses word boundaries to prevent false positives (e.g., "Ross" no longer matches "across").

Critical date creation, agent run history, and CSV export endpoints — 4 runtime crashes resolved.

Dashboard urgency badge now shows live overdue + critical date counts in the sidebar navigation.

Multi-tenant organizations. B2B customer isolation with organization-scoped data, user management, and role-based access. Admin endpoints for creating and managing organizations.

Row-Level Security (RLS). PostgreSQL row-level policies enforce data isolation at the database level — defense-in-depth against cross-organization data leaks.

Subscription tiers. Free trial (100 queries/month), Professional (2,000/month), and Enterprise (unlimited). Usage tracking and quota enforcement.

Critical date tracking. Monitor lease expirations, renewal deadlines, and option exercise dates with urgency-tiered alerts (overdue, 30-day, 60-day, 90-day).

Query templates. 19 pre-built CRE query templates across financial analysis, lease review, portfolio comparison, and due diligence categories.

Scheduled reports. Configure weekly summaries, critical date digests, and custom reports delivered via email on a recurring cadence.

Portfolio analytics dashboard. Tenant risk scores, lease rollover analysis, concentration metrics, rent escalation calendar, and data quality monitoring.

Structured logging. JSON logs now include organization ID, correlation IDs propagate to background tasks, and slow database queries (>500ms) are flagged.

Scroll-to-bottom button in chat now appears correctly when scrolling up during a conversation.

Streaming errors no longer replace partial AI responses — errors append below the content you already received.

Escape key now properly closes the evidence panel.

Long conversation titles no longer overflow the chat header.

Automatic model tiering. Queries are routed automatically across a fast tier (quick lookups), a standard tier (standard analysis), and a deep tier (deep reasoning) based on complexity — no manual switching.

Cost tracking. Every AI provider API call is logged with input/output token counts and estimated cost per query for transparent billing.

Search-first document retrieval. Redesigned RAG pipeline: search Egnyte first, cache document IDs, then fetch full text on demand. More efficient and reliable than embedding-based retrieval.

Real-time thinking narration. See what the AI is doing as it works — each search and document read shows a descriptive status update with discovery summaries.

Efficiency. Typical queries now complete in 2-5 tool calls (down from 10+). Search snippets are checked before full document reads.

LOI Generator agent. 7-step automated pipeline: searches your historical Letters of Intent in Egnyte, extracts format and clause patterns, picks the best-match template, generates a new LOI in your exact style, and flags deviations from your standard positions.

Clause deviation review. Automatic comparison of new LOI terms against your historical standard positions with high/medium severity flags.

Large context windows. Handle longer documents and multi-document analysis in a single query using our AI provider's large-context models.

Reasoning orchestration. Queries are classified by complexity (simple, moderate, complex) and routed to appropriate reasoning strategies — faster answers for simple questions, deeper analysis for complex ones.