Parallel News Research
News agent now plans and executes multiple search queries in parallel, then aggregates results for faster and more comprehensive coverage.
The latest features, improvements, and fixes to the StressGen platform.
News agent now plans and executes multiple search queries in parallel, then aggregates results for faster and more comprehensive coverage.
Kalshi and Polymarket are now analyzed by dedicated agents with LLM-powered market interpretation, replacing the single prediction agent for more granular signals.
US Treasury 2Y yield now correctly sources from FRED instead of Yahoo Finance futures.
Added EWMA correlation estimation, Ledoit-Wolf matrix shrinkage, and condition number monitoring for more robust risk factor dependency modeling.
New dashboard widget tracking NFCI, STLFSI4, and OFR FSI financial stress indices.
Users can now share any scenario to a public page.
Key metrics in historical narratives now show provenance tooltips revealing the exact data source and computation method behind each number.
When a crisis isn't in the knowledge base, an agentic research loop (news/web search) fills the gap automatically.
New contact form page for reaching the StressGen team. Added a curated regulatory calendar with verified dates for upcoming Fed, ECB, and prudential deadlines. Crisis Chronicle drawer now surfaces historical narrative context.
Fixed HMM regime detector to correctly identify market stress states in the dashboard. Improved site discoverability with SEO fixes across sitemap, metadata, and llms.txt. Dashboard widget preferences now persist correctly across sessions.
Added GDELT and Finnhub as new news providers for broader market and geopolitical coverage. Prediction market data from Kalshi and Polymarket now injects price momentum signals into scenario generation with tighter relevance filtering.
- Portfolio snapshots with delta/gamma/vega exposures per risk factor - Stress test engine with unit-aware impact computation - Pivot table with drag-and-drop, heatmaps, and CSV export - Cross-run comparison with Shapley attribution - Snapshot audit trail for regulatory compliance
- Subscription tiers (Free, Professional, Enterprise) - Subdomain routing for app vs marketing site - Regime detection alerts and PDF viewer - SEO and logging hardening
- Geopolitical risk taxonomy with 15 risk types and calibration anchors - Causal transmission DAG engine for modeling shock propagation paths - Contagion correlation monitor with regime detection - Crisis matching against 14 historical episodes (GFC, COVID, etc.) - Per-shock provenance tracing for full audit trail
Streamlined role-based access controls and introduced clearer subscription tiers throughout the platform.
New dedicated FAQ page covering common questions about stress testing, scenarios, and platform usage.
Fixed a slowapi header injection bug causing intermittent 500 errors, and resolved Redis connection pool cascade failures that could take down database connections during high load.
Upload portfolio exposures via CSV or Excel files with template validation and error reporting. Snapshot deletions now use soft delete for regulatory audit compliance, with full user attribution tracking.
Corrected a PII sanitization method call that could fail silently when generating chat titles, ensuring personal data is always scrubbed before reaching LLM providers.
Resolved chat message text overflowing in the expanded sidebar, fixed duplicate key warnings in the activity feed, and corrected earnings calendar date grouping and hover states.
Run stress tests against portfolio snapshots to compute P&L impacts across risk factors — with waterfall charts, factor attribution breakdowns, and cross-run comparisons.
Explore stress test results with drag-and-drop pivot tables featuring collapsible rows, inline bar charts, heatmaps, sorting, and a hide-empty-rows toggle.
Track portfolio risk exposures over time with daily snapshots, per-risk-factor delta and gamma sensitivities, and an analytics dashboard featuring time-series charts and exposure matrices.
Generate regulatory stress test scenarios (DFAST, CCAR) with dedicated agent routing and RAG context. Scenario detail page now features a card-based layout with color-coded hero, expandable descriptions, and numbered key risk factors.
Redesigned the Market Snapshot and Scenarios pages with richer data displays, improved layouts, and interactive details. Scenario cards now highlight top primary shocks. Macro and inflation widgets show clearer thresholds and data freshness.
Run stress tests grounded in real financial crises (2008 GFC, COVID-19, Oil Shock, and 5 more), with automatic narrative generation and historically-calibrated shock values.
Significantly faster document processing, more resilient infrastructure, and improved uptime for consistent performance.
Access corporate yield curves, credit spreads, economic calendars, and international macro indicators from additional data sources.
Project how stress scenario impacts unfold over time, giving a forward-looking view of portfolio risk evolution.
See which stress scenarios are most likely to materialize based on current market conditions, with an interactive ranking on the dashboard.
Create a free account to get notified about new features and try AI-powered stress testing today.