Clearer signal timing
Risk signals now show whether they reflect what has already happened or what markets expect next, so the timing of each signal is unambiguous.
The latest features, improvements, and fixes to the StressGen platform.
Risk signals now show whether they reflect what has already happened or what markets expect next, so the timing of each signal is unambiguous.
Scenarios now draw on Eurostat, the IMF, and the BIS for richer global economic context.
Each scenario now shows a coverage score — an at-a-glance read on how thoroughly its narrative is grounded in retrieved evidence.
Applied routine security patches and dependency updates across the platform.
You can now hover a figure in a scenario narrative to read the exact source text it was drawn from.
Historical replays now cover the full set of risk factors for each episode, with clearer instrument labels, correctly scaled dollar values, and an honest count of what the knowledge base could and could not supply.
Filing analysis reads real 10-K and 8-K structure far more reliably, removes duplicate material events, and attributes each item to the issuer that reported it.
Scenarios centred on Bitcoin, Ethereum or the wider crypto market now pull live crypto prices and crypto-specific news alongside the usual macro context.
Scenario narratives now draw their numbers from a single evidence ledger, so each figure carries a link back to the market data, filing or historical episode it came from. Figures we can't verify are marked as such rather than quietly adjusted.
The scenario Intelligence tabs share one layout and one set of labels, units and colour meanings; selection states, tooltips and empty states now reach screen readers and keyboards properly.
Prediction-market probabilities and forecast ranges are now derived from the live order book and the full price ladder, giving steadier expected values and confidence cones across Kalshi and Polymarket.
Sharing a scenario link again renders a rich preview card — scenario name, type, severity, and top shocks — in social and chat apps.
Numbers quoted in narratives are grounded more strictly against live market data, and shock calibration handles edge cases more consistently.
Generated scenarios again cite analogous historical episodes and knowledge-base context throughout their narratives and causal maps.
Routine security patches and dependency upgrades across the platform.
Fixed an issue where new scenario runs could hang at 0% before starting. Generation now runs on a dedicated background worker, so the app stays fast and responsive while scenarios build.
Modeled shock magnitudes are now scaled to each scenario's time horizon.
Enforces credit ladder consistency and aggregation consistency.
Strengthened safeguards.
The news engine now runs follow-up research.
A range of bug fixes and stability improvements across the platform.
Scenarios and the dashboard now show the unemployment and inflation trajectories implied by live prediction markets.
The conversational assistant can now pull SEC filings, Fed projections, prediction markets, and reference knowledge directly into its answers.
The Fed's own economic forecasts (Summary of Economic Projections) and dot plot are now on the dashboard, shown side-by-side with what markets are pricing in.
A new dashboard tile tracks demand at recent Treasury auctions, including bid-to-cover ratios and indirect-bidder share across maturities.
Filing analysis now follows earnings-release exhibits in 8-K reports and captures the full risk-factor section of annual reports for more complete coverage.
Routine security patches and dependency upgrades across the platform.
Unified severity indicators, redesigned data tables, a clearer causal-map header, and timeframe-aware calendars across the scenario Intelligence view.
Market data loads more reliably across the dashboard and scenarios thanks to smarter caching of upstream sources.
Stability improvements and bug fixes across scenario generation, the dashboard, and the Intelligence views.
Strike-ladder prediction markets now display a per-event expected value and directional probabilities, with signal reliability weighted by market liquidity. Adds a new private-credit reference page to the knowledge base.
Every scenario now carries a calibrated confidence score, so you can see at a glance how well-supported its projections are.
The macro dashboard opens on a compact Overview tab with a richer Rates view for faster reading of the market backdrop.
Routine security patches and dependency upgrades across the production stack.
Stability improvements across the scenario generation pipeline, intelligence views, and dashboard components.
Automatically generates stress scenarios and notifies subscribers when market conditions cross configurable thresholds. Each alert includes an LLM-written cause analysis and a public share link.
New dashboard widget showing the probability of entering a stress regime over the next 21 days, conditioned on current macro covariates using time-varying transition probabilities.
Reference assets now show 90-day sparklines with labeled 1D/1W/1M performance windows. Macro indicators display native-cadence sparklines.
Scenario intelligence now pulls more relevant insights from SEC filings, with sharper relevance ranking and broader historical coverage.
Repaired dashboard widgets (media attention, earnings, commodity sparkline), resolved news-pipeline timeouts, and hardened data providers against rate-limit cascades and empty-result caching for more reliable scenario runs.
Intelligence views now include filterable tables for signals and contested claims, making it easier to drill into the evidence behind a scenario.
Scenarios that finish with empty or degraded output are persisted as failed instead of completed.
Long-running scenario pipelines no longer block fast endpoints — they execute on a separate worker process.
Secondary-shock correlations are now calibrated per regime using empirical Kendall's tau, with copula parameters surfaced in the copula table.
A new dashboard card ranks six stress themes (recession, tariff, inflation, war, uncertainty, cybersecurity) by news-volume z-score versus the trailing 90 days.
Hypothetical scenarios now generate roughly 40% faster end-to-end.
Historical scenarios now include a per-factor Market Data view with sparklines, peak/trough readings, and distribution stats for each tracked asset.
SEC filings on the scenario page now show the full detailed summary with a Show more / Show less toggle.
Expanded risk factor coverage to include international rates, emerging-market equity, additional commodities, FX, and sovereign bonds.
The Predictions tab now loads every attached market via infinite scroll, no longer capped at 30.
StressGen is in private beta. Request access to try AI-augmented stress testing and get notified about new features.