A hosted computation engine that turns investment theses into computed, auditable research objects — with structured output any surface can consume. Your Cursor skill calls it. Your Excel model calls it. Your portfolio management agent calls it. Same endpoint, same math, same methodology.
Start with six free analytical workflows. Upgrade to computed infrastructure when you need real math.
Free skills work with Cursor, Claude Code, OpenClaw, and Cowork. The Engine API works with anything.
Citadel, Balyasny, and Point72 have deployed AI research assistants that compress weeks of analyst work into minutes. Their edge isn't the model — it's the structured workflows, data plumbing, and quality governance underneath.
You need the same throughput. You don't have the same headcount.
Each workflow encodes institutional best practices into a repeatable decision framework. Free, open-source, and ready to use in your IDE today.
Go from a macro thesis to a ranked list of investable names in minutes — with the non-obvious second and third-order plays most screens miss.
See example outputProduce an IC-ready memo that argues a position, not just describes a company. Variant perception, key drivers, valuation, risks — done in one pass.
See example outputKnow the 25 hardest questions before you walk into the room. Pre-built answers, supporting evidence, and clear red lines for each.
See example outputSee every event that could move your position — with asymmetry analysis that tells you which catalysts are worth trading around.
See example outputFind out whether rates, credit, FX, commodities, and vol agree with your thesis — or are quietly contradicting it.
See example outputKnow your upside, downside, and exactly where the thesis breaks. Probability-weighted returns with sensitivity tables and decision triggers.
See example outputThe Engine is a hosted computation API that takes investment context and returns computed, auditable analytical objects. Any client can call it — your IDE, your spreadsheet, your agent, your application. Same endpoint, same structured output.
Sensitivity grids calculated from valuation models, not guessed by an LLM. Monte Carlo across 1,000 iterations. Every formula, every assumption, every derivation visible in the response. You see exactly where your thesis breaks — and so does your PM.
The same computation endpoint serves a Cursor skill, an Excel add-in, a web dashboard, or another AI agent. The engine doesn't know or care what's calling it. Your output schema is portable: trivially mappable to an Excel range, a chart, a JSON payload, or a markdown table.
A portfolio management agent calls Scenario Analysis to validate a thesis before executing. A robo-advisor calls Investment Memo to generate client research. A compliance agent calls Cross-Asset Signals to flag inconsistencies. The Engine is analytical infrastructure, not a CLI tool.
The Engine launches in Q2 2026. Join the waitlist for early access and launch pricing.
We work directly with mid-sized investment firms to integrate custom AI workflows into daily research operations — tailored to your process, your data, and your team. Your analysts cover more names. Your research process becomes repeatable.
We run the system on your coverage universe, map your research workflow, identify bottlenecks, and deliver a concrete implementation roadmap. You keep everything — whether or not you go further.
Production research flows tailored to your process, wired to your data, embedded in your daily tools, with a firm-specific quality evaluation suite and ops runbook.
Start getting value immediately with the free skills and public data. Connect your licensed research, internal KPIs, or portfolio data through the Engine — and the same workflows produce materially sharper output.
Public filings and AI estimates. Every estimate flagged for verification. Structured, useful, ready to build on.
Your licensed data, internal metrics, and proprietary signals. Institutional-grade, differentiated output that reflects what you actually know.
Built on the Model Context Protocol (MCP). FRED macro data is active and free. Paid providers (FactSet, S&P Global, PitchBook, Morningstar, etc.) plug in via your existing API keys. Your data stays local — nothing leaves your environment unless you send it to the Engine API.
Anyone who needs structured investment analysis — human or machine. The free skills work for individual analysts in any supported IDE. The Engine API serves analysts, fund teams, fintechs building with investment analysis, and AI agents that need computed analytical output as a building block.
No. The skills run on whatever LLM your IDE provides. No additional API keys, no account required.
Yes. The Engine is a standard REST API that accepts JSON and returns structured JSON. Any client that can make an HTTP request can call it — IDE skill, Excel add-in, web app, another AI agent, or a raw API consumer. Bearer token auth, self-contained inputs, no session state.
The free skills produce structured markdown with estimated numbers. The Engine computes real sensitivity grids, runs Monte Carlo simulations, and returns structured JSON with full computation methodology — every formula, assumption, and derivation exposed. The skills are the methodology. The Engine is the math.
ChatGPT and Claude are general-purpose models. Investment Intelligence is investment analytical infrastructure — structured computation that returns auditable, portable, agent-callable analytical objects. The difference is the same as between a blank spreadsheet and a fully built financial model, except this one has an API.
The free skills run entirely locally in your IDE. The Engine API processes inputs server-side — we do not train on your data, and all data is encrypted in transit and at rest.