See Medusa in action
Your book, the way your team sees it. Two walkthroughs: a fund's full morning on our demo book, and a deep look inside the risk engine.
A fund's morning, end to end
Seven minutes. Use the chapters to jump to any part of the morning.
One morning at Saltmarsh Capital, a demo multi-strategy book: 291 positions, five sleeves, six asset classes. A multistrat because it is the hardest book to run. Seven files land before the desk opens, from brokers, fund admin, and the risk engine, in different formats and often in disagreement. The book is reconciled and mapped to the desk's own sectors and themes before the first question is asked.
Then the morning starts: what moved, what broke, and what needs a decision? The agent writes the brief with every number cited to its source, and the dashboard shows the same two breaches. Then the decisions. What did the committee change this year, and did it add value, measured with hindsight. What would the agent change today. The final call stays with the human, by design. And every conversation is recorded, so any answer can be replayed months later, citation by citation.
Saltmarsh is a fictional fund. The market data behind it is real.
Saltmarsh's workspace points to the Factor Risk Model as its next phase. That is the second walkthrough, on our reference book.
Go inside the risk engine
The Risk Agent on a representative long/short equity book: a genuine factor model, factor attribution, and stress scenarios designed on demand. Investment risk, in the language you already use.
What the walkthrough shows
The video walks through the four things the Risk Agent does, each as a live prompt on a representative long/short equity book:
Monitor
"What are my beta risk limits, and am I complying with them?" The agent fetches the exposures, pulls the limits, flags any breach, and reasons about the implications.
Analyze
"What is the impact of closing my Apple position?" The agent runs the counterfactual, decomposes the impact across factors, and judges whether the move is risk-efficient.
Advise
"How do I reduce my Leverage factor tilt?" The agent traces the contributors, simulates trims, searches for replacements, and cross-checks every idea against the other limits.
Stress test
"Design a stress scenario for a global oil supply shock and apply it to my portfolio." The agent builds the scenario from scratch, shocks interest rates, FX, sector spreads, and volatility, and runs them against the book. Scenario design that takes a risk team a full afternoon, in under a minute.
Every number is traceable
Each answer carries citations back to the source data, and every conversation is recorded end to end: the question asked, the answer given, and every data query the agent ran in between. When an investor or a regulator asks how a number was produced, you can show them, step by step.
From the demo to your data
These walkthroughs run on representative books, not yours. The next step is the same session on your own data: we connect to your existing risk engine (MSCI, Axioma) or run Medusa's native equity risk model, and you ask the questions. Book a fit call and we will scope it.
These demos run on synthetic portfolios.
Yours runs on your books.
The risk engine walkthrough is powered by our custom equity risk model: think MSCI Barra or Axioma, built for lean teams. Saltmarsh runs on real market data with a fictional book, reconciled underneath.
Every vendor shows you their version of your portfolio. Medusa shows you yours.
On a fit call we walk through your actual stack (Excel, broker files, Axioma, legacy scripts, wherever your data lives) and scope the one workflow where a six-week pilot would prove this on your own data.
Show us your workflows, and we will build your own custom agentic system. In about a month, you will see what your team can achieve.