Notes on grounded investing.
How we think about optimisation, tax and building an AI investing platform that you can actually audit.
Why our AI advisor cannot invent a ticker
Grounding is not a prompt trick, it is an architecture. Here is how a deterministic engine and a tightly constrained narrator make an AI investing platform you can audit.
Optimising after tax, not just before it
A rebalance that ignores tax can cost more in gains than it ever saves in risk. Here is what per-lot accounting changes on an AI investing platform built for taxable accounts.
Reading the efficient frontier
What the curve is really telling you, and why the distance from it is the number that matters most when an AI investing platform recommends a rebalance.
Strategies that watch your book
Save an investment policy once, bind it to a portfolio and get told the moment drift is worth a trade. How scheduled reviews turn an AI investing platform into an assistant.
Money is not a float
How we keep currency precise and trades atomic under concurrency, and why that correctness is the floor an AI investing platform has to stand on.
From statements to a thesis
Turning fundamentals, a discounted-cash-flow valuation and macro context into one read you can explain, on an AI investing platform that shows its sources.