Why FFP One

Let's say you have a client call at two, and the company on the agenda is one you haven't looked at in a year. This page covers what FFP One does for an afternoon like that, how it compares with the big research platforms and with building your own, and why it costs what it does.

What does an easier day look like?

Open the company's page and click Make Memo. In under a minute you have a one- to three-page summary to read before the call.

Say the call turns up a bigger question: is a competitor's margin lead real, or a one-off? Start aResearch Report and get on with your day. It runs in the background, usually finishes within 20 minutes and almost always inside half an hour, and it leads with the answer (confirmed, refuted or reframed), then the evidence and where its figures came from.

Asked who Marvell competes with, a report took the competitor list from Marvell's own 10-K, noticed that a one-off $1.8B gain flattered Marvell's net margin, and ranked the peers on operating margin instead. That took about five minutes.

FFP One generates an analyst-grade deep-dive Research Report in minutes. You know better than anyone how long something similar takes to assemble by hand.

How does the price compare?

There are many tools on the market that do some version of what FFP One does, and some of them are very good. The established enterprise platforms charge per seat, and a seat runs $20,000 or more a year. Add a colleague and you add another seat.

FFP One has no per-seat fees. A plan buys one pool of credits for your whole firm, with unlimited users. The entry plan is $149 a month and covers four in-depth Research Reports and about nine questions a working day on Claude. The larger plans are on the pricing page.

Why not build it yourself?

You can, and it's easier than it used to be. Point a general AI assistant at a 10-K and you'll have something working by the afternoon. For one filing, that may be all you need.

Keeping it right is the harder job. Filings aren't consistent: the same figure turns up in different places and under different names from one company to the next, so a tool that works on ten of them meets surprises on the hundredth. Then it has to be kept working as models and filing formats change, and checked so that a wrong number doesn't slip through quietly.

That's the work behind FFP One's over 2,100 companies and over 5,200 funds. The text of each filing is checked against the original SEC document, every dollar figure and percentage in a summary is checked against the section it came from, and a quoted passage is matched word for word. You can read how in how FFP One works.

So the question is whether you want that to be your job. If you do, there's no better way to learn the problem. If you'd rather spend the time on your clients, that's what FFP One is for.

Where does the AI fit in?

FFP One is an AI service, and the AI is how you ask. What you're asking is the FFP One Data Layer: filings, fund holdings and prices read and organized ahead of time, so the AI looks figures up instead of recalling them. The AI is there because it makes the research easier to reach, and the research is the product.

What it won't do

FFP One is a research tool, not an adviser. It doesn't know your clients' circumstances, so it doesn't tell you what to buy. It does the reading, and the decision stays yours. Nothing it writes is investment advice.

Quarterly (10-Q) figures are on the way; today FFP One has annual reports and recent 8-K filings. Fund holdings come from each fund's latest N-PORT filing, so they're usually last quarter's.

How can it cost so much less?

So how can FFP One cost so much less than the enterprise platforms? Because it's a one-person operation. I'm deliberately bootstrapped, there's no sales team, and there are no investors demanding a massive return. I've been obsessive about cost controls, and I want to pass the savings on to you. I do make a margin, of course, but this is fundamentally about value for money. It's built and run by me, and I think we can make a fair deal together.

The system is also built so that all customers share the cost of extracting the data.

And this is a problem I like. I enjoy doing this. Let me take the hassle off your hands.

Randall Helms, founder of FFP One