Suppose an agent has been asked to buy a token, and your service can do that. How does it find out?

Not from your homepage — it cannot reliably read a JavaScript app, and marketing copy does not tell it which endpoint to call. Not from your docs site, which assumes a reader who already decided to integrate. If discovery depends on a human having read something and then written code, your service is not agent-accessible; it is human-accessible with an API attached.

An AI agent trying to use a paid API hits a wall that has nothing to do with intelligence. It cannot sign up.

Signup assumes a person: an email to confirm, a card with a billing address, sometimes a captcha or an SMS. An agent has none of that. What it can have is a wallet — and if a service is willing to be paid by wallet, the entire onboarding problem collapses into a single HTTP exchange.

From the outside, a prediction market is the same thing everywhere. You pay something under a dollar for a claim on an outcome, and if the outcome happens you collect a dollar.

The mechanics underneath are not the same, and the differences are not cosmetic — they determine what you actually own, what it costs to get in and out, and which specific things can go wrong. BT365 runs both Polymarket and Hyperliquid's HIP-4 outcome markets, so this is a comparison from having implemented against each rather than from reading their docs.

Most order-handling code is written as if there are two outcomes: the order worked, or it didn't.

There is a third, it is more common than people expect, and it is the one that actually costs money. You send an order. The connection stalls, or the venue returns a shape you don't recognise, or a gateway hands back a 502. You now do not know whether you have a position.

If you have integrated one exchange API you have integrated most of them. The signing scheme is near-universal: a key id, a secret, an HMAC over some canonical form of the request.

What varies — and what almost no documentation explains — is exactly which bytes go into the signature, what else the server checks, and in what order. Those details are the security. The HMAC is the easy part.

Most explanations of leverage stop at the point where you open one position. The interesting behaviour starts at the second one.

If you are long one market and short another and the first goes badly, what happens to the second? The answer depends entirely on whether your positions share collateral — and on a unified margin account, they do. That is the whole design, and it is rarely spelled out before you use it.

Here is a situation with no obviously right answer, which is why it is worth writing about.

You hold a position in an outcome market. It has not resolved. The venue removes the market — the event was cancelled, or the listing was migrated, or the whole set was replaced. The last price it traded at was forty cents. What is your position worth?

A token transfer on a modern chain confirms in a couple of seconds and costs a fraction of a cent. So when a platform tells you a withdrawal is "processing" for several minutes, the natural assumption is that something is stuck.

Usually nothing is stuck. The transfer really does take seconds — it is the two questions on either side of it that take the time, and both of them are questions a platform has to get right or lose your money.

Most automated trading systems keep an excellent record of what they did and no record at all of what they decided against.

That sounds like a minor omission until you try to answer a simple question about a bot that has not traded in four days: is it being patient, or is it broken? A log containing only trades gives you an empty file in both cases.

Open any prediction market with several candidates and add up the YES prices. In a market where exactly one outcome can win, those prices should sum to $1 — each YES share pays out $1 if its outcome resolves true, and precisely one of them will.

They frequently sum to $1.03. Sometimes $0.96.

That gap is not a display bug, and it is not free money either. It is worth understanding what it actually is.