Darly Selby

Every time we try to write a case study, the biggest bottleneck is actually interviewing the internal team.

Engineers are busy fixing bugs, PMs are on to the next launch, and nobody remembers the exact metrics from months ago.

It feels like 80% of the effort goes into back-and-forth calls just trying to rebuild what actually happened before writing a single word.

How does your team capture project details early so you don't have to chase people down later?

We re giving agents access to APIs, databases, CRMs, payments and internal systems.

But something feels missing.

We can observe what an agent did.
We can evaluate whether it was right.
We can detect a policy violation.

Not a complaint about pricing. A real question I could not answer until I went looking.

The intuition is that a better model needs fewer attempts, so a job should get cheaper. My bill kept going the other way, and the price per token had gone down, not up.

The answer turned out to be in the docs. Reasoning models produce a block of internal work before they answer, and OpenAI's guide says it plainly: those tokens are "not visible via the API" but are "billed as output tokens". Anywhere from a few hundred to tens of thousands of them. Anthropic bills the same way.