5 posts
4 min read
Billing per message is easy and wrong: one user sends a sentence, another uploads a report. Metering the tokens you actually spend is harder, and the hard parts are idempotency, allowance checks and what to do mid-conversation.
4 min read
Most agent platforms pick one model and use it everywhere. Splitting model selection by role rather than by task is where the cost curve actually bends.
4 min read
An agent that reads your uploaded file perfectly and then forgets it on the next turn is not a memory bug. It is a context design where file content was only ever turn-transient. The fix also cuts token cost.
4 min read
Every major provider now exposes a knob for how hard the model thinks. Left at its default it burns tokens on arithmetic. Set per role, it is one of the largest cost reductions available without changing models.
4 min read
Rendering every page in a headless browser is the expensive way to import a website. Discovery through robots.txt and sitemaps costs almost nothing, and most pages never need a browser at all.