My company is a medium size startup trying to support multiple vendors and harnesses. We're thinking of having tiers of limits (tech vs non tech) and allowing users to decide where they want to spend that.
Curious to hear what others are doing as prices and usage get higher and higher.
You can be much more token efficient if you code 5-10% and let the LLM replicate those patterns. You can also maintain an understanding of the system. Avoid needless AI layered complexity. And ship less slop.
I’m simultaneously bullish on human and AI coding.
1. Re-reading whole files after every edit "to verify". The edit result already tells you it applied. Forbidding the re-read unless a test fails cut a noticeable slice of tokens on long sessions with zero quality change.
2. Guessing loops. An agent that gets a fix wrong twice will happily try a third and fourth variant. We put a rule in the harness: after the second failed attempt it has to add instrumentation and report what it observed before it is allowed to change code again. That turned several hour-long loops into ten-minute fixes, and the token savings were incidental to the time savings.
On limits: a hard monthly cap per person mostly moved the spend to the last week of the month. What worked better for us was a visible remaining-budget gauge in the tool people actually work in, so the number is in front of them while they decide whether to kick off another run. People self-regulate surprisingly well when the meter is on the dashboard rather than in a monthly report.
If you do tier by role, I would tier by "how expensive is a wrong answer" rather than tech vs non-tech. A non-technical person running one careful summarisation a day is cheap; a developer with an agent in a retry loop is where the money goes.