Stop Rationing Tokens: Let the Harness Pick the Model — Kimchi by Cast AI
Source
youtube.com
Author
AI Engineer
Date
Context
Kimchi's proposed unit of optimization is the completed coding task. In the company's conference presentation, Cast AI describes software that coordinates coding agents and chooses models according to task outcomes. That moves model selection into the system running the work, where it can be assessed against what the task costs to complete.
The product page says Kimchi brings multiple models together to plan, build and review code, matching each step to a model. The useful idea is to evaluate model choice across those steps, rather than treating the price of each unit of generated text as the whole cost comparison.
Key takeaways · AI-distilled
Cast AI built its own open-source coding agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition →, Kimchi, after its coding-AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → bill took off, and argues that limiting tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → cripples developers.
The harness chooses a proprietary or open model per task based on outcomes and switches automatically as new models ship; the talk presents three months of internal results from 300 employees.
Ferment runs milestone-based, self-scoring autonomous coding tasks for hours and deploys to staging. Teleport keeps agent sessions running in remote sandboxes after you close your laptop, and Studio adds a shared Kanban board for teams.
Terms in this piece · Glossary
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.