building executor.sh to connect any agent to every tool, API, and service your team uses | yc 26
We're going to look back on the amount of inference we used in 2026 as laughably small In order to properly read this article, you have to assume two things are true: The cost of inference is going to
i want to use the skills, knowledge, and apis your company has spent years developing, not your custom agent almost every company by this point has shipped an agent there's a cloudflare agent in their
mcps, apis, clis, are all ways to invoke tools, thats it the goal of this article is to help share how i think about tool calling, the different specifications, when to use each, and the underlying
mcp came out when the best models were sonnet 3.5 and GPT 4o not a lot was known about how to properly work with these tools yet, we were still incredibly concerned on models having access to tools,
LLMs are in desperate need of an execution layer made for them to run tool calls in. A year ago LLMs were making direct calls to tools, we found that it flooded their context with irrelevant
Wooof Wooof: Woo-wooof Wooooof Wo woo wooof wooooof woof woooof wooof woo woof wooooof woof wooof wooof wooof woooof woof wooof wooof wooof; wooof woooof wooof wooof wooof wooof wooof woof wooof