Seismic Impact (30%)
8.0/10
How newsworthy is this in AI?
Ecosystem Relevance (70%)
9.0/10
How useful for your apps?
[On agents using CLI tools in place of REST APIs] To save on context window, yes, but moreso to improve accuracy and success rate when multiple tool calls are involved, particularly when calls must be correctly chained e.g. for pagination, rate-limit backoff, and recognizing authentication failures.
Other major factor: which models can wield the skill? Using the CLI lowers the bar so cheap, fast models (gpt-5-nano, haiku-4.5) can reliably succeed. Using the raw APl is something only the costly "strong" models (gpt-5.2, opus-4.5) can manage, and it squeezes a ton of thinking/reasoning out of them, which means multiple turns/iterations, which means accumulating a ton of context, which means burning loads of expensive tokens. For one-off API requests and ad hoc usage driven by a developer, this is reasonable and even helpful, but for an autonomous agent doing repetitive work, it's a disaster.
— Jeremy Daer, 37signals
Tags: prompt-engineering, skills, generative-ai, 37-signals, ai, llms
For Zac's ecosystem, this insight is directly applicable to the orchestrator's agent design, particularly in how Claude agents like rails-expert and test-engineer interact with CLI tools across multiple Rails apps. The strategy of using CLI for more reliable, lower-context tool chaining could significantly improve the orchestrator's ability to handle complex tasks like automated testing, code generation, and deployment across the diverse suite of infrastructure and game applications.