In the LLM era, building a brand-new DSL feels unnecessary. DSLs used to make sense because they gave you a compact, domain-specific syntax that simple parsers could handle. But modern language models can already read, write, and explain mainstream languages effortlessly, and the tooling around those languages—REPLs, compilers, debuggers, libraries—is miles ahead of anything you’d roll on your own. So rather than inventing yet another mini-language, just leverage a well-established one and let the LLM (plus its mature ecosystem) do the heavy lifting.
I have a similar idea; it essentially instructs the LLMs on how to use the URLs of a site. Here is an example of guiding LLMs on how to embed a site that contains TradingView widgets.
We think here's how it may work from a triple-win perspective:
1. Users care about the outcome and enriched user experiences without needing to learn how to use the app first. So, cut to the chase.
2. Third-party app providers want their data protected and not leaked to LLM providers. Most importantly, it provides a way to convert traffic to their own sites, similar to what they expect from a search engine, rather than being replaced by a feature of an LLM-based app.
3. LLM-based platforms require little effort to support this and can monetize by replicating traditional methods of recommending and advertising apps.