Mann: Raycast extracts LLM tool definitions directly from TypeScript JSDoc
Thomas Paul Mann · Raycast: Your AI Automation Assistant · Feb 26, 2025 · at 16:42
Raycast CEO Thomas Paul Mann explains how Raycast simplified AI tool-calling for developers by reusing familiar TypeScript code structures rather than requiring bespoke agent frameworks.
0:00 / 0:13exact quote · 13.2s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“Basically what we came up with, it's essentially you just write a TypeScript function and you document your TypeScript function with JSDoc. And then we extract all the information from there and basically make that and pass that information to the LLMs.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Thomas Paul Mann
OpenAI models remain the industry best for chained function calling
“And so we find like the open AI models function calling wise for our use case. So for the best ones and like, yeah, basically verifying the others. We had a beta group and testing different models. So basically from all providers and yeah, find basically the b…”
Mann: AI evaluations for tool calling are super unsolved across industry
“Nobody talks about how to do evals with tool calls. It's, like, a super unsolved thing.”
Raycast CEO: Incumbent operating systems are too mature to innovate
“But I can't really see that coming from the big operating systems. They're like so mature. They're like nothing moves anymore.”
Raycast built its Ray 1 models by fine-tuning GPT-4o and mini
“And so we looked into all the various models we had and then we picked, at the moment, it's gbd-for-o and gbd-for-o-mini, Which we basically did a fine tune to really optimize for our use case, and then basically shipping that in the app as Ray one and Ray one…”