My Projects

These are a few notable side projects that I've worked on. If you're interested in a more comprehensive list checkout my blogs and my YouTube

Teachers Pet

teacherspet.tech (the SaaS, not main site, is down as we are considering our next steps with the project)

PAT (Personal Assistant in Teaching) is a Teachers Pet SaaS that makes it easier for Teachers to complete common workflows and cut down on repetative tasks using AI. The product allows teachers to leverage AI without prompt engineering, coding, or clunky chat threads. Some features include:
- structured rubric creation (able to directly import to Canva - no copy and paste reformatting necessary) - FAQ chatbot creation for student questions - Turn syllabus, assignments, and more into a chatbot that cites its sources -

Current the it is closed source, but I can share the arch diagram below:

Struct Strm

struct_strm (structured streamer) is a Python package that makes it easy to stream partial json generated by LLMs into valid json responses. This enables partial rendering of UI components without needing to wait for a full response, drastically reducing the time to the first word on the user's screen. Why Use Structured Streamer?

JSON format is the standard when dealing with structured responses from LLMs. In the early days of LLM structured generation we had to validate the JSON response only after the whole JSON response had been returned. Modern approaches use constrained decoding to ensure that only valid json is returned, eliminating the need for post generation validation, and allowing us to use the response imediately. However, the streamed json response is incomplete, so it can't be parsed using traditional methods. This library aims to make it easier to handle this partially generated json to provide a better end user experience. See the benchmarks section in the docs for more details about how this library can speed up your structured response processing.