Background My work with language models began years before ChatGPT's public release in late 2022. As an early user of OpenAI's APIs, I built prototypes for agentic conversational systems before today's abstractions and terminology became standard. These systems included schema-constrained JSON generation, reasoning

Overview Humans communicate in different ways about the same concepts. They bring their own terminology, phrasing, and context when interacting with an agent. In this post, we explore how LLM-based workflows can improve an agent's ability to identify, clarify, and interpret user intent in the context of

Overview When working with a few customers, we wanted to identify simpler ways of interacting with SalesForce objects on the go for a few operational personas such as the Sales Lead, and the Operator. We designed a solution that would (hopefully) reduce the each persona's operational surface area

Large Language Models (LLMs) have introduced a variety of vulnerabilities into traditional business processes. The technology acceleration occurring within the AI-space lends itself to the creation of a variety of competing solutions looking for an edge on cost, quality, and features, sometimes, at the expense of security. Today, we

Overview We're leveraging protobufs (gRPC) to optimize the way we communicate across services with oof.gg. As a result, we wanted to leverage the benefits of this strong typing and compression within our ReactJS web application. A drawback of using gRPC natively for web applications is its lack

When you think of agents, you may think of highly flexible and dynamic agents that can respond to your communication, and reason over your answers. People today are using Large Language Models (LLMs) and agents to solve a variety of complex reasoning problems. But what if you need an agent

Github Copilot, a qualitative review: Here, we analyze the overall usefulness of Copilot (via GPT4o, o1) as an assistant in your workspace.

While using Structured Outputs (with "strict mode" enabled), their latest model (gpt-4o-2024-08-06) scores a perfect 100% reliability on their internal evals. This feature aims to enhance the accuracy of generated outputs to match specified schemas. Diving deeper, there are caveats, such as having some