Overview

Interfaces are fully hackable, which you can use to build personalized pipelines for: logging, evaluations, guardrails, human labelling, agentic workflows, self-optimization, and more.

simply unify.log your data, and then compose your own custom interface using the three core building blocks: (1) tables, (2) plots and (3) views.

Despite the explosion of LLM tools, many of these are inflexible, overly abstracted, and complex to navigate.

Tooling requirements constantly change across projects, across teams, and across time. We’ve therefore made Unify as simple, modular and hackable as possible, so you can spin up and iterate on the exact AI platform that you need, in seconds ⚡

Rather than going through each concept in detail, we explain interfaces through a simple case study, where we’re building an education app for students.

This single case study walks through the use of logging, evaluating and debugging the LLM application. This is by no means an exhaustive list (you can build an interface for pretty much anything), but it should give you an idea of how flexible and hackable interfaces are 🛠️

Head over to the next page to dive in! ➡️