Plum AI evaluates and improves the quality of LLM applications

Analysis

DeepSeek R1 analysis: open source model has propaganda supporting its “motherland” baked in at every level

DeepSeek R1: Open-weights, Hidden bias - part 1

Blog posts

How often are your LLM agents doing what they’re supposed to?

Getting the most out of agentic workflows

Introduction to Fine-Tuning

Supervised Fine-Tuning (SFT)

Introduction to Soft Prompting

Model Distillation

Plum AI Analyzes and Boosts LLM Quality Dramatically with Limited Training Data: A Case Study

Plum AI Documentation

API documentation for getplum.ai

Contact us

Email