24 September 2026
Tricorder MCP server: feedback your agent won't forget
Using Tricorder and its MCP server with coding agents.
10 September 2026
Are we formal proofs yet? On formal proofs of programs with coding agents
An experiment in constraining coding agent output with formal proofs
27 February 2025
Evaluating the evaluators: know your RAG metrics
Evaluating retrieval-augmented generation (RAG) is easier than ever, but you need to keep a close eye on the LLMs that drive the evaluation metrics. We discuss some common pitfalls and solutions.
21 May 2024
LLM-based work summaries with work-dAIgest
Do you regularly wonder where your time went during a week worth of work? We present work-dAIgest, a tool developed during Tweag's GenAI hackathon that aims to use data from standard workplace tools such as GitHub, Google Calendar, ... to create a summary of your work week (or any other time period), powered by open-source large language models (LLM).
6 February 2024
Evaluating Retrieval in RAGs: A Gentle Introduction
We introduce the many pitfalls of RAGs, including in retrieval, explain why we need systematic evaluation and provide a quick introduction to existing evaluation frameworks.