A detailed summary of a workshop on building and deploying production-minded AI coding agents using Dagger. The session covers creating controlled, observable, and test-driven agent workflows and integrating them into CI/CD systems like GitHub Actions for automated, reliable software development.
VCs Dani Grant and Chelcie Taylor provide a tactical playbook for AI engineers on raising their first round of funding. They cover when to raise, how to write effective cold emails, what to focus on in a pitch (vision over tech), how to answer key questions about competitors and go-to-market, and the dynamics of a successful investor meeting.
Traditional benchmarks and leaderboards are insufficient for production AI. This summary details a practical, multi-layered evaluation strategy, moving from foundational system performance to factual accuracy and finally to safety and bias, using open-source tools like GuideLLM, lm-eval-harness, and Promptfoo.
Madhavan Ramanujam, a leading expert on monetization, shares a framework for pricing and scaling AI products. He discusses why AI companies can capture 25-50% of the value they create, how to choose the optimal pricing model using a 2x2 of attribution and autonomy, and provides advanced tactics for negotiation and reframing POCs as business case creation.
Philipp Krenn from Elastic demystifies the 'R' in RAG, arguing that modern retrieval is a sophisticated blend of classic keyword search (like BM25) and modern vector search. This workshop explores the fundamentals of lexical analysis, scoring, dense/sparse vectors, and advanced hybrid search techniques like Reciprocal Rank Fusion (RRF).
A deep dive into SGLang, an open-source serving framework for LLMs. This summary covers its core features, history, performance optimization techniques like CUDA Graph and Eagle 3 speculative decoding, and how to contribute to the project.