AUTHOR

Maksim Shaposhnikov

ML Engineer at Tessl focused on AI-native development with LLMs. Previously at Amazon, built scalable multimodal, voice, NLP, and recommender systems.

Articles

Article

A Proposed Framework For Evaluating Skills [Research Eng Blog]

A new framework evaluates the impact of skills on agent performance, showing a 20% accuracy boost and cost efficiency, while highlighting evaluation challenges.

Article

A Proposed Evaluation Framework for Coding Agents: Tiles Enhance Proper Use of Public APIs by ~35%

This article proposes an evaluation framework highlighting how specifications enhance coding agents' effective use of public APIs, increasing code quality and efficiency by approximately 35% amidst evolving software interfaces.