What actually shipped in agent engineering, pulled from the labs, arXiv and Hacker News.
See who we follow →GLiNER2-PII extracts personally identifiable information across multiple languages.
GLiGuard uses schema-conditioned classification to moderate LLM-generated content.
Method corrects stochastic update bias in preconditioned language model optimizers.
Pioneer Agent continuously improves small language models deployed in production.
Framework measures proactive problem-solving capabilities in LLM agents beyond reactive behavior.
GLiNER2 performs multi-task information extraction using schema-driven interface design.
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.
