§ 01 / Writing · 5 dispatches
Writing.
Long-form notes on the systems I work in — agents, retrieval, and the cloud-native plumbing underneath. Half technical autopsy, half field journal.
- № 0110 min read
How We Evaluate Our Agentic Systems: Evals, Evalite, and Humans in the Loop
Shipping a multi-agent system on vibes is a great way to break production. Here's how we made a probabilistic analytics agent measurable — with Evalite, layered scorers, and human review that actually feeds back into the loop.
AIEvalsAgentic AIEvaliteRead → - № 028 min read
The AI World Just Had Its Wildest Month — Here's Everything You Missed
From trillion-dollar mergers and AI models that outperform engineers, to Disney characters in AI generators and deepfake scandals — a complete roundup of the biggest AI news from the last few weeks.
AIMachine LearningIndustry NewsClaudeRead → - № 039 min read
Claude Agent Skills: What They Are, Why They Matter, and How to Build Your Own
A deep dive into Anthropic's Agent Skills — the open standard that turns general-purpose AI agents into specialized experts. Learn the architecture, the spec, and how to create your own skills.
AIClaudeAnthropicAgent SkillsRead → - № 047 min read
Mastering Clawdbot: 5 Power Tips to Supercharge Your AI Assistant
Transform your Clawdbot from a simple chatbot into a proactive AI employee. Learn advanced memory optimization, multi-model workflows, and automation techniques.
AIClawdbotOpenClawProductivityRead → - № 056 min read
Building a Graphiti Knowledge Base with Python
Learn how to build a graph-based RAG system using Graphiti and Python for smarter retrieval and richer context in your AI applications.
PythonRAGKnowledge GraphGraphitiRead →