Using Claude Code: Session Management & 1M Context
Harness, Memory, Context Fragments, & the Bitter Lesson
this is a work in progress mental dump on interesting intersections between how we use and design a harness, implications for memory being accumulated over long timescales, and the search bitter lesson we can’t escape
this
Your harness, your memory
Latent Briefing: Efficient Memory Sharing for Multi-Agent Systems via KV Cache Compaction
The New Software: CLI, Skills & Vertical Models
Anthropic sees the moat. Do you?
You Don't Know LLM Training: Principles, Pipelines, and New Practices
The golden rules of agent-first product engineering
Impeccable: Design skills for AI harnesses
1 skill, 20 commands, and curated anti-patterns for impeccable frontend design.
Spec-Driven Development – Adoption at Enterprise Scale
Spec‑Driven Development helps align intent between humans and AI, but enterprise adoption requires cultural change, workflow integration, and scalable collaboration patterns.
Trace learning for self-improving agents
Skill chaining and why skills should be actions
Multimodal Embeddings and RAG: A Practical Guide | Weaviate
Multimodal embeddings allow AI systems to search and reason across text, images, audio, and video in their native formats. This blog covers the key intuitions behind how this all works and walks through three practical implementations using Weaviate and Gemini.
i studied the architecture of claude code so u dont have to
From Hierarchy to Intelligence
Building CLI app for AI and Agents
How To Solve Problems Of Long Running, Autonomous Agentic Engineering Workflows
The law firm model for software developers and agencies
The Harness Is The Product. The Model Never Was
seedance 2.0 can change your life, here's the complete guide
shanraisshan/claude-code-best-practice: practice made claude perfect
practice made claude perfect
The Complete Boris Cherny Claude Code Skill Changes How You Build Software
How we build evals for Deep Agents
The Architect's Playbook.pdf
anthropics/claude-cookbooks: A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude. - anthropics/claude-cookbooks
kubernetes-sigs/agent-sandbox: agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes. - kubernetes-sigs/agent-sandbox
You Don't Know AI Agents: Principles, Architecture, and Engineering Practices
Anatomy of the .claude/ folder
How to Become a Claude Architect in 6 Months (Full course)
How Steering Hooks Achieved 100% Agent Accuracy Where Prompts and Workflows Failed
Steering hooks achieved a 100% accuracy pass rate across 600 evaluation runs, compared to 82.5% for simple prompt-based instructions and 80.8% for graph-based workflows.