A hands-on test of Jev’s typed decisions, probability outputs, latency, and failure modes inside an agent-style workflow.

A hands-on experiment with MLX, three quantized Qwen models, and 24 scheduling problems — with runnable code, token traces, and measured results.

Announcing my new workshop + Special Discount for Paid Subscribers

How to design, build, and evaluate what your agent actually sees.

Four isolated coding agents, one integration failure, and a graph that retries only the branch that owns it.

Announcing my First Live Course + 20% Early Bird Discount

Testing Write, Select, Compress, and Isolate in the Claude Agent SDK Deep Search Agent

Five reliability patterns from a repository with 170K+ GitHub stars in its first week

Implementing Write, Select, Compress, and Isolate in a progressively improved technical research agent

Graph Engineering for AI Agents: When a Loop Becomes a Workflow

The Foundations of Context Engineering for AI Agents

Three practical methods: use a bounded-memory C99 engine, run a Rust full-checkpoint runtime, or reduce the model to Unsloth’s 594 GB dynamic 1-bit GGUF.

How to supervise long-running coding work with explicit contracts, verification, retries, and stopping conditions.

Learn How to Use Claude loop to automate repetitive tasks

Learn How to Use Claude loop to automate repetitive tasks

Learn How to Use Claude loop to automate repetitive tasks

A practical course on persistent agents, memory, skills, and real workflows — with 30% off during launch week + 50% off for paid subscribers

A practical course on persistent agents, memory, skills, and real workflows — with 30% off during launch week + 50% off for paid subscribers

Most AI tools wait for prompts. I tested whether MyClaw could run a recurring research workflow and send useful updates before I asked.

A practical course on persistent agents, memory, skills, and real workflows — with 30% off during launch week + 50% off for paid subscribers

How Nous Research’s Hermes Agent turns the idea of an AI assistant into a long-running agent that remembers, learns skills, and works across tools

Hands-On Hermes Agent: Persistent Agents, Memory, Skills, and Real Workflows

Hands-On Hermes Agent: Persistent Agents, Memory, Skills, and Real Workflows

Claude Loop Engineering: How to Design Agents That Iterate, Verify, and Remember

Hands-On Hermes Agent: Persistent Agents, Memory, Skills, and Real Workflows

Memory Caching gives RNNs a growing memory, offering a middle ground between efficient recurrence and expensive full attention.

Hands-On Hermes Agent: Persistent Agents, Memory, Skills, and Real Workflows

Hands on Claude Cowork - From Essintal settings to Building Workflows

Learn how to use Claude Cowork to delegate real tasks, organize files, connect your tools, and build recurring workflows that run without you.

A practical breakdown of the folders, files, and boundaries that usually appear once a Gen AI application has to survive production

Learn how to use Claude Cowork to delegate real tasks, organize files, connect your tools, and build recurrin

The 6 Claude Code Skills I Would Install First

Learn how to use Claude Cowork to delegate real tasks, organize files, connect your tools, and build recurring workflows that run without you.

Teaching MoE Models When Not to Think: A Simple Explanation of ZEDA

Get All My 7 Courses, One Button Away With 60% Off

Why HTML is becoming the better default for AI-generated reports, reviews, and working surfaces.

Learn how to use Claude Cowork to delegate real tasks, organize files, connect your tools, and build recurring workflows that run without you.

ParFraming the Problem: Why deep search matters, the limits of normal search and basic RAG, and what makes deep search different.

A GitHub repo with 100+ commands, MCP servers, plugins, workflows, and agent frameworks — all in one place.

A Practical Architecture Workshop for Planning, Tool Use, Validation, Merging