Archive

Durable Agents with LangGraph and LangSmith

Part 6: State that survives crashes, approvals that expire, evaluations that gate releases, and an authenticated streaming API.

Oct 14

Durable Agents with LangGraph and LangSmith

AI Agents Course

Multi-agent orchestration with LangGraph

Part 5: Parallel specialist workers, shared state, and a reviewer that reconciles their findings.

Oct 11

Multi-agent orchestration with LangGraph

AI Agents Course

Planning and Verification Loops with LangGraph and Jev

Part 4: Plans, independent verification, stuck detection, budgets, and loops that stop when the task is done.

Oct 4

Planning and Verification Loops with LangGraph and Jev

AI Agents Course

Agent Harness with LangChain Middleware and Jev

Part 3: Retries, fallbacks, routing, guardrails, permissions, and the first human-in-the-loop interrupt.

Sep 27

Agent Harness

Run any agent harness under one interface

How UHP and HarnessRouter standardize agent execution across Codex, Claude Code, Hermes, and other runtimes.

Sep 23

Run any agent harness under one interface

Jev

Jev, Clearly Explained

We have been using LLMs like a hammer for every AI problem, even simple decisions. Jev handles those decisions in milliseconds at a fraction of the cost. Let's understand how it works and where it fits.

Sep 23

LLMs

MoE inference engineering, clearly explained

Everything you need to understand how MoE serving engines route tokens, batch expert computation, distribute weights across GPUs, and manage communication and load imbalance.

Sep 22

MoE inference engineering, clearly explained

AI Agents Course

Middleware-Driven Context Engineering in LangChain

Part 2: Dynamic prompts, memory, compression, and isolation with middleware

Sep 20

Middleware-Driven Context Engineering in LangChain