AI Agents Course
Durable Agents with LangGraph and LangSmith
Part 6: State that survives crashes, approvals that expire, evaluations that gate releases, and an authenticated streaming API.
Avi Chawla
435 posts published
AI Agents Course
Multi-agent orchestration with LangGraph
Part 5: Parallel specialist workers, shared state, and a reviewer that reconciles their findings.
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.
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.
Agent Harness
Run any agent harness under one interface
How UHP and HarnessRouter standardize agent execution across Codex, Claude Code, Hermes, and other runtimes.
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.
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.
AI Agents Course
Middleware-Driven Context Engineering in LangChain
Part 2: Dynamic prompts, memory, compression, and isolation with middleware
AI Agents Course
First Steps Towards a Production-Ready Agent with LangChain
Part 1: Tools, structured output, runtime context, and tracing, in one small agent.
LLMOps
KV Cache Engineering for LLM Serving
12 techniques to manage KV cache in production.
RAG Systems Course
Preloading Knowledge Into a Model Instead of Retrieving It (Part C)
Part 15: Block-Attention, Cartridges, and what running preloading in production actually involves, with implementations
LLMOps
KV vs Prefix vs Prompt vs Semantic Caching
...explained with best practices in production.
LLM Engineering Guides
LLM Engineering
Building real systems on top of large language models.
Agents
Grok Bot Masterclass
Everything you need to understand, set up, and get real work out of Grok Bot.
LLMOps
How a GPU Actually Works
The intuition an LLM engineer needs, without the hardware manual. By the end, techniques like quantization, speculative decoding, and continuous batching should stop looking like a list of tricks to memorize.
RAG Systems Course
Preloading Knowledge Into a Model Instead of Retrieving It (Part B)
Part 14: Shrinking a preloaded cache and the problems with those approaches, covered with implementations
LLM Engineering Guides
Continuous Batching in LLMs
The technique behind vLLM's 23x throughput jump and the default scheduler in every serving engine.
RAG Systems Course
Preloading Knowledge Into a Model Instead of Retrieving It (Part A)
Part 13: Reading the corpus once before any query arrives, and the two limitations that decide whether it works in production, with implementations
LLMOps
5 LLM Quantization Techniques
...explained visually.
Agents
Why Your Agent Remembers Everything and Understands Nothing
Building a pattern recognition layer for memory in production.
RAG Systems Course
Why RAG Latency Is a Prefill Problem, Not a Retrieval Problem
Part 12: Why prefill dominates RAG latency, and how to reuse KV caches that share no prefix, with implementations
LLMOps
6 LLM Deployment Formats in Production
...explained visually.
Agents
[Hands-on] Rebuilding Claude Code's Harness
...step-by-step, from scratch, using an open-source stack.
![[Hands-on] Rebuilding Claude Code's Harness](https://storage.ghost.io/c/3f/df/3fdf6ed2-17ac-4b12-a693-8078bd13e748/content/images/size/w400/2026/07/f3efbbc7-24b4-4c59-965d-6c3d3fc3c694_1200x1200.webp)
Reinforcement Learning Course
How do AI teams use RL in production?
RL Part 13: An exploration of real-world RL case studies.
Agents
Build Your Own 100% Local AI Second Brain
How the best builders in tech are all converging on AI second brains.
LLMs
Why Small Models Alone Don't Reduce Inference Costs
A complete guide to build production-grade SLM pipelines.
Reinforcement Learning
How to build an RL environment?
...explained step-by-step with code.
Reinforcement Learning Course
Agentic RL: Environments, Trajectories, and the Training
RL Part 12: From a single judged group to a full multi-step training loop with ART and RULER.
LLMOps
Rethinking KV Caching For Production Inference
A practitioner's guide to KV cache management in production.
Agents
How to Reduce LLM Costs by 50-60% Using Model Routing
...explained with code.
