Blog Research Lab AI Letters The Lab Interactive 3D

Skip to main content

EngineersOfAIPython Math for AI ML Data Eng LLMs AI Systems MLOps Agentic AI AI Engineering Break Into AI Open Source Models Hardware & Silicon Applied AI Foundational CS Code Bank

Recent Posts

2026

AI Letters #35 - Why We Built SynapseKit: The Framework We Deserve
AI Letters #34 - The 30-Day LLM Framework Verdict: 25 Benchmarks, One Clear Answer
AI Letters #33 - We Built Traceprop: Finally, an ML Audit Trail That Answers the Regulator's Question
AI Letters #32 - Your RAG Has No Immune System
AI Letters #31 - Graph Workflows: When Chains Break and DAGs Take Over
AI Letters #30 - Async Throughput: The Framework Tax on Every Concurrent Request
AI Letters #29 - Week 3 Scorecard: Six Agent Benchmarks, Three Frameworks, One Uncomfortable Truth
AI Letters #28 - Agent Error Handling: LangChain Wins on Features, But What Does It Actually Catch?
AI Letters #27 - Agent Observability: 3 Lines Gets You In, But What Can You Actually See?
I Built a Lightweight LLM Framework Because LangChain Frustrated Me - Here's What I Learned
AI Letters #26 - Multi-Agent Orchestration: 16 vs 19 vs 23 Lines (And Three Completely Different Mental Models)
SynapseKit - A Production-Grade LLM Framework Built for Speed, Simplicity, and Scale
AI Letters #25 - The Built-in Tool Race: 30 vs 29 vs 12 (And Why the Headline Number Lies)
AI Letters #24 - ReAct Agents: Six Lines vs Nineteen (And What You Lose in Between)
AI Letters #23 - The RAG Scorecard: Six Benchmarks, Three Frameworks, One Clear Pattern
AI Letters #22 - Conversation Memory in RAG: One Param vs Forty Lines of Boilerplate
AI Letters #21 - Streaming RAG: Time to First Token Across Three Frameworks
AI Letters #20 - Hybrid Search: RRF Fusion Across Three Frameworks
AI Letters #19 - The BM25 Test: One Framework Silently Fails
AI Letters #18 - The Chunking Test: Two Frameworks Are Identical, One Is Not
AI Letters #17 - The PDF Test: Which Framework Makes You Learn a New API?
AI Letters #16 - Week 1 Scorecard: Which LLM Framework Wins on Developer Experience?
AI Letters #15 - The Framework That Tells You What Went Wrong
AI Letters #14 - Switching LLM Providers Shouldn't Cost You 3 Files
AI Letters #13 - The RAM Cost of LLM Frameworks. Measured.
AI Letters #12 - How Much Code Does RAG Actually Take? We Measured.
AI Letters #11 - Dependency Hell: What Actually Installs With Each LLM Framework
AI Letters #10 - The Hidden Tax Before Your First LLM Call
AI Letters #09 - Ship It Without Breaking Things: Evals, Observability, and Production-Safe Agents
AI Letters #08 - Many Agents, One Goal: Planning, Orchestration, and Multi-Agent Systems
AI Letters #07 - Agents That Remember: Vector Memory, Episodic Recall, and the Retrieval-Augmented Agent
AI Letters #06 - Give Your Agent Hands: Tools, APIs, and the Model Context Protocol
AI Letters #05 - Build Agents, Not Chatbots: The Loop That Changes Everything
AI Letters #04 - The ML Skills That Didn’t Get Commoditized
AI Letters #03 - The Bitter Lesson, 10 Years Later
RAG was supposed to fix the hallucination problem. Here's why it got complicated.
AI Letters #01 - Why Most RAG Systems Fail in Production

Tags

A

Agentic AI5
Agents7
ai1
AI Agents5
AI Letters34
AI Systems1
ai-engineering1
Architecture1
Async1

B

Benchmarks22

C

compliance1

D

Deep Dive2
Developer Experience2

E

engineering1
evaluation1

G

Graph Workflows1

L

LLM7
LLM Engineering13
LLM Frameworks7

M

ml-engineering1

O

Open Source2

R

RAG9
research1

Learning Tracks

Python Engineering
Math for AI
Machine Learning
Data Engineering for AI
LLMs
AI Systems Design
MLOps
Agentic AI
AI Engineering
Break Into AI

Platform

Code Bank
Blog
Research Lab
AI Letters
The Lab

Community

LinkedIn
Twitter / X
GitHub
YouTube
Substack

Copyright © 2026 EngineersOfAI