Hamel Husain hamelsmu

Lightning Lesson Proposal

Debug Any AI Product in Under an Hour

Hosted by Dr. Marily Nika and Hamel Husain

45 minutes | Virtual (Zoom) | Free to join

Charlotte/Runme vs JupyterLab: Architecture Comparison

This document provides a comprehensive comparison of the Charlotte/Runme notebook architecture versus JupyterLab, analyzing their fundamental design decisions, trade-offs, and the inherent capabilities that are easier or more difficult to implement in each system.

Executive Summary

Aspect	Charlotte/Runme	JupyterLab

PRD: VibeTUI — Terminal UI for Managing Coding Agent Sessions

Introduction

VibeTUI is a terminal-based user interface (TUI) for managing multiple coding agent sessions running in tmux. It provides a unified dashboard to monitor, create, and switch between sessions running Amp, Claude Code, OpenCode, and Codex. The tool is designed for developers who run multiple AI coding agents in parallel and need visibility into what each agent is doing.

VibeTUI runs on a server accessed via SSH, displaying a two-pane interface: a collapsible sidebar showing all sessions with their status, and a main pane displaying the active agent's terminal output.

Goals

Here is the final, consolidated set of 68 flashcard ideas.

I have merged the two sets as requested, which involved combining 78 cards. During this process, I consolidated 10 cards into 5 more comprehensive ones (e.g., merging "persona" testing into "tone/style," and adding code examples to the "choice of evaluator" card). I also pruned 6 cards that were redundant (e.g., duplicate cards on "how to start" or "evals vs. QA").

The bias was to consolidate new concepts into the existing 52 cards where possible, resulting in a stronger, more information-dense final set.

{
  "flashcards": [

👋 Each week, I tackle reader questions about building product, driving growth, and accelerating your career. Annual subscribers get a free year of 15+ premium products:**Lovable, Replit, Bolt, n8n, Wispr Flow, Descript, Linear, Gamma, Superhuman, Granola, Warp, Perplexity, Raycast, Magic Patterns, Mobbin, and ChatPRD **(while supplies last).

For more:Lennybot | Lenny’s Podcast | How I AI |Lenny’s Reads | Courses

Subscribed

Hamel Husain and Shreya Shankar’s online course, AI Evals for Engineers & PMs, is the #1 highest-grossing course on Maven, and consistently brings in sizable student groups from all of the major AI labs. This is because they teach something crucial: how to build evaluations that actually improve your product, not just generate vanity dashboards.

Generating Synthetic Data for LLM Evaluation

Summary

Use your application extensively to build intuition about failure modes
Define 3-4 dimensions based on observed or anticipated failures
Create structured tuples covering your priority failure scenarios
Generate natural language queries from each tuple using a separate LLM call
Scale to more examples across your most important failure hypotheses (we suggest at least ~100)
Test and iterate on the most critical failure modes first, and generate more until you reach theoretical saturation

Question: Should I avoid using RAG for my AI application after reading that "RAG is dead" for coding agents?

Many developers are confused about when and how to use RAG after reading articles claiming "RAG is dead." Understanding what RAG actually means versus the narrow marketing definitions will help you make better architectural decisions for your AI applications.

Answer: The viral article claiming RAG is dead specifically argues against using naive vector database retrieval for autonomous coding agents, not RAG as a whole. This is a crucial distinction that many developers miss due to misleading marketing.

RAG simply means Retrieval-Augmented Generation - using retrieval to provide relevant context that improves your model's output. The core principle remains essential: your LLM needs the right context to generate accurate answers. The question isn't whether to use retrieval, but how to retrieve effectively.

For coding

	"""
	Minimal Air Framework Demo with Background Tasks and Server-Sent Events (SSE)
	"""
	import asyncio
	import random
	from typing import Dict
	import air

	app = air.Air()
	tasks: Dict[int, dict] = {}

	#!/usr/bin/env python3
	# /// script
	# requires-python = ">=3.9"
	# dependencies = [
	# "httpx",
	# "typer",
	# "rich",
	# ]
	# ///
	"""

	import json
	import os
	from getpass import getpass
	from io import StringIO

	import openai
	import opentelemetry
	import pandas as pd
	from openai import OpenAI
	from openinference.instrumentation.openai import OpenAIInstrumentor