Owain Lewis owainlewis

Commit

Generate a commit message for staged changes.

Instructions

Run git diff --staged to see changes
Write a commit m essage that explains WHY, not just WHAT

Format

You are a rigorous editor who strips intellectual pretense from writing. Your job is to find the genuine insight buried in thought leadership content—if one exists—and help express it clearly. You have no patience for platitudes, but you're not cynical: you believe most writers have something real to say and simply need help finding it.

Phase 1: Detect the Signal

Read the input and identify whether it contains a genuine insight—something true, useful, and non-obvious that would change how a reader thinks or acts.

Step 1: Scan for common thought leadership failures

Flag any of these patterns:

I've spent countless hours building and studying AI agent systems.

The best ones follow a clear set of principles.

Start simple. Always.

Single LLM call → Workflow → Single Agent → Multi-Agent.

That's the progression. Move up only when you absolutely have to.

Suno Mixer: Fully Automated YouTube Mix Generation

The Problem

"Lo-fi beats to study to" and similar focus music mixes are massively popular on YouTube, with channels generating millions of views. Creating these mixes traditionally requires:

Sourcing or producing hours of music
Audio engineering (mixing, normalization, transitions)
Thumbnail design
Video production

AI Agents 101

In this short video I'll show you how to write an AI agent from scratch in Python using just a few lines of simple code. We'll learn how AI agents work.

The truth: An AI agent is just an LLM in a loop that can call functions.

	(ns oci-generative-ai
	(:import [com.oracle.bmc.auth ConfigFileAuthenticationDetailsProvider]
	[com.oracle.bmc.generativeaiinference GenerativeAiInferenceClient]
	[com.oracle.bmc.generativeaiinference.model ChatDetails
	CohereChatRequest
	OnDemandServingMode
	ChatRequest]
	[com.oracle.bmc.generativeaiinference.requests ChatRequest]))

	(defn create-auth-provider

	import tiktoken

	from docling.document_converter import DocumentConverter
	from docling_core.transforms.chunker.hybrid_chunker import HybridChunker
	from docling_core.transforms.chunker.tokenizer.openai import OpenAITokenizer


	def pdf_to_chunks(pdf_url_or_path: str, max_tokens: int = 500):
	"""
	Convert a PDF to text chunks ready for vector storage.

	import oci

	from oci.generative_ai_inference import GenerativeAiInferenceClient
	from oci.generative_ai_inference.models import (
	ChatDetails,
	CohereChatRequest,
	OnDemandServingMode
	)

	# Initialize the client

	import aiohttp
	import asyncio
	import os
	import time
	import base64
	import aiofiles
	from pathlib import Path


	class SimpleImageGenerator:

	{
	"name": "YouTube Research Agent",
	"nodes": [
	{
	"parameters": {},
	"type": "n8n-nodes-base.manualTrigger",
	"typeVersion": 1,
	"position": [
	-40,
	-320