Workflow Automation
271 episodes · Page 2 of 12
#5573: Audio Post-Processing for AI Podcast Pipelines
Silence trimming, loudness normalization, EQ, and tempo fixes — the CLI tools that turn raw TTS output into a finished episode.
#5565: Inside the Factory: Why Plant Tours Are Addictive
Boeing, Ford, and Shenzhen's Future Factory: why watching a bottling line is mesmerizing, and where to find real golden tickets.
#5536: Staging Environments for Blog Posts and AI Pipelines That's 54 characters. This captures both the content workflow angle and the AI pipeline angle. Good.
Content teams are reinventing staging, draft states, and version history on their own — and AI pipelines are adding autonomous review stages betwee...
#5505: Send a Bot to Your Next Sales Call
Daniel wants a bot that takes his sales meetings, asks hard questions, and ends the call when the pitch is spray-and-pray.
#5469: Open Source's New Map: India, Croatia, Ethiopia
One in three new GitHub developers now comes from a country outside 2020's top ten. What that shift means for open source.
#5467: Small Models, Big Schemas: When JSON Constraints Backfire
Small models plus strict JSON schemas should be a safe bet. A 15,000-generation study found the opposite.
#5465: Packaging AI Pipelines So They Actually Get Reused
Daniel's podcast pipeline works — so why can't he reuse it? Recipes, containers, and Hebrew code-switching TTS.
#5459: Rebuilding the Podcast: Turn-Taking, Buttons, and Chatterbox
Daniel wants a push-to-interrupt button and a live voice loop. The research says the button is easy and the live part is a research project.
#5455: Custom GPTs Are Sunsetting: What Happens to Your Actions
OpenAI is retiring Custom GPTs — and custom Actions don't survive the migration. What that means for your workflow.
#5399: Who's Actually Behind the AI? Fauxtomation Explained
Amazon's Just Walk Out needed 1,000 workers in India. Google Duplex, Facebook M — the pattern of selling humans as software goes deep.
#5390: Chaining Small Models for Dictation Cleanup
Daniel's Android dictation fork won't render "three point five" as a decimal. How many models does cleanup actually need?
#5389: Hugging Face vs Kaggle: Where Models Actually Live
Hugging Face and Kaggle aren't rivals — one is infrastructure, one is a practice field. Here's how the two platforms actually differ.
#5355: Why AI Emails Don't Sound Like You
ChatGPT's Gmail integration can now send email for you. The hard part is making it sound like you — not a committee-written average.
#5374: Why Trades Still Say Apprentice, Journeyman, Master
A papyrus contract from 18 BC, a five-euro coin, and the German Walz — how one medieval ladder survived only in the licensed trades.
#5312: Fighting Fake-Personalized Spam With AI Sinkholes
Scraped flattery, fake familiarity, and the one-sided ask — plus the tarpit history behind Daniel's sinkhole agent idea.
#5277: AI Handles the GTD Inbox So You Don't Have To
GTD says capture everything — then caps your inbox at 100 items. What if AI did the organizing layer instead?
#5206: Why IKEA Has No Replacement-Parts API
IKEA's catalog is community reverse-engineering. GS1 solved replacement semantics years ago. Neither reaches a purchasing manager's database.
#5178: Who Checks on Empty Houses — And What It Costs
Absentee owners pay a stranger to flush the toilets and photograph the water heater. The whole industry runs on trust — and a written report.
#5111: The Quiet Appeal of Industrial-Grade Stuff
Why do some people get genuinely excited about a heavy-duty bin? The strange, satisfying world of spec-driven purchasing.
#5078: When Shopping Lists Outgrow the Grocery Store
Why grocery list apps fail when you need drywall anchors, and what actually works for multi-store household shopping.
#5055: The Invisible Machinery of Autonomous Agents
Heartbeats, state stores, and budget caps — the unglamorous infrastructure that actually makes always-on AI agents work.
#5014: PWA vs Native: One Developer's Home Inventory Dilemma
PWAs cover 80% of use cases. What's the cost of the last 20%?
#4991: Self-Healing Codebases: Can AI Fix Bugs Autonomously?
How far are we from AI systems that fix their own bugs without human intervention? The answer might surprise you.
#4976: Building a Procurement Agent That Actually Works
How to encode the weird, undocumented skills technical buyers use every day into an AI agent that won't get you audited.