Mike reports fixing his septic air pump with an $80 repair kit after considering a roughly $300 replacement. Joe walks through the podcast agent: cache the exports, review available analytics, propose focused longs and experiments, prepare a review package, then publish after approval.

Also: an HOA website waiting for a domain change, custom Slack emojis, hardware stories, and whether Claude can replace parts of a budgeting app.

This is a conversation about personal experience, not a pump repair tutorial. Costs and outcomes are Mike’s account. The production workflow still needs manual YouTube B/C setup; Spotify analytics are not yet connected despite the broader description in the conversation.

Build It Faster — season 1, episode 19.

Using Claude for home projects, Joel, Mike, and Joe discuss Home Assistant setup, self-hosting, and hands-on fault diagnosis.

Joel shares how a new home workshop changed his approach to 3D printing, why he assembled a personal radio station around his music library and cloned voice, and how Claude now handles configuration work he could do himself but does not have time for. Mike also explains how Claude helped him identify a torn diaphragm in an above-ground air pump; the repair kit still needed to be fitted at the time of recording.

They also get into:
- Three-legged versus four-legged tables
- Kids asking surprisingly difficult questions
- Proving intermittent ISP latency
- Wiring a new house for Ethernet
- Home Assistant automations and self-hosted services
- Building a neighbor’s website
- Orchestrators and a granularity gradient for software work

This is an informal project conversation, not a step-by-step repair, radio, or Home Assistant tutorial.

More Build It Faster: https://fasterpod.com

0:00 Meet Joel
9:25 A home workshop and 3D printing
18:10 Three legs, four legs, and wobbly tables
25:27 Curious kids and how things work
31:03 Candy detour
39:26 Joel FM: a personal AI radio station
42:43 Proving intermittent ISP latency
45:15 Wiring a new house
47:31 Claude for Home Assistant and self-hosting
51:19 A website for a neighbor
52:35 Diagnosing an air-pump failure
56:00 An orchestrator and a granularity gradient

Michael returns from a working road trip and catches up with Joe on a major refactor of their meeting app. They discuss separating board rules from networking and question whether peer-to-peer sync is still the right choice.

Then Michael describes how AI has changed his work as a PM: when he writes a small PR himself, when he hands a problem back to engineers, and what happened when a six-PR solution grew beyond his reach. They explore shared work with an agent in a Slack thread, time set aside to improve skills, and a customer-service lead who built a spreadsheet validation tool for her team.

The refactor and team workflows are works in progress. This conversation shares their choices and lessons, not a finished product demo or a universal process.

More Build It Faster: https://fasterpod.com

One person could not join a real session in our meeting app. Joe and Michael discuss what this means for its peer-to-peer design. They compare it with a hosted real-time service and weigh privacy against a simpler setup.

They also discuss short-lived retro boards and how they work on the project from a phone and a cloud development setup.

This is a design discussion. They have not measured a user limit or built the hosted option.

More Build It Faster: https://fasterpod.com

Claude and Codex workflows depend on more than the model: context, permissions, quotas, and the harness shape the result.

Mike, Joe, and Josh talk through a practical AI coding agent discussion: testing a new AI coding tool on Windows, deciding how much access to give an agent, how Claude and Codex handle projects differently, and why moving work between harnesses is not always seamless.

Topics include:

- AI coding agents on Windows

- Claude, Codex, and different agent harnesses

- Giving agents repo access without handing over private data

- Owning your context instead of fighting tool-specific project state

- Claude subscription limits, third-party usage, and token burn

- Why learning the harness matters before expecting the workflow to transfer

Chapters:

- 00:00 Opening

- 00:23 Combining the episode and testing an AI tool on Windows

- 11:04 The first magic and reliability gap

- 20:59 Enterprise concerns and agent permissions

- 22:25 Letting Codex work on trusted repos

- 27:33 Context windows and agent harnesses

- 34:23 Claude, subscriptions, and third-party harnesses

- 39:13 Extra usage, token burn, and safety questions

- 43:09 Owning your context

- 44:19 Moving context between different harnesses

- 50:04 Learning how each harness works

More Build It Faster: https://fasterpod.com

Mike and Joe celebrate launching their Google Meet lean coffee app, work through branding and early feedback, reduce friction in the Meet experience, assess mobile usability, and reflect on AI-assisted development patterns they want to reuse.

- 0:00 Celebrating Rapid Development

- 2:47 Exploring Branding and Domain Names

- 5:34 Feedback and User Experience

- 8:37 Mobile Experience and Usability

- 11:49 Lessons Learned from Development

- 17:38 Applying Knowledge to Future Projects

Joe preps for the AI Engineer World’s Fair, Mike and Joe review Google Marketplace rejection fixes, then Mike shares how he used Claude for a first production PR and automated his photography paperwork workflow.

- 0:00 Anticipation for the AI Engineer World's Fair Conference

- 2:53 Goals and Expectations for the Conference

- 6:06 Networking and Knowledge Acquisition Strategies

- 9:04 Exploring AI in Literature and Media

- 12:08 Preparing for Effective Networking

- 14:57 Transitioning to New Topics and Future Discussions

- 16:05 Navigating Rejection: Lessons from Google Marketplace

- 21:00 Personal Growth: Achievements in Project Management

- 33:34 Streamlining Photography: Automating the Creative Process

AI agent skills become much more useful when you treat them as context engineering, not just prompt templates.

Mike and Joe start with launch prep for Meet for Coffee, including naming cleanup, a simple homepage screenshot, support/terms polish, Terraform-managed infrastructure, and what it means to actually launch something instead of releasing it into the void.

Then Joe gives a practical walkthrough of how he is using AI agent skills at work:

- Turning repeated instructions into modular skills

- Keeping the agent instruction budget under control

- Boiling internal onboarding docs into usable agent guidance

- Converting governance processes into prepared inputs

- Using Markdown and Mermaid instead of traditional slide decks

- Planning an AI conference schedule from a sessions JSON file

- Why context engineering can matter more than perfect prompting

- How loose, natural language can help agents understand the spirit of the task

Mike and Joe also talk about AI-assisted knowledge work, clipping useful podcast segments, and the feeling of “context bending” when agents can pull, split, summarize, and apply information across repositories and workflows.

- 00:00 Meet for Coffee launch check-in

- 01:14 Homepage screenshot and product simplicity

- 04:51 Support, terms, and launch blockers

- 06:31 Terraform and infrastructure as code

- 07:31 Launch milestones and invite flow

- 10:38 Product launch, Product Hunt, and growth

- 12:17 Clipping the gold from the podcast

- 13:29 Past product launches and failures

- 16:32 Joe’s AI presentation workflow

- 22:17 What AI agent skills are for

- 26:15 Boiling governance into agent skills

- 29:31 Markdown, Mermaid, and presentation deliverables

- 36:06 Compliant inputs from repository context

- 40:21 Using AI to plan a conference schedule

- 43:34 Context engineering vs prompt engineering

- 45:00 Prompting with natural language and intent

- 52:53 AI tools changing knowledge work

- 55:41 Context bending and performance reviews

Tags: ai agents, agent skills, context engineering, prompt engineering, agentic engineering, claude skills, coding agents, ai workflow, terraform, markdown presentations, meet for coffee, build it faster