The Good Stuff

Good Stuff Episode 28Pete and Andy reunite in person at City Beach to explore how AI agents are can give individuals the power to solve their own problems. From Wingman V2's evolution to the resurrection of pre-digital work practices, they discuss why treating agents like employees with their own computers might be the key to unlocking practical AI leverage without the complexity of SaaS abstractions.0:00 Back in the van at City Beach, Perth - discussing grass, beaches, and jet lag after Madeira 2:55 Kicking off with Wingman V2 development and the importance of reading skills documentation 5:02 What is Wingman? The TLDR for new listeners on agent orchestration software 9:05 Anthropic releases Claude Code on mobile - perfect timing for Wingman's approach 10:19 The lobotomization problem and why model flexibility matters for production systems 13:29 Building processes with agents: triggers, workflows, and file-based conventions 16:12 File watchers and convention-based programming for agent coordination 18:44 The challenge of selling Wingman vs. using it to run businesses directly 21:08 Why agents are like employees: managing workload across multiple direct reports 23:30 The cloud vs. on-premises debate: putting computers in businesses, not businesses in computers 25:42 Staying involved in the process to maintain intuition and avoid costly mistakes 27:52 The last mile problem: getting from 95% to production-ready 30:09 Small vibes, many courses: iterative development with constant testing and commits 31:38 The shift from resource allocation to rapid experimentation in enterprise 34:17 Why outsourced consulting models struggle with agent-driven development 37:20 Multi-user Wingman: the philosophical question of shared vs. individual agents 39:53 Using Nostr keys for identity management in small business tools 42:10 Building Good Stuff with just two people and AI leverage 44:45 The importance of developer logs, security reviews, and daily highlight reports 48:49 Relearning structured work practices from the pre-digital era 52:07 Building Pontefex: a visual interface bridge for Claude Code web development 54:37 Why clipboard-based workflows beat complex integrations 56:07 The Excel principle: empowering people to solve their own problems with tools

The Good Stuff, with Pete and Andy - Episode 27: Lessons LearnedHosts: Pete and AndyEpisode Overview: Pete and Andy reflect on lessons learned from months of experimentation with AI agents, coding tools, and building software. They discuss the shift from "vibe coding" to more structured approaches, the importance of shipping usable tools, and their plans for a multiplayer version of Wingman.Key Discussion Points:Side Quests and Experimentation (01:16-08:30)Andy builds a habit tracker that evolved into a doom-scrolling prevention appPete experiments with media over QUIC and real-time streaming protocolsThe power of AI to remove gatekeeping from learning new technologiesBuilding an Nostr-based virtual pub with spatial audioVibe Coding vs. Slow Coding (09:38-16:13)Insights from working with serious engineers on AI-assisted developmentEveryone uses AI differently - no single "vibe coding" workflowThe importance of understanding your codebase architectureMoving slower to go faster: maintaining intuition while delegating implementationBuild vs. Buy: The Shopify Question (14:25-25:06)Andy's journey building an e-commerce site from scratch instead of using ShopifyThe value of understanding how things work vs. convenience of platformsLocalization of software development - kids will build these things nativelySelf-reliance as a valuable use of AI-gifted timeShipping Tools People Can Use (25:06-33:00)The critical lesson: put working demos in users' handsPlans for multiplayer Wingman to lower barriers to experimentationDesigning the business into Wingman - mapping workflows and agentsTesting at Bush Bash with live coding sessionsOrchestrators vs. Deterministic Processes (33:00-38:52)Why probabilistic orchestrator agents often fail in productionThe case for simple, deterministic workflow rulesLeft curve vs. mid curve: sometimes simpler is betterHumans should still design the business processesRate Limits and Model Selection (38:52-42:43)Claude Haiku as a solution to usage limitsRunning agents via API for unlimited usageMultiplayer mode for sharing subscriptions efficientlyThe challenge of making complex technology accessibleSimplifying the Message (42:43-48:31)Beacon demo: focus on the "moment of magic" not the complexity"Solvatur Ambulando" - solve it by walking aroundWingman's unique value: anywhere access + multiplayer agentsDon't let ego get in the way of clear communicationAI Agents Playing Games (48:31-59:09)Using game environments to test model performance for business applicationsGames as sandboxes for learning resource allocation and strategic thinkingBeyond single-agent approaches: teams of specialized agentsGeneral Catalyst's investment in gaming arenas for model testingMultiple Minds Per Task (55:13-01:01:38)Humans have multiple personalities for different contextsAgents may need similar specialization to avoid being overwhelmedFile-based handoffs between agents as a clean interfaceThe power of forcing agents to document their reasoning"Mid curve me is just like 'oh I've been so clever' - but that's not for the person on the other end that wants to look at it."

The Good Stuff, with Pete and Andy - Episode 26: Beyond CodingHosts: Pete and AndyEpisode Overview: Pete wraps up Sovereign Engineering's final week while Andy discovers Claude Code's surprising versatility beyond coding. The hosts explore multi-agent orchestration, Nostr ecosystem developments, and the expanding use cases for AI agents in everyday business tasks.Key Discussion Points:Claude Code for Non-Coding Applications (01:30-08:00)Andy shares his revelation about Claude Code's effectiveness beyond programming tasks, including organizing financial records, preparing taxes, and restructuring Apple Notes into Obsidian. The tool excelled at extracting action items from scattered notes and even analyzed a 100-page DNA report to create a personalized diet plan. Discussion of why Claude Code feels more capable than Claude Desktop for complex tasks, potentially due to different system prompts optimizing for autonomous operation versus interactive sessions.Multi-Agent Architecture and Wingman (08:00-12:00)Pete describes building agent orchestration systems where Wingman calls other specialized agents through local APIs. Beacon now integrates Wingman for complex research tasks, automatically determining when to use web search or other tools. The vision includes abstracting recipes and MCP servers to switch between Claude Code, Codex, Goose, and Gemini based on task requirements.AI for Content Optimization (12:00-16:00)Andy experiments with using Claude Code to analyze podcast YouTube data, discovering which thumbnail text styles drive better click-through rates. YouTube's built-in A/B testing capabilities for thumbnails revealed. Discussion of the resistance to over-optimizing content for platforms like LinkedIn versus the authentic engagement on Nostr.Nostr vs. Traditional Social Media (16:00-19:00)Pete's viral post on Primal contrasts with the performative nature of LinkedIn. Both hosts appreciate Nostr's ability to provide meaningful content without the dopamine-driven engagement loops of traditional platforms. The five-minute check-in versus the endless scroll.Sovereign Engineering Demo Day Prep (19:00-31:00)Pete showcases progress on WhatsApp Bitcoin integration with Lightning payments, emphasizing the "hook" of seamless crypto in mainstream messaging. Rebuilt gateway architecture to support multiple networks. Tired on the Field game adds skydiving cows, laser eyes, and Nostr login for persistent leaderboards. Other notable demos include Context VM servers, Gigi's Amps semantic search, local-first relay architecture, DNS alternatives using public key infrastructure, and BitChat's offline Bluetooth mesh for protest coordination.Andy's Project Portfolio (31:30-38:00)Building Supply Drop, a standalone e-commerce brand using Shopify with third-party manufacturing APIs. Developing a podcast knowledge graph with Neo4j to track recurring themes and philosophical evolution across episodes, aiming to create an interactive agent for exploring the show's intellectual journey. Designing a minimalist habit tracker app that locks users into one habit for 21 days before allowing additional habits, incorporating AI accountability coaching.Future Direction (38:00-39:00)Plans for workshops on both coding and non-coding agent applications when Pete returns to Perth. Recognition that agent capabilities are poorly understood despite their power across diverse use cases.

The Good Stuff, with Pete and Andy - Episode 25: Freedom Tech & The Beacon ProjectHosts: Pete and AndyEpisode Overview: Pete and Andy reflect on their Jeff Booth conversation, exploring contradictions in AI-debt narratives. Pete unveils major progress on Beacon, his freedom tech project bringing internet access and Bitcoin payments to constrained environments via WhatsApp. The hosts debate AI coding tool frustrations and the shifting development landscape.Key Discussion Points:AI, Productivity, and the National Debt Paradox (01:35-09:55)Examining flawed logic that AI productivity gains will solve government debt. The hosts argue this ignores job displacement and debt repayment mechanics through taxation. If AI eliminates jobs while boosting productivity, governments lose salary tax revenue - accelerating wealth concentration and triggering more money printing.Gold Manipulation vs Bitcoin's Transparent Ledger (14:46-21:42)Gold price suppression through derivatives and lack of auditing contrasted with Bitcoin's audit every 10 minutes. The importance of self-custody to prevent paper Bitcoin markets. "If we all fully reserve our Bitcoin, then there will be no paper Bitcoin for these guys to trade."Bitcoin in Madeira and Nostr's Permissionless Payments (21:42-29:30)Pete shares observations from Madeira where Bitcoin acceptance has normalized. The revelation of Nostr's permissionless payments - sending value instantly without intermediaries. Andy's realization: traditional money transfers require multiple friction points; Nostr enables instant zaps.The Beacon Project: Internet Access via WhatsApp (29:30-47:10)Pete introduces Beacon for environments with no smartphones or reliable internet - only text-based WhatsApp. Beacon enables AI queries, research, and Bitcoin payments through text messages. Origin story from Togo, where internet costs were prohibitive but WhatsApp was free. The vision: delivering the entire internet via text messages to people without internet access.Beacon's Trust Architecture (47:10-58:02)Deep dive into Beacon V5 design separating identity from AI services. Two independent providers create a trust model where neither can unilaterally defraud users. Uses Context VM over Nostr for discovery and communication, eliminating firewall complexities. Challenges the custodial vs self-custodial dichotomy, creating middle-ground trust models where full self-custody isn't practical.AI Development Tool Chaos (58:02-01:12:23)Frustrations with Claude Sonnet 4.5's rate limits and inconsistent performance. Andy hits weekly limits after one day. Pete's migration to Codex and Goose, finding better consistency. The problem: opacity in which components change makes debugging impossible.Notable Quote:"Bitcoin audits the entire world supply every 10 minutes - like melting down all the gold in the world repeatedly to make sure it's legit."

In this engaging conversation, Jeff Booth, an author and entrepreneur focused on technology and Bitcoin, delves into the transformative power of Bitcoin and the role of agency in shaping reality. He emphasizes how our beliefs influence experiences and highlights Bitcoin’s potential for value creation in a deflationary market. Jeff discusses the impact of AI on productivity, contrasting zero-sum thinking with an infinite mindset. As he shares personal journeys toward Bitcoin, he emphasizes the importance of making conscious choices in a rapidly changing world.

Explore the fascinating challenges of AI reliability and why many pilots falter. Discover the innovative Nostra protocol and its role in decentralized applications, boosting security and identity portability. Get insights into the struggling Claude Code and the bugs affecting its performance. Uncover the debate between bionic augmentation versus human-at-the-edge AI. Plus, learn about creative solutions for building effective AI integrations in business, focusing on minimalistic architectures and practical takeaways.

Exploring the scenic streets of Madeira, the hosts dive into the seamless adoption of Bitcoin among local merchants, challenging centralized finance. They discuss the evolution of eCash and how AI is revolutionizing online services, making payments more accessible. With a vision for a permissionless internet, they highlight Nostr’s role in fostering decentralized communities. The conversation also touches on using AI for business transformation and creating tools that simplify user interactions without ideological barriers.

Pete and Andy dive into the fascinating world of remote vibe coding, showcasing how geographic separation can enhance AI development. They introduce an innovative trigger system that automates tasks overnight while utilizing the quirky 'Grug Brain Developer' principles for security audits. The duo explores the dual-agent approach—Claude Code as the rapid coder and Goose as the thoughtful planner. They also tackle the limits of chat interfaces for documentation, advocating for structured note-taking to enhance discoverability. Tune in for a blend of tech insights and playful banter!

Discover the revolutionary AI orchestration system called Wingman, designed to streamline project management and enhance productivity. Explore how dedicated environments for AI agents transform workflows, making tasks more efficient and secure. Dive into the economic challenges of software subscriptions versus custom solutions. Uncover the exciting potential of AI in gaming, from enhancing player interactions to innovative gameplay dynamics. Join the conversation on balancing aesthetics and functionality in design, while navigating the complexities of modern software development.

In a riveting discussion, Bethan Winn, author of "The Human Edge" and corporate training expert, delves into critical thinking in the age of AI. She explores the balancing act between leveraging AI tools and preserving human creativity. Listeners will discover her insights on the writing journey, the concept of 'AI veganism,' and the collaborative potential of AI in creative processes. Bethan emphasizes the importance of questioning AI outputs and the need for personal judgment, making a compelling case for the human edge in an increasingly automated world.