The Good Stuff 27: Lessons Learned with AI Agents

Oct 16, 2025

Pete and Andy dive into their hands-on experiments with AI agents and coding tools. Andy's transformation of a habit tracker into a doom-scrolling prevention app highlights rapid innovation. They explore how AI dismantles barriers to learning complex technologies and the transition from vibe coding to methodical approaches for improved software architecture. Andy shares his choice to build an e-commerce platform from scratch for deeper insights. The duo emphasizes the significance of shipping usable demos and plans for a multiplayer version of Wingman.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

ANECDOTE

From Habit Tracker To Doom-Scroll Blocker

Andy built a habit-tracker that morphed into a doom-scrolling prevention app he uses on his phone.
He explores iOS development and experiments quickly by generating code with AI to iterate and break the app himself.

INSIGHT

AI Dismantles Gatekeeping

AI removes gatekeeping and makes complex technologies approachable for beginners.
Pete observed he can now try unfamiliar stacks and compile Rust with AI guidance rather than being blocked by hostile community responses.

INSIGHT

No Single Vibe Coding Workflow

Every engineer used AI differently; there is no single 'vibe coding' workflow.
Most agreed they'll never stop using AI in daily coding, though their personal workflows vary widely.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

The Good Stuff, with Pete and Andy - Episode 27: Lessons Learned

Hosts: Pete and Andy

Episode 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 app
Pete experiments with media over QUIC and real-time streaming protocols
The power of AI to remove gatekeeping from learning new technologies
Building an Nostr-based virtual pub with spatial audio

Vibe Coding vs. Slow Coding (09:38-16:13)

Insights from working with serious engineers on AI-assisted development
Everyone uses AI differently - no single "vibe coding" workflow
The importance of understanding your codebase architecture
Moving slower to go faster: maintaining intuition while delegating implementation

Build vs. Buy: The Shopify Question (14:25-25:06)

Andy's journey building an e-commerce site from scratch instead of using Shopify
The value of understanding how things work vs. convenience of platforms
Localization of software development - kids will build these things natively
Self-reliance as a valuable use of AI-gifted time

Shipping Tools People Can Use (25:06-33:00)

The critical lesson: put working demos in users' hands
Plans for multiplayer Wingman to lower barriers to experimentation
Designing the business into Wingman - mapping workflows and agents
Testing at Bush Bash with live coding sessions

Orchestrators vs. Deterministic Processes (33:00-38:52)

Why probabilistic orchestrator agents often fail in production
The case for simple, deterministic workflow rules
Left curve vs. mid curve: sometimes simpler is better
Humans should still design the business processes

Rate Limits and Model Selection (38:52-42:43)

Claude Haiku as a solution to usage limits
Running agents via API for unlimited usage
Multiplayer mode for sharing subscriptions efficiently
The challenge of making complex technology accessible

Simplifying the Message (42:43-48:31)

Beacon demo: focus on the "moment of magic" not the complexity
"Solvatur Ambulando" - solve it by walking around
Wingman's unique value: anywhere access + multiplayer agents
Don't let ego get in the way of clear communication

AI Agents Playing Games (48:31-59:09)

Using game environments to test model performance for business applications
Games as sandboxes for learning resource allocation and strategic thinking
Beyond single-agent approaches: teams of specialized agents
General Catalyst's investment in gaming arenas for model testing

Multiple Minds Per Task (55:13-01:01:38)

Humans have multiple personalities for different contexts
Agents may need similar specialization to avoid being overwhelmed
File-based handoffs between agents as a clean interface
The 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."