Vibing with AI Code

Six months into running his Claude Command Center, Brendan has a confession: the morning brief broke for a week and he didn't notice, because he'd already stopped reading it. This episode is the honest post-mortem on why a personal AI system can genuinely make you more productive and still feel like it's missing the point. Sparked by GrokBot and a conversation with Jesse Hanley of Bento, Brendan and Baird dig into what's actually broken — a system that generates content for you to look at but never acts on your behalf, briefs that insist a task isn't done when the proof is sitting in Slack, and the context gaps that make consolidating four channels into one feel worse than juggling four. Baird pushes back on the framing with the better question — are you being productive, or just busy? — and makes the case for scoping agents into real lanes instead of chasing one that does everything: let it audit what you actually do, then build the small utilities and read-only tools it needs to take the first step for you. The back half gets into the guardrails: why production stays read-only no matter how good the models get, why an agent that's right 99 times out of 100 is still a problem, why the "I've been asked this four times" moment is the real automation signal, and the danger nobody talks about — shipping so much cognitive load to the agent that you can't answer why anything was built the way it was. Plus Wade Foster's evening brief, agents-as-employees, and why neither host is ready to let a bot answer a human.

Sponsor

Signup for our newsletter:

Check out our Website

Baird's been building a reactive, background agentic framework — something that sits around all day surfacing what actually matters instead of waiting to be kicked off — and Brendan compares it head-to-head with his Claude Command Center. The whole episode circles the hardest problem in personal AI systems: cutting through the noise. Both hosts are fighting the same battle from different angles — a morning brief that dumps 30 to-dos when only two matter, figuring out whether a Slack message was actually answered, piecing together a Gmail thread and a Slack message that are secretly about the same thing, and Brendan quietly abandoning his own morning briefing because it stopped being useful. The big takeaway that keeps surfacing: the answer isn't "let AI do everything." A lot of this work is mechanical — data processing, cleaning, webhooks and cron — and doing that part in code first, then bringing AI in only where judgment is actually needed, is what makes the whole thing reliable. Plus: Vercel's new Eve framework, why an agency's fragmented context is harder than a single company's, an agent that got so confident it stopped opening PRs and committed straight to main, and how AGENTS.md / CLAUDE.md let a project teach itself as it goes.

Sponsor

Signup for our newsletter:

Check out our Website

With Fable's Pro-plan window closing, Brendan and Baird both did the same thing on their own: instead of trying to build with it, they had Fable plan — full roadmaps and individual feature specs — so cheaper models like Opus and Sonnet could execute against a high-quality plan. That kicks off a wider check-in on where AI is actually landing right now. Models feeling far more thorough and meticulous, Opus writing Python scripts to verify Ruby physics it can't run, Claude Code's improved auto-permissions mode finally letting you kick off work and walk away, and why agent loops still aren't the answer when there's no clear "right" to test against — especially for subjective frontend and design work. They close on the real distinction that's going to matter: AI is a tool that fills gaps you couldn't otherwise fill, but take the human out and all you've got is slop.

Sponsor

Signup for our newsletter:

Check out our Website

Brendan dove back into three stalled projects in one day — a personal command center, a video game tracker, and a Rails 8 app he hadn't touched in two months — and both hosts dig into why AI makes restarting old projects so much easier: it remembers where you left off, tells you what's actually built, and (with Fable) plans and cross-checks the reassessment before you write a line of code. They get into when it's worth splitting context (personal vs. project-specific memory), why Fable feels like the best planner but not necessarily the best daily driver, and how tools like Conductor now auto-select models per task. Plus: what actually happens when sub-agents run out of session usage mid-task, and why lowering activation energy might be the single biggest thing AI has changed about how they work.

Sponsor

Signup for our newsletter:

Check out our Website

Two years into building daily with AI, Brendan and Baird check in on what's actually still broken. Baird shares an image-processing pipeline (GPT Image 2, Nano Banana) that nails 8 out of 10 images — then randomly crops the sandwich out of frame. Brendan tells the story of Claude claiming it spun up 10 sub-agents when it actually did the work itself and just said so. They dig into why non-determinism is still the real blocker for hands-off automation, why they're skeptical of "just let the agent loop figure it out," and where AI has genuinely transformed their work: killing activation energy, handling the tedious stuff, and letting them build things they never would have built otherwise.

Thinking about bringing AI into your own work? We're opening up a limited amount of consulting — reach out via the link below.

00:00 Two-year check-in kicks off

Sponsor

Signup for our newsletter:

Check out our Website

AI design is getting better — but it's also getting more homogenous. First it was the Tailwind default. Now it's the Claude Design default. In this episode, Baird walks through how he rebuilt his personal portfolio site using a design-systems approach with AI skills — and why that process produces something that actually feels intentional.

Sponsor

The hosts discuss the rising costs and tightening limits for AI tools as companies try to recoup massive infrastructure spending. They note signs that features like Claude Code may be removed from the $20/month Pro plan. They compare experiences hitting usage caps faster when using agent-style workflows like the “Get Shit Done” framework, which can burn tokens quickly especially during planning. To cope, they describe mixing tools and models—Claude Code, OpenAI Codex, Windsurf, and free alternatives like Kimi—using cheaper models for research or simple tasks and reserving premium models for complex work. They also explore switching costs from tool ecosystems, differences between models and harnesses, and how reusable “skills” (often just markdown files) can improve reliability across platforms and help users stay productive on a budget.

Sponsor

Signup for our newsletter:

Check out our Website

In this episode, the hosts share a hands-on update on using Claude Dispatch. They discuss how it works as a separate synced chat that can trigger and check on jobs remotely, create tickets from analysis results, and request new agents. They also reference the current friction around permissions and repository selection. The conversation then shifts to exploring local and lower-cost agentic AI workflows due to usage limits and subscription costs, including experimenting with Google’s Gemma 4 as a local “brain” via LM Studio and using Kimi in Windsurf to build a new local agent app (code-named “Loki”) with chat, tools, memory, and research capabilities.

Sponsor

Sign up for our newsletter

00:00 Dispatch Update Kickoff

In this episode, the hosts discuss practical challenges with Claude Cowork and scheduled AI jobs, focusing on friction points like needing a laptop to be awake for tasks to run, inconsistent scheduling behavior, and recurring permission prompts that can silently halt background workflows.

Sponsor

Sign up for our newsletter

00:19 Show Format And Goals

AI is powerful but risky in the wrong hands. We break down the real liability and security concerns founders face when using LLMs in local development — from overly permissive "YOLO mode" to production database wipeouts. Plus practical best practices for vibe coders who want to ship fast without blowing up their app.

Sponsor

Link to The Bootstrapped Founder episode we discussed

Sign up for our newsletter

00:00 AI News Overload