Vibing with AI Code

Brendan Buckingham

We are here to discuss the latest in the world of coding with AI. We explore both the good and the bad, and help you make informed decisions based on our experiences. A key component of this channel is sharing what we learn, to improve both our skills and yours. Let's grow together!

  1. 4 days ago

    Episode 013: Building a Personal AI Agent That Cuts Through the Noise

    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 Powerful podcast hosting & analytics By podcasters, for podcasters. Since 2016 Brought to you by https://fireside.fm claudecode #claudeai #aicoding #aiagents Signup for our newsletter: https://vibing-with-ai-code.beehiiv.com Check out our Website https://vibingwithaicode.com

  2. 5 Aug

    Episode 012: The Plan Matters More Than the Model

    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 Powerful podcast hosting & analytics By podcasters, for podcasters. Since 2016 Brought to you by https://fireside.fm claudecode #claudeai #aicoding #aiagents Signup for our newsletter: https://vibing-with-ai-code.beehiiv.com Check out our Website https://vibingwithaicode.com

  3. 27 Jul

    Episode 011: Activation Energy: How AI Gets You Back Into Old Projects

    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 Powerful podcast hosting & analytics By podcasters, for podcasters. Since 2016 Brought to you by https://fireside.fm claudecode #claudeai #aicoding #aiagents Signup for our newsletter: https://vibing-with-ai-code.beehiiv.com Check out our Website https://vibingwithaicode.com

  4. 20 Jul

    Episode 010: Where AI Still Breaks

    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 02:00 Baird's image-cleanup pipeline: GPT Image 2 vs Nano Banana 05:00 "Fixes" that made it worse — stretched and doubled sandwich 10:00 Nano Banana's silent regeneration limit 12:00 Prompting in English: ambiguity is the real interface problem 14:00 Brendan's Rollbar sub-agent story 15:00 Babysitting scheduled automations 17:00 Why agent loops aren't the answer yet 20:00 Wrapping AI-written scripts to dodge non-determinism 21:00 Activation energy + missing the craft 26:00 Consulting announcement Sponsor Powerful podcast hosting & analytics By podcasters, for podcasters. Since 2016 Brought to you by https://fireside.fm claudecode #claudeai #aicoding #aiagents Signup for our newsletter: https://vibing-with-ai-code.beehiiv.com Check out our Website https://vibingwithaicode.com

  5. 24 Jun

    Episode 009: How to Get Bespoke AI Design (Without Being a Designer)

    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 Powerful podcast hosting & analytics By podcasters, for podcasters. Since 2016 Brought to you by https://fireside.fm claudecode #claudeai #aidesign #aicoding #aiagents

    Episode 009: How to Get Bespoke AI Design (Without Being a Designer)

  6. 27 Apr

    Episode 008: AI Coding Tools Are Getting More Expensive: How to Adapt with Models, Harnesses, and Skills

    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 Powerful podcast hosting & analytics By podcasters, for podcasters. Since 2016 Brought to you by https://fireside.fm claudecode #claudeai #aicoding #aiagents Signup for our newsletter: https://vibing-with-ai-code.beehiiv.com Check out our Website https://vibingwithaicode.com

  7. 16 Apr

    Episode 007: Claude Dispatch Update and Building Local AI Agents with Gemma 4

    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 Fireside Powerful podcast hosting & analytics By podcasters, for podcasters. Since 2016 Sign up for our newsletter Check out our Website 00:00 Dispatch Update Kickoff 01:10 What Dispatch Can Do 03:04 Poolside Rollbar Workflow 05:37 Dispatch Integration Questions 08:35 Rethinking Work With Agents 13:50 Claude Limits Spark Local Shift 15:26 Gemma 4 Local Agent App 18:32 Building The Framework Fast 22:52 Tauri Local First Architecture 27:43 Model Switching And Cost Hacks 30:58 Loki Next Steps Wrap Up

  8. 6 Apr

    Episode 006: Claude Cowork Scheduling & Permissions: Fixing Friction in Autonomous AI Workflows

    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 Fireside Powerful podcast hosting & analytics By podcasters, for podcasters. Since 2016 Sign up for our newsletter 00:19 Show Format And Goals 01:25 Claude Cowork Friction 01:59 Scheduling And Permissions 06:43 Dashboard And Tool Sprawl 08:08 Dispatch Mobile Layer 09:46 Live Debug With Claude 15:39 Global Bypass Is Risky 20:37 Whitelist The Middle Ground 24:17 Wrap Up And Subscribe

See All (13)

About

We are here to discuss the latest in the world of coding with AI. We explore both the good and the bad, and help you make informed decisions based on our experiences. A key component of this channel is sharing what we learn, to improve both our skills and yours. Let's grow together!

Information

  • Creator
    Brendan Buckingham
  • Years Active
    2025 - 2026
  • Episodes
    13
  • Rating
    Explicit
  • Copyright
    © 2026 Vibing with AI Code
  • Show Website
    Vibing with AI Code

You Might Also Like