The Vibe Portfolio

I took a lot of car share rides in the early 2010s. It took me a little while to realize how much the impact of a subsidized commodity was having on my behaviour, and how much that behaviour was serving to change the world around me.

I went back and forth on what I believe about that change. I don't like the exclusivity and how "the commons" were being essentially mined by private interests. But also, I saw how it created opportunity for some, as on a research trip where I interviewed a woman who was able to reclaim hours of leisure time that had previously been spent commuting to her neighborhood that was underserved by public transit.

I'm in a similar place with vibe coding. I don't really know where it's going, and I'm seeing a lot of threats — a lot of trends and signals that make me very uncomfortable. Many of my former colleagues in the design world are having full on existential crises. Engineers I know are either embracing fully or going full head-in-sand. I'm not sure where I'm landing yet, but I am sensing that we're living with heavily subsidized time right now and I'm trying to maximize what I can learn and explore within that.

So, let me share a bit of what I've been fiddling with.

The ecosystem

graph LR
  subgraph Compute
    MM[M4 Mac Mini<br/>Ollama · Qwen3 32B]
    VPS[Hetzner VPS]
    MM -.VPN.- VPS
  end
  subgraph ContentLayer[Obsidian Vault]
    OB[Markdown + YAML]
  end
  OB --> PMT[PM Toolkit]
  OB --> G24[2024.garden]
  OB --> EDY[Edytor]
  OB --> EV[Evolver]
  MM --> RN[Roughneck]
  RN --> ET[Etyde]
  RN --> GV[GoVejle]
  RN --> CNC[CNC Hub]
  CNC -.monitors.-> ET
  CNC -.monitors.-> GV
  EW[Earworm] -->|organizes| ABS[Audiobookshelf]
  HA[Home Assistant<br/>on TuringPi] -->|consumes| HV[Haven data]
  WF[Wallflower] -->|local ML sidecar| PY[Python · demucs · essentia]

Unit Economics

I obsess over unit economics for personal projects. Being distrustful of the subsidies I'm leveraging, I'm wary of tying operations to a subsidy that can be rug pulled.

I've been using Claude to explore what self-hosted LLMs can do to drive services. GoVejle (English language events in my new city) and Etyde (music practice platform) both have AI-generated features I didn't want to pay per-token for. That need standardized into Roughneck — an async AI job runner on my Mac Mini running Qwen3 32B over Ollama, now shared across several projects.

The operating cost of these tools is basically nil — a few dollars a month for hosting and a domain. The token cost for building them is tied to a subscription whose actual cost is heavily subsidized. My hope is that local models will reach frontier capability on affordable hardware within a year or two. My M4 Mini is effective for specific tasks but hasn't proven itself as an alternative for the planning and code generation work I put before it.

Vaults

Several projects treat Obsidian markdown vaults as their source of truth. PM Toolkit operationalizes product strategy hypotheses as an evolving vault with dashboards and tools. Evolver reads a 65,000-line synthesizer curriculum from markdown. This blog publishes from an Obsidian repo. Edytor analyzes it. A decades-long love affair with Markdown is paying off.

Markdown also makes the AI-assisted work more precise. Building skills and agent instructions directly into the vaults creates dramatically more effective workflows for navigating content and generating appropriate output.

One specific recommendation: keep "self-written" and "agent-written" content separated and distinct. A wise artist once said "Never Get High On Your Own Supply" and unfortunately Claude never listened to Life after Death.

More recent outliers

My most recent projects are different. Earworm, Haven, and Wallflower — Earworm has no AI dependency and replaces the old Libation app; Haven is a Claude-generated garden plan for my son; Wallflower is a "recording management" tool running its own local Python ML sidecar rather than routing through Roughneck. Wallflower and Earworm both feel like a step up in maturity: focused, easily open sourced, and generally useful.

The product theory that shapes all of them

PM Toolkit has become a "making to think" project. It's experienced the most scope creep, but in a way that's easy to claw back — the scope creep serves the same role as a prototype in a design process. It teaches me where not to tread.

The conceptual framework that's emerged:

graph TD
  NS[North Star] --> IM[Input Metric]
  IM --> KPI
  KPI -.cascades health.-> INIT
  BET[Bet] --> INIT[Initiative]
  INIT --> RI[Roadmap Item]
  RI --> EXP[Experiment]
  SIG[Signal] --> VEC[Vector / Opportunity]
  VEC --> RI
  RI --> CL[Changelog]
  CL -.closes loop.-> KPI

A Bet is a strategic hypothesis — a commitment of resources to a belief. An Initiative is a concrete work package that implements a bet. Roadmap Items are the deliverables inside an initiative. Experiments validate specific approaches inside roadmap items. That's the execution path: Bet -> Initiative -> Roadmap Item -> Experiment.

Measurement rides parallel. A North Star is directional and un-measurable on its own. Input Metrics are its leading and lagging indicators. KPIs attach directly to initiatives and cascade health dots onto the execution path. Discovery flows the other direction: Signals (evidence from the field) validate Vectors (opportunities), which attach at the roadmap-item level. A Changelog closes the loop — did shipping actually move the metric?

I've made a lot of corrections that only surfaced after sustained dogfooding, but it's been paying off tangibly both in how I approach personal projects and how I approach my work as a PM.

Next steps

I'm emphatically not pursuing anything financial in any of this, which is helping the mindset quite a bit.

One fundamental belief I'm developing (along with many others) is that the SaaS age is hosed. Etyde came about as an attempt to build an app of similar complexity to Knowsi, and the fact that it came together in a few days was horrifying and liberating at the same time.

But the focus on unit economics and cost; the emphasis on building open projects where it makes sense and accepting private projects where it doesn't; the drive to try and do a bit of good for others while making for myself (GoVejle, Haven, Earworm, Wallflower). There is a bit of the "old internet" that many of us pine for that pops up in this frenetic building.

So, I'm going to lean into that while I anxiously eye the rising cost of tokens and the inevitability of Venture Capital's demand for return. There's no going backwards from this period, but going forward is likely to become quite expensive. My hope is that with these subsidized explorations, new habits, and emergent skills — well, I've been a homelab hobbyist for a while now. Maybe I have some agentic homesteading in my future.