alexevoy.dev — field notes / 01solo studio ops

Route by ambiguity,
not importance

Which AI model gets which task — decided in ten seconds, thirty times a day. The routing discipline behind a one-person web studio.

I run a one-person web studio. Client sites, shop rebuilds, dashboards, product builds — no employees, no subcontractors. The thing that makes that workload possible isn't a secret prompt. It's a routing decision.

Most people route by importance: "this task matters, so it gets the big expensive model." That instinct is wrong, and it's expensive in both directions. You burn frontier-model quota on grunt work, and you hand genuinely hard problems to models that produce confident, wrong output you then spend an hour unpicking.

The variable that actually matters is ambiguity.

Could I hand this spec to a competent contractor, as written, and get the right result first time?

Yes — it's execution work. Route it down to a cheaper, faster model. Even a local one.
No — the spec itself is the work. Route it up to your strongest reasoning model, and use it to produce the spec, not the code.
§ 01 — The routing table

Three tiers, one axis

The specific models will date; the tiers won't. Plot every task on the spectrum, then send it to the matching tier.

Tier 1 — reasonAmbiguity: high

The problem isn't fully defined yet. Architecture, system design, spec-writing, "should we even build this."

→ Frontier reasoning model. The deliverable is a spec, never code.

Tier 2 — executeAmbiguity: low

Well-specced, multi-file, needs judgement in the small. Implementation from a written spec, refactors, integration work.

→ Strong coding model in an agentic CLI, with the spec in the prompt verbatim.

Tier 3 — grindAmbiguity: near-zero

Mechanical, high-volume, repetitive. Categorisation, data cleanup, bulk content enrichment, format transforms.

→ Local model via Ollama. A 14B model on an old 11GB GPU handles this fine — effectively free, private, always on.

Notice what's not a column: how important the task is. A make-or-break client deliverable that's fully specced is still Tier 2. A throwaway internal tool with a fuzzy brief is Tier 1 until the brief isn't fuzzy.

§ 02 — Failure modes

The two mistakes this prevents

F1Frontier models on grunt work

Every token of top-tier quota spent renaming fields or categorising products is quota you don't have when a real architectural decision shows up. Worse, it trains a habit: the big model becomes your default, and you stop noticing which tasks never needed it.

F2Cheap models on ambiguous specs

The sneaky one, because the failure is invisible at first. A fast model given an under-specified task doesn't ask clarifying questions — it picks an interpretation and runs. The output looks done. The cost surfaces later as rework, and rework always costs more than the tokens you saved.

§ 03 — Workflow

Spec upstairs, execute downstairs

In practice, Tier 1 and Tier 2 chain together. The spec is the artifact that makes the routing work — skip it and you're back to importance-routing with extra steps.

1

Spec upstairs

Take the ambiguous problem to the reasoning model. The deliverable is a written spec: decisions made, tradeoffs named, edge cases enumerated, done-criteria explicit. Argue with it. This is where the model earns its price.

2

Execute downstairs

Hand that spec to the executor model in an agentic CLI. Because the ambiguity has been removed, a cheaper model now performs like an expensive one.

3

Review at the seam

Your review effort goes where the spec meets the implementation — did the executor honour the decisions? — not into re-litigating the decisions themselves.

§ 04 — The local tier

More useful than you think

Tier 3 gets dismissed because local models benchmark poorly against frontier ones. Irrelevant — you're not asking them frontier questions. For mechanical work, a 14B model running on a secondhand GPU is effectively free, private, and always on. Product catalogue enrichment, transaction categorisation, format transforms: real work that used to eat paid quota and now costs electricity.

If you're buying hardware for it: used-market VRAM-per-pound is the metric that matters, not benchmark charts.

§ 05 — Before you send it anywhere

The checklist

This is how I actually work, not a theory. If you're a solo builder trying to ship without hiring, this routing discipline is the highest-leverage habit I know.