---
title: "The model is a component, monō Insights"
description: "Pick the best model for each job today. Swap it tomorrow. Your business should never be tied to one lab's release schedule."
---

[← Insights](/insights/)

![](/insights/the-model-is-a-component/thumbnail.png)

11 June 2026 · 2 min read

# The model is a component

Pick the best model for each job today. Swap it tomorrow. Your business should never be tied to one lab's release schedule.

[![The monō team](/mono-team.png)**The monō team**](/insights/author/mono-team/)

[Engineering](/insights/category/engineering/)

Right now the leading labs genuinely lead. The frontier is real, and you should use the best model you can for the work in front of you.

But look five years out. It may not matter which lab you started with. New entrants, open-source models and fine-tuned variants keep arriving, and the lead changes hands more often than procurement cycles do.

## A component, not a commitment

So we treat the model as a component. You pick the best one for each job, and you change it the moment a better one ships, without rebuilding the work around it.

The opposite is quiet lock-in. When your capability is welded to one provider, their release schedule, their pricing and their limits slowly become yours.

## One job, one tile

Each agent does one job, which we call a tile. Forecasting, collections, board reporting: each is its own tile, with its own definition of done.

A tile does not care which model sits underneath it. The work, the memory and the guardrails belong to the tile. You can move from a frontier model to an open one, and the tile still runs.

> The model is a component, not a commitment.

## Cost is an architecture choice

Running the same work for far fewer tokens is not a discount you negotiate. It is an architecture: send only the context that matters, check memory before re-reading, and route volume to smaller models.

Same work, fewer tokens. That advantage is structural, and it holds whichever model is best this month.

## Bring your own API keys

Because the model is just a component, you can run inference through your own cloud and model accounts, at your own negotiated rates. That way you are not paying a margin on someone else's relationship with a lab.

## What to keep portable

Keep three things in your hands and the model stops mattering: the work, the memory, and the right to swap. Hold those, and every new model on the frontier is an upgrade you opt into, not a migration you survive.

## Related posts

![](/insights/why-ai-pilots-stall/hero.png)

18 June 2026 · 2 min read

## [Why most AI pilots stall](/insights/why-ai-pilots-stall/)

Most AI work fails before it ships. Not because the technology is weak, but because nobody rewires how the business actually runs.

[Point of view](/insights/category/point-of-view/)![Portrait of David Hyman](/david-hyman.jpg)[David Hyman](/insights/author/david-hyman/)

![](/insights/most-software-depreciates/thumbnail.png)

4 June 2026 · 2 min read

## [Most software depreciates](/insights/most-software-depreciates/)

Most tools lose value the day you buy them. A system with memory does the opposite. It gets sharper every month you run it.

[Point of view](/insights/category/point-of-view/)![Portrait of David Hyman](/david-hyman.jpg)[David Hyman](/insights/author/david-hyman/)