Bring Your Own AI

Whenever we build a product now, we ask the same question: where could AI make this experience easier?

Replace a form with a conversation or let someone upload documents instead. Translate existing material in any language. Query data using natural language.

We've built several of these experiences at Commons. They work. Often incredibly well.

One design pattern has proven especially effective: instead of letting the model generate SQL, API calls, or business logic directly, we define a small domain-specific language.

The application owns the semantics.The model translates the user's intent into that language.

The AI doesn't need to understand the entire system. It just needs to speak the application's language.

That separation of concerns makes the system more reliable, easier to evolve, and much simpler to reason about.

One downside of these new experiences is that every AI feature becomes its own AI product. You're suddenly managing providers, API keys, monitoring, costs, prompts, and ever-changing model capabilities. The rest of your application wants stability; the AI stack refuses to stand still.

This got me thinking.

If the application already owns the semantics, why does it also need to own the intelligence? What if applications simply welcomed agents as first-class users?

Give people secure agent tokens with exactly the permissions they already have. Expose the application's capabilities through a clean API. Whether the interface is MCP or something else almost doesn't matter.

Now users can bring their own AI.

The application still has a great interface. But Claude, ChatGPT, Gemini, or whatever comes next, can also interact with it on the user's behalf.

That AI already knows how the user writes. It speaks their language. It has access to the files they chose to share. It can combine information across several applications instead of being trapped inside one carefully designed chatbot.

The application becomes stable.

The intelligence becomes portable.

There is a loose parallel with identity. An application doesn't necessarily need to create and own your identity; it needs a reliable way to establish who you are and what you're allowed to do.

Perhaps intelligence will become similarly portable.

Instead of every product attempting to own its own AI experience, products may simply become places where your AI gets work done.

We've started calling this Bring Your Own AI, and we're gradually introducing it across our applications.

Maybe everyone will keep embedding chatbots forever.

Or perhaps, in a few years, building a separate AI into every product will feel as unnecessary as every website implementing its own login system.

I don't know.

I just know this direction feels surprisingly liberating.