A language for writing agents.

Matiq is Tessera's language for building agents: easy to read, and designed to declare what the agent does rather than how the machine executes it.

What the agent does is buried in how it runs.

An agent written in general-purpose code mixes two things: the work it's supposed to do and the machinery that gets the machine to do it. The people who own the work don't always read the machinery, and the people who read the machinery don't always know what the work was.

From what you describe to the agent that runs.

You start by saying, in natural language, what the agent should do. Tessera turns that request into Matiq: a short, readable declaration of the work, with the goal, the tools the agent can use, the data it reads and the rules that apply to it.

From that declaration, the platform builds the execution flows. Anyone reading the Matiq understands what the agent does without opening up the machinery, and whatever changes in the declaration changes in the flow, with a version, an owner and a policy from day one.

Why a language for agents.

When an agent is described in a language made for it, what it does stops being scattered across the code that runs it.

Readable

Whoever owns the agent can read what it does.

Separate intent

What the agent does, separate from how it runs.

Reviewable

Every change is text: diffable, reviewable, approvable.

Simple

Written by people who know the work, not just the machine.

Why our team loves Matiq.

Because it grew out of a story we admire: a programmer who, in the 1950s, decided the machine had to understand the person describing the work, not the other way around. Matiq brings that idea to agents.

We're here to change how agents are written: less machinery for the people who build them, more clarity for the people who answer for them.

Wear Matiq.

T-shirts, caps and mugs for people who write agents, or just like the story.

Write your next agent in the language of the people who describe the work.

Govern what you've already built.

Connect agents from different frameworks to a common layer for operations and governance.