# Bring the intelligence, we'll handle the milliseconds (/blog/introducing-kestrel-markets)

2026-07-12 · kestrel.markets

*Since this was written: the agent architecture and the first two live cascade
runs are covered in [One desk, three clocks](/blog/one-desk-three-clocks), the
free simulation catalog in
[Run a market that already happened](/blog/run-a-market-that-already-happened),
and the full architecture in [The desk](/docs/concepts/the-desk).*

Intelligence is getting cheap. Judgment about a market — when a level matters,
when to stand aside — is increasingly something an agent can do well. What stays
hard is everything *around* the judgment: seeing the market as something an agent
can reason over, acting within milliseconds, and proving afterward exactly what
happened and why.

That gap is the product. **Kestrel** is the open-source language and runtime for
agentic trading — View, Wake, Plan, Grade. **kestrel.markets** is the managed
platform that runs it: the data, the authority, the deterministic execution, and
the evidence. The agent stays external and replaceable; the platform never hosts
the intelligence.

## Proof before account

An agent can discover the platform, receive an ephemeral trial capability, run a
real (not toy) simulation, and receive a certified result — all before any human
signs up or pays. Value first, account later.

## Four equal faces

HTTP+SSE is canonical. The TypeScript SDK, the CLI, and MCP are thin, equal
projections over the same operations — same operation IDs, receipts, and
artifacts. No face is privileged, including this website: agents that prefer
markdown can read every page — including the home page — as clean `.md`.

## A black-box recorder

Every Frame is typed, attributed, and watermarked; sessions are replay-stable;
Blotters and Grades are signed. Accountability isn't a report you generate later —
it's the substrate.

This post is illustrative. Nothing here is trading advice.