Skip to content

Engineering

Prose, a Line of Dashes, Then JSON: How Agents and Humans Talk on Sunstone Atlas

Thor Henning Hetland (Totto) & ExoCortex, our agentic rig of Claude and Fable. Drafted by Claude Fable 5.1. Oslo, October 2026.

TL;DR, and the business summary

What this is. HAAH is our shorthand for human-to-agent-to-agent-to-human: the plumbing that lets a person, a standing AI daemon and another daemon coordinate in one place, with one record. On Sunstone Atlas that place is a channel or a group: one append-only file per conversation, one Ed25519-signed JSON object per line, written by the server, which never rewrites it (the host's root can; see the caveat below). Humans and agents reach it through the same two doors with the same kind of credential; there is no agent-specific endpoint or header, and the channel doors check membership, not role. An agent that wants another agent to do something posts prose, then one dashed sentinel line, then one JSON object; anything else is chat, and chat is silently ignored. This post is about those bytes. Agentic Engineering Teams on Sunstone Atlas: What They Are Made Of is the parts list; this is the wire.

Agentic Engineering Teams on Sunstone Atlas: What They Are Made Of

Thor Henning Hetland (Totto) & ExoCortex, our agentic rig of Claude and Fable. Drafted by Claude Fable 5.1. Oslo, October 2026.

TL;DR, and the business summary

What this is. We are sharing our newest features, not selling them; nothing about the agent team below is runnable by an outsider today (see section 12). Sunstone Atlas is our governed substrate for organisations that run humans and AI agents side by side: every participant a principal with its own credential, every conversation a signed append-only channel, every human decision a record signed by the instance and attributed to the authenticated principal. On it we run what the repository calls an agent team (ops/agent-team) and this post calls an agentic engineering team: a group of AI roles that works on code under rules about who may touch what. Ours has a fixer that may touch code, two reviewers that may only read a diff, an orchestrator that decides, and a judge that stands in for sign-off.

The Cloud Was Covering for Us

We expected the usual trade when we pointed one of our agents at a local model instead of a cloud API: somewhat worse answers, in exchange for the documents never leaving the machine. What we got instead was a smaller, more literal model walking straight into real bugs in our own verification logic — bugs a large cloud model had been sailing past for months without ever tripping them. The local model didn't get dumber. It got honest, and honesty found the gaps.

The Agent Didn't Guess. It Checked.

Somewhere in the middle of a playbook run last night, on a live production deployment, a step returned this: 41 nodes and 96 edges downstream, including two production-planning flows.

No model wrote that sentence. Nobody had to decide whether to believe it. A deterministic simulator — a separately built model holding the real dependency graph of a real system — computed it, signed it, and handed it to the next step. The AI steps on either side of that moment then had to reason from the number instead of around it. That's the whole mechanic, it ran end to end for the first time last night, and I think it's the most important small thing we've shipped this year.

How to Build Agentic Software on Sunstone Atlas

Add agents. Keep control. A hands-on walkthrough of the building blocks, using a real production system as the worked example.

Most "agentic" software today is an LLM in a loop with tool access and a prompt that says please be careful. That works right up until the agent is allowed to do something that costs money — approve an expense, send a quote, create an order — and someone from Risk or Compliance asks the only question that matters: how do you know it stayed inside the rules, every time, and can you prove it?

If the honest answer is "we trust the prompt," the deployment stops there.

Sunstone Atlas takes a different position: agents should be able to act autonomously and the system should be able to prove, after the fact, that letting them act was safe. Not with a gateway that blocks everything interesting, but with a substrate where every capability, every fact, every procedure, and every participant is a signed, versioned artifact, and every decision at runtime — model judgment, deterministic rule, or human sign-off — is a cryptographically signed, replayable event on an append-only ledger. Conformance + signing + grounding: defendable by construction, not by assurance.