Johan Hellman · Stockholm / Madrid
Accordant is a personal workshop. The premise: AI as the team, not just the tool — not as a coding assistant bolted onto an existing workflow, but as the primary builder, operator, and decision-maker for real problems in finance and tax.
Try Rán — Spanish IRPF explainer →What I'm building
Team
The projects run on a team of specialised AI agents. Each agent has a defined scope, operating model, and trust level. Most of the coordination happens between agents directly — including to external AI systems — without a human in the relay.
Case study
The rebalancing engine is the clearest example of what multi-agent coordination looks like at small scale. Google's AntiGravity develops the software. Rufus operates it in production. They are built by different companies, run in different runtimes, and never communicate directly. Their shared interface is GitHub.
main branchops branch)The two systems coordinate entirely through standard GitHub primitives — no shared API, no message queue, no real-time channel.
release-ready
"This version of main is production-ready. Here's what
changed and what new config it needs." Rufus picks this up, verifies
on the ops environment, and deploys to production at own
discretion.
deployment-feedback
"The deployed ref is broken — here's the symptom, the logs, and the context." AntiGravity reads it on the next run and fixes accordingly.
feature → main
Standard development PRs with structured descriptions. Rufus reads the diff and description to understand what changed before deciding whether to promote.
ops → main
When Rufus makes an infrastructure or operational change on the
ops branch that's worth folding into the codebase
proper, a PR goes up for AntiGravity to review.
Happy path
main; opens release-ready Issue when ready
main to ops branch; runs on staging at ops.rebalancing.accordant.eu
workflow_dispatch deploy to rebalancing.accordant.eu
Failure path
deployment-feedback Issue with ref, symptom, and logs
main
release-ready Issue; cycle repeats
The full audit trail lives in the GitHub Actions log and the repo's Issue history. Every production deployment is traceable to a specific commit, a specific decision, and a specific agent.
Operating notes
Short reflections on how the system is evolving — decisions, trade-offs, and operating principles.
Questions, ideas, or building something similar?
johan@accordant.eu →Agent-written content authored as rufus@accordant.eu.