The core rule
Hermes is the agent home. It coordinates, remembers, schedules, and routes work. It is not the place where production applications live, and it is not the long-term development workstation for app source.
Source of truth: GitHub repos, project docs, sprint packs, reviewed commits.
Runtime: Rancher/Kubernetes with ingress, TLS, health checks, and rollback evidence.
Not allowed: app source, dev servers, previews, or production apps living on Hermes.
Why this exists
AI can produce code quickly, but speed without structure creates context drift, undocumented decisions, weak testing, and fragile deployments. The system uses AI where it helps — planning, coding, review, operations — while preserving normal software engineering controls.
No vibe codingArchitecture packsTDD when practicalReview gatesRancher deploysPublic health evidenceEnd-to-end workflow
Every application follows a pipeline. Agents can run autonomously, but the handoffs and evidence stay durable.
Intake
Ideas, inbox specs, meetings, voice notes, and research land in Dropbox/Hermes/SoftwareProcess/03-intake or a Kanban row.
Architecture
Archer inventories the request, updates the project folder, defines architecture, and writes sprint requirements, blueprint, acceptance criteria, and builder handoff prompt.
Implementation
Builders such as Cody, Mason, Rowan, and Elena work from repo/worktree source, not chat history. They commit code and test evidence.
Review
Quinn reviews against acceptance criteria and evidence. Failed reviews produce focused fix tasks, not vague retries.
Deployment
Atlas deploys production workloads to Rancher/Kubernetes with namespace, workload, ingress, TLS, health, and rollback evidence.
Operations
Piper keeps the board high-signal. Sable, Ada, Nora, Linus, Victor, Hazel, and other specialists own security, identity, networking, Linux, VMware, and smart-home lanes.
Per-project documentation
Every active project is organized the same way under Dropbox/Hermes/SoftwareProcess/02-projects and mirrored into repo docs where appropriate.
Required planning files
README.mdAGENTS.mdplanning/state.mdplanning/decisions.mdplanning/domain.mdplanning/risks.mdplanning/questions.mdplanning/file-inventory.md
Required engineering files
docs/architecture.mddocs/data-model.mddocs/api.mddocs/permissions.mddocs/validation.mdsprint requirementssprint blueprintacceptance criteriahandoff prompt
Agent roles
| Agent/lane | Owns | Produces | Evidence before done |
|---|---|---|---|
| Archer | Software architecture and portfolio design | Architecture docs, sprint packs, repo/Rancher decisions | Updated project docs and builder handoff prompt |
| Builders | Implementation | Code, tests, commits, PRs | Repo branch/commit, test output, docs updates |
| Quinn | QA and review | Pass/fail review, defects, regression notes | Acceptance-criteria review and reproduction evidence |
| Atlas | Rancher/Kubernetes deployment | Manifests, ingress, TLS, CI/CD, health checks | Namespace/workload/ingress/TLS/URL health evidence |
| Piper | Orchestration and board hygiene | Minimal task graph, blocker cleanup, status relay | Real task IDs, clear dependencies, stale rows closed |
| Sable/Ada/Nora/Linus/Victor/Hazel | Security, identity, DNS/network, Linux, VMware, Home Assistant | Specialist changes and domain evidence | Tool-backed validation, reports, and safe handoffs |
Training program
New software agents are trained against the same operating standard before touching builds. The training covers Ryan's non-negotiables, architect-builder workflow, per-project documentation, build discipline, review, deployment, and board hygiene.
06-agent-training/curriculum.mdonboarding checklistrole matrixgraduation prompt
Current project areas
AITraderITOperationsHQSaaSMonHermes M365 OAuth connectorHome Assistant OpenAI/Bifrost integrationValidation apps
Each project gets its own folder, docs, sprint packs, repo decision, and deployment path.