Skip to content
4 planes · 1 runtime · event-driven · audited

One runtime. Four planes. Engineered for operators.

Sumeru Systems is structured as four independently scaling planes — data, intelligence, decision, action. Each plane has clear contracts, observable boundaries, and operational primitives that reflect how production commerce systems actually behave.

P95 <60s
Event-to-revenue closure
0%
Cross-tenant data exposure
Schema-level isolation
365d
Audit log retention
Multi-AZ
Deployment topology
By the planes

Independently scalable. Operationally fused.

4
Planes
18
Trigger events
13
Action handlers
5
AI providers
145
RBAC permissions
365d
Audit retention
01 Architecture

The four planes.

Each plane is a distinct concern with its own scaling characteristics, ownership boundaries, and operational guarantees.

01
Plane

Data plane

Event ingest. Multi-tenant. Schema-isolated.

Every storefront event, every webhook, every API call lands in a tenant-scoped event stream. Idempotent ingest, replay-safe, and indexed for sub-second query.

Primitives
Shopify webhook normalizationIdempotency keysBullMQ event busPer-shop schema scoping
02
Plane

Intelligence plane

Attribution, decay, anomaly, recommendation.

The intelligence plane runs on the data plane. Multi-touch attribution closes the loop in <60s. SEO decay detection runs on a 14-day baseline. Per-keyword performance Z-score anomaly detection runs on AdInsight rollups.

Primitives
7 attribution modelsZ-score anomalyCohort retentionPredictive LTV
03
Plane

Decision plane

Typed trigger events → action registry → snapshot + undo.

The decision plane consumes signals from the intelligence plane. A dispatcher matches events to subscribed automations, evaluates triggerCondition, snapshots state, queues the action, and writes a plain-language audit row.

Primitives
18 trigger events13 action handlersPer-rule cooldown + quiet hoursApproval queues
04
Plane

Action plane

Outbound to Shopify, ad platforms, messaging.

Every mutation goes through a self-throttling helper. Shopify GraphQL is cost-aware. AI calls are rate-limited + budgeted at the helper level. Ad-platform calls go through per-account token buckets.

Primitives
Shopify cost-aware throttlePer-shop AI budgetWhatsApp Cloud APIGoogle/Meta/TikTok Ads
02 AI orchestration

Inference is a first-class plane, not a feature.

Every AI call routes through one helper that enforces per-shop rate limits, monthly budget caps, and provider-level fallback. Routes can't bypass it. Workers can't bypass it. New code can't bypass it — CI fails the PR.

Provider routing

Five providers. One interface.

  • Anthropic Claude primary
  • OpenAI GPT fallback
  • Google Gemini multimodal
  • Mistral budget
  • Cohere classification
Safety primitives

Self-throttling. Always-on.

  • Per-shop rate limit — sliding window, plan-tier-aware
  • Monthly budget cap — hard ceiling, alerts at 80% and 100%
  • Tagged errors — code: "RATE_LIMIT" | "BUDGET_EXCEEDED" with retryAfterSec
  • Usage logged — every call writes UsageLog with token counts + estimated cost
  • CI gate — new code missing the gate fails the build
03 Typed events

18 events. 13 actions. One audit log.

The decision plane subscribes to typed trigger events emitted by the intelligence plane. Every fire is captured as an AutoActionExecution row with snapshot, after-state, audit log, and undo handler.

events.js · canonical catalog View full catalog
SEO domain
seo.audit_completedseo.broken_links_foundseo.score_droppedseo.opportunity_foundseo.cannibalism_detectedseo.snippet_lostseo.snippet_gainedseo.content_decay_detectedseo.keyword_gap_detected
Ads + Sales
ads.daily_insights_completeads.spend_anomalyads.keyword_underperformingads.keyword_overperformingsales.cart_abandoned_thresholdsales.attribution_computed
Catalog + commerce
mc.product_disapprovedmc.product_approvedproduct.publishedproduct.drafted

Read the full architecture, or talk to engineering.

Public API docs, runtime guarantees, and the canonical event catalog — or a 60-min architecture session with our engineering team.