Six layers. One platform.
Receipts at every step.
The platform behind the conversation. Composable from foundation to delivery, ratified contracts between layers, per-tenant secret isolation, NIST AI RMF mapped in code (not on a slide), and 10+ tenants live today. Each layer below shows the actual modules, the executive one-liner, and the on-disk evidence.
Config, identity, persistence, files, observability — same code, two clouds
(GCP DelectableAI · Azure EIS), per-tenant secret isolation enforced by the env resolver,
dual-remote on every module. Configuration is hierarchical: global → customer → environment →
module, with secrets stored per-cloud in Secret Manager / Key Vault.
infrastructure/customers/
Secret path · via/<tenant>/<env>/<module>/<key>
Per-cloud Terraform · deploy/terraform/{gcp,azure}/{dev,stage,prod}/
Audit + provenance · audit_store.py
Services ship actions.yaml manifests. Workflow ingests them at boot,
validates Pydantic schemas, and executes HTTP steps gated on a shared event bus.
No tight coupling — composition by contract. The contract was
ratified 2026-05-22 and is mirrored by every shared-service module.
parsing/actions.yaml
Multi-cloud secrets · scheduling/secrets_{azure,gcp}.py
Safety as a service · safety/routes/{incidents,policies,evaluations}.py
Event bus topics declared in each actions.yaml
Specialized parsers (Tika · OCR · VLM · video · chem · math) unified by one orchestration surface. Research connectors hit PubMed · bioRxiv · Cochrane · SEC EDGAR · BLS · B Corp · CDP. Social listening from Instagram · TikTok · Google Trends · Digital Shelf. Right tool per format; one typed contract for all of them.
parsing/parsers/{tika,ocr,vlm,vision-llm,chem,math,video}/
Research · research/connectors/{arxiv,food_research,market_intel,sustainability}.py
Viral intent listener · delectable/social/workers/viral_intent_listener.py
Evidence quality grading at ingest time
PIM owns products + food intelligence + embeddings. CMS owns content + branding (per-tenant stylesheets resolved at request time). IA owns the Memgraph hypergraph with provenance per edge. Governance owns frameworks — NIST AI RMF mapped in code, AIRR scoring deterministic, evidence collected automatically.
ia/knowledge_graph/{graph_models,provenance,measurement_store}.py
NIST AI RMF in code · governance/assessment/nist_ai_rmf.py
Memgraph deploy · infrastructure/deploy/memgraph/ per cloud × env
Tenant branding · cms/branding/<slug>/stylesheet.css
Recommenders are composed score functions — not a black box. Twelve grocery sub-disciplines: food science, constraint, householding, pantry intelligence, personalization, semantic bridge, contextualization, consumption, fulfillment, data quality, embeddings, dietary. LLM-as-judge harness grades the agents on persisted runs.
ml/recommenders/{orchestrator,score_functions,agent_tool}.py
Propensity · ml/propensity/{session_propensity,signals,train_weights}.py
Eval harness · governance/evaluation/runner.py + 4 governance agents
Safety redactor in the loop · delectable/ml/safety/
FastAPI gateway fans out to module backends. One platform chrome across every console. Expo React Native mobile reuses the same agent layer the web does. Per-tenant branded surfaces ship from one codebase.
workflow/static/platform-chrome.js
Mobile agent · delectable/mobile/lib/agent.ts (shared with web)
UCP gateway · agent-callable endpoint per tenant
8 tenant portals · demo/public-*
infrastructure/customers/
Memgraph deploy scripts per cloud/env
parsing/actions.yaml step-action contract
NIST AI RMF mapped in code, not slides
Per-tenant Secret Manager / Key Vault paths
Identity + entitlements service · audit_store.py
session_audit.py in governance · SOC-2-ready foundations
Dual-remote git: origin (GCP) + earley (Azure)
You're not buying AI. You're buying a contract.
Every grocer has AI vendors knocking. The story is that Delectable's foundation through delivery is one composable platform with ratified contracts between every layer — so when you want to swap in your own analytics warehouse, route through your own identity provider, or bring your own LLM gateway, the contracts hold. That's the difference between a vendor demo and a platform you can build on for ten years.
Where to go next
Knowledge Graph Explorer →
130 nodes · 201 edges · 17 entity types. Drill three hops from any shopper, product, or research artefact.
Data Insights Dashboard →
10 tabs covering data pipeline · customer 360 · agent analytics · vector search · embeddings projector · catalog enrichment · user intelligence · knowledge graph · agent context.
Instacart-layered architecture →
Five-layer integration model showing where Delectable wraps Storefront Pro, Carrot Ads, IDP, and Connect — without forcing a replatform.
AI Governance pillars →
NIST AI RMF mapping · AIRR scoring · evidence-quality grading · safety redactor · governance evaluation harness.