Single source of truth for Delectable AI’s product demos, architecture deep‑dives, and technical thought‑leadership content. Linked from cep-dai, firstmile-dai, florida-funders-dai, and other branded portals so we maintain one canonical version of every asset.
Live retailer demos showing the Delectable AI agent embedded in real-world commerce surfaces.
The actual shopper-facing storefront with shoppable videos, creator spotlights, trending signals, AI shopping assistant, and a CMS that composes it all per tenant. Opens in a new tab.
delectable-prototypes.web.app/social-experience →Personalized agentic landing experience with embedded chat assistant.
integrated-home.htmlProduct detail view with agent-driven recommendations and substitutes.
integrated-product.htmlFull agent-driven shopping flow from intent to cart.
integrated-shop.htmlPersonalized category browse with propensity-driven ranking.
ge-category.htmlThe platform stack, built on the Agentic Commerce Protocol (ACP). Each module is independently entitled and deployable; tenants opt in via the multi-tenant config in infrastructure/customers/<slug>.json.
The contract: A2A capabilities, MCP tools, A2UI events. The model- and channel-portable foundation for every other module.
acp-overview.htmlWalk through how Google Search calls a grocer endpoint hosted in the grocer's own GCP project. Watch which services light up; track the consumption attributed to the customer's billing.
ucp-interactive.htmlHow AXP emits structured conversational attributes (MerchantListing JSON-LD, Q&A chunks, variant matrices, comparison tables) so ChatGPT, Perplexity, Gemini & Claude cite retailer SKUs in agentic answers. Princeton/GT KDD 2024: up to +40% citation lift. Includes live SKU explorer.
ai-ready-catalog.htmlThree pillars in one frame: Food Intelligence Graph + Shopper Memory + Cart Builder. Switch personas, run a query, and watch the unified context object mutate in real time as the live agent streams events. Hover any pillar to focus its slice.
unified-commerce.htmlThe Social Shopper persona walks through home → category → product → cart with the underlying UCP request firing live in the engine panel. Bridges the shopper experience and the protocol surface in one view.
persona-studio.html?persona=socialAgentic retail media network. Brand-attribute targeting and live ad placement.
ads-interactive.htmlFull RMN platform walkthrough: campaign authoring, attribution, ROAS reporting.
ads-platform-demo.htmlShoppable discovery pitch: viral trend detection, creator-driven cart, real-time intent signals. For the actual product, see Composable Social Experience above.
social-interactive.htmlMulti-tenant content + branding + entitlement backbone for every console.
cms-overview.htmlThe four-pillar substrate that earns trust by construction: hard rules (allergen, dietary, recall), regulatory compliance (FDA · FTC · state, pre-validated at emit), audit trail (every decision logged, every claim traceable in <5s), and model provenance (constrained to the tenant's verified live catalog — never invented). Built into the same execution path as the agent.
ai-governance.htmlThe Food & Shopper HyperGraph — the moat under everything.
delectable-knowledge-graph.htmlDrill from any node — shopper, product, recipe, ingredient, dietary, flavor — into its semantic neighborhood. Inspect edge metadata (purchase frequency, substitution similarity, allergen risk). See the equivalent Cypher that would fire against Memgraph. Hybrid: static dataset by default, with a live-proxy toggle when configured.
graph-explorer.htmlThe levers a merchandiser or marketer uses to steer the agent. Three tabs — Levers (promotion, substitution, audience, brand safety, workflow), Test (A/B harness, holdouts, p-value tracking), and Attribution (multi-touch paths, ROAS matrix, incremental lift). Grounded in ads/ + workflow/ subsystems. Every change auditable.
How retailer data, agent calls, and module surfaces tie together end-to-end.
delectable-integration-flows.htmlThe polished consumer + admin experiences that the platform ships with. Investors comparing the Persona Studio (curated mocks) against the production-grade admin console see both the storytelling and the actual product.
Deep-dives written for engineering and product diligence audiences.
Click through the full system topology: agents, graph, data layer, deploy targets.
architecture-interactive.htmlHow the agent reasons, routes between models, and grounds in the HyperGraph.
eagle-ai-agent-architecture.htmlPropensity model training, feature store, household GNN, attribute sensitivity.
ml-personalization-pipeline.htmlLive shopper-behavior analytics on the production data warehouse.
data-insights-dashboard.htmlHallucination scorecards, accuracy benchmarks, latency budgets.
evaluation-tracker.htmlSearch-era grocery vs. agentic grocery — side-by-side outcomes.
before-after.htmlTechnical thought leadership: how we build defensible AI for grocery without falling into LLM-wrapper traps.
The full thesis in one read.
challenge-executive-summary.htmlHow the agent is grounded, routed, and evaluated end-to-end.
challenge-ai-pipeline.htmlThe defensibility argument: HyperGraph is the moat.
challenge-vs-chatgpt.htmlWhere the prompt, the graph, and the model interact.
challenge-llm-levers.htmlGraph neural networks for household-level inference.
challenge-householding-gnn.htmlHow rankings stay relevant without becoming homogenous.
challenge-algorithmic-curation.htmlArchitecture for engineering audiences.
challenge-technical-deep-dive.htmlThe unit-economics story behind the platform.
challenge-delectable-value.html
