Skip to content

Elie Serge Tannous

User Journey Specialist

Ten years shipping customer experiences across retail, fintech, and grocery - now building production LLM systems and agentic automations on top of that operational depth. Ask my AI anything about my work.

>

Powered by Claude Sonnet 4.6 + RAG over my real projects

// AI in production

0
Projects shipped
personal + Mike Sport, end to end
0
Running on Claude / OpenAI
in production, with real users
0
RAG chunks indexed
powering the agent above
0K+
Products enriched by AI
Claude-powered PIM pipeline
ClaudeOpenAINext.jsTypeScriptPrismaPostgreSQLVercel AI SDKAnthropic SDKTailwindFlutterFirebaseBullMQRedisShopify APIExpresstRPCAuth.jsStreamlitPythonPlaywrightDockerRailwayNginxClaudeOpenAINext.jsTypeScriptPrismaPostgreSQLVercel AI SDKAnthropic SDKTailwindFlutterFirebaseBullMQRedisShopify APIExpresstRPCAuth.jsStreamlitPythonPlaywrightDockerRailwayNginx

// Featured AI work

Production AI, real teams

View all projects
AI inside2025Live

AI SEO Collection Optimizer

Autonomous SEO content engine that captures Lebanese organic search demand by generating high-confidence collection landing pages on a parallel VPS layer, grounded in Search Console signals, Shopify orders, and live catalog data, with a self-improving GSC measurement loop.

  • Claude Sonnet 4.6 production prompt engineering with strict JSON output
  • Multi-signal confidence scoring (GSC, sales, catalog, similarity)
  • RAG over Shopify catalog and historical performance
AILLMSEOfull-stackView case study →
AI inside2025Live

Marketing Intelligence Dashboard

Enterprise marketing analytics platform with real-time dashboards, OpenAI-powered insights via the Vercel AI SDK, and one-click PPTX stakeholder reporting.

  • Vercel AI SDK with OpenAI provider
  • Streaming LLM inference embedded in dashboard widgets
  • Prompt design for grounded, data-aware insight generation
AILLManalyticsfull-stackView case study →
AI inside2025Live

Product Data Enrichment Dashboard

AI-assisted product enrichment pipeline with confidence scoring, source-tracked LLM proposals, and a queue-based architecture that never silently overwrites master data.

  • Anthropic Claude SDK + provider-agnostic LLM abstraction
  • Structured-output prompting for enrichment fields
  • Confidence scoring per proposed value
AILLMautomationfull-stackView case study →

// about Elie

Want the full story behind these projects?

Decade of UX in retail, fintech, and grocery. Two years shipping production AI. 7 certifications. The complete timeline, skills matrix, and how I work.

Read about me

// JD Matcher (recruiters)

Powered by Claude + RAG

Hiring? Paste your job description below. Claude will retrieve the most relevant pieces of my real experience and produce a recruiter brief mapping JD requirements to specific shipped work, with project citations.

0 / 8000