Three systems.
One thesis: deterministic gates first.

Business outcomes — TNG Shopper, 2024 – present

Traction

Commercial proof for the autonomous content pipeline. 11 paying enterprise retailers across 5 countries (currently live: Spain, Portugal, Israel; historical: United States, Mexico). Raised, signed, and shipped within the first 18 months.

$500K

Raised

From top-tier angel investors. Founders-First investor base.

$118K / $223K

Collected ARR / Booked ARR

Cash-realized revenue and signed contracts from enterprise retail clients.

$1.53M

Contracted ARR pipeline

From existing live and signed enterprise clients. Conditional roll-out as deployments expand to all client locations.

Recognition

Named to top-100 retail-tech startups of 2025. Independent industry recognition for the autonomous content pipeline + multi-agent architecture.

Revenue model: clients begin with a proof-of-concept on 10% of all locations, then expand to full rollout once SEO/AEO compliance and indexing performance are validated against the following KPIs. The Contracted ARR figure represents the full-rollout commitment potential from already-signed enterprise customers.

1. Local Store Visibility
  • Local Pack Inclusion Rate
    Top 3 local results for key terms per store area · tracked weekly
  • Target Keywords on Page 1
    ≥ 70% of keywords (e.g., "buy [product] near me")
  • Traffic Share from Primary Location
    ≥ 80% traffic from each store's geographic area
2. Local Product Page
  • Dedicated Local Page Coverage
    ≥ 60% of top-searched SKUs with a location-specific page (post filtration)
  • Store Locator Clickthroughs
    +20% increase from product pages · tracked via UTM or event triggers
3. Search Impression Proximity
  • Geo-Gridded Search Visibility
    Top 3 visibility in ≥ 70% of target grid points per location (SemRush Map Rank Tracker)
  • Proximity Search Coverage
    Local product pages triggered by "[product] near me" across all covered zip/postcodes

Post 90-day trial, validated KPIs unlock full-account rollout.

Case Study 01

Autonomous multi-agent DAG pipeline

A 7-node Directed Acyclic Graph generating localized product content for 11 enterprise clients across 5 countries. Human-supervised autonomous execution. Deterministic validation fires first; the LLM activates only if the gate passes.

Problem

Enterprise clients required localized, SEO-compliant product pages across dozens of cities. Manual creation is mathematically impossible at ~10.5M product-location combinations per month.

Approach

A fail-closed 7-node DAG with RAG-constrained generation (Google SPAM policies + E-E-A-T standards). Full architecture, deep-dives, and live trace are documented on the Pipeline page.

Result

260K+ pages

400K+ impressions across 3 client properties, 68.9% average pass rate per boundary, $0.0006/PDP end-to-end. 234 managed websites across 5 countries.

Why this exists

Multi-location retailers need unique, localized product pages for every item in every city they serve. At enterprise scale, this means millions to billions of pages — each requiring localized copy, structured data, and policy-compliant content. Manual creation doesn’t get close.

100K SKUs × 500 locations = 50,000,000 pages A mid-size retailer. Hypermarkets need billions.
Scale

Validated with SEO leadership at retailers operating 10–10,000+ store locations. The content gap is six orders of magnitude beyond manual capacity.

Zero friction

No CMS integration. No developer hours. No API setup from the client. Operates as an external, headless discovery layer that activates with a single switch.

Compliance-first

Every generated page carries audited structured data (Schema.org, JSON-LD) and policy-checked copy against retailer compliance rules — the prerequisite for being indexable inventory, not noise.

Verified evidence — Google Search Console

Aggregate results across 3 active client properties — verified via Google Search Console.

Enterprise Client A — Major European DIY Chain (Spain)
Google Search Console page indexing chart for Client A: 99.9K pages indexed in ~60 days
Page indexing
99.9K pages indexed

Hockey-stick from 0 → 99.9K in ~60 days. Autonomous pipeline output.

Google Search Console performance chart for Client A: 54.4K impressions and 614 clicks
Search performance
54.4K impressions · 614 clicks

1.1% CTR, avg position 10.9. Zero manual content creation.

Enterprise Client B — Largest Supermarket Chain (Portugal)
Google Search Console page indexing chart for Client B: 130K pages indexed
Page indexing
130K pages indexed

Steep growth curve from 0 → 130K. Largest property by page volume.

Google Search Console performance chart for Client B: 245K impressions and 2.19K clicks
Search performance
245K impressions · 2.19K clicks

0.9% CTR, avg position 8.7. Highest impression volume.

Enterprise Client C — Leading Discount Retailer (Spain)
Google Search Console page indexing chart for Client C: 30.2K pages indexed
Page indexing
30.2K pages indexed

Rapid ramp from 0 → 30.2K. Newest property in pipeline.

Google Search Console performance chart for Client C: 101K impressions and 2.33K clicks
Search performance
101K impressions · 2.33K clicks

2.3% CTR, avg position 8.7. Highest-converting property.

Live demo

End-to-end pipeline experience — the self-serve interface for autonomous content generation with human-supervised quality gates

Engineering trade-offs

Quality vs. cost

Validation that doesn’t spend a generation budget. Rule-based checks run before the SLM-as-judge layer ever fires — cheap rejections stay cheap. Mechanism documented on the Pipeline page.

Decision: deterministic-first validation, 68.9% pass rate.

Safety vs. throughput

Fail-closed design means ~31% of content is rejected. Intentional — no partial or low-quality content ever propagates downstream to production surfaces.

Decision: fail-closed at every boundary, zero tolerance.

Self-improvement

RLAIF data flywheel. DPO preference pairs generated from Node 6/7 evaluation signals for continuous model alignment.

Decision: closed-loop flywheel, autonomous preference pairs.

Scale vs. locality

5 countries require different linguistic, cultural, and regulatory context. Per-locale context injection increases prompt engineering complexity but eliminates fine-tuning per market.

Decision: context-first architecture, zero-shot locale adaptation.

Python Google ADK Vertex AI Langfuse
Case Study 02

Gemma 4 MoE — Vertex AI deployment forensics

March–April 2025 16+ hours · 30+ versions 20 failure modes

Deployed Google’s Gemma 4 26B-A4B-it Mixture-of-Experts model on Vertex AI with vLLM. Documented 20 distinct failure modes across 30+ deployment iterations in a public forensic runbook.

Problem

Gemma 4 MoE was newly released with no production deployment guides. Required custom vLLM builds, GCSFUSE container configs, and careful chat template engineering.

Approach

Systematic forensic debugging across 2 deployment cycles (16+ hours, 30+ versions). Every crash, OOM, and dependency conflict documented with root-cause analysis.

Result

20 failure modes

Forensically documented across 30+ iterations — proving the engineering diligence of developing stable, cost-effective MoE inference. Currently running stable base version while advancing toward full PRD: quality, cost efficiency, intelligence, and reliability.

Deployment timeline

v1 – v10
Container bootstrap failures

GCSFUSE mount crashes, OOM on model loading, vLLM version incompatibilities. Root cause: custom Google vLLM build required specific CUDA/PyTorch matrix.

v11 – v20
Chat template & tokenizer issues

Jinja template rendering errors, special token misalignment, multi-turn conversation state corruption. Required custom chat_template.jinja authoring.

v21 – v30
Stable base inference

Working configuration locked: vLLM 0.17.2rc1.dev133 + PagedAttention + custom entrypoint.sh. Base inference stable; advancing toward full PRD.

Cycle 2
LoRA enablement — blocked

Attempted multi-LoRA serving. Identified unsolvable dependency triangle between vLLM custom build, PEFT, and model architecture. Documented as community call-to-action.

vLLM PagedAttention Vertex AI GCSFUSE
Case Study 03

Antigravity-OS — AI agent governance kernel

Active 2025–present 8 core modules Apache-2.0

An open-source governance kernel for AI agents that enforces cost budgets, policy-as-code constraints, deterministic state tracking, and self-healing CI. The operational backbone for autonomous AI development environments.

Problem

AI coding agents operate without cost guardrails, state persistence, or policy enforcement. Runaway token costs and context-window rot are standard failure modes.

Approach

A governance kernel with cost enforcement (per-session and cumulative budgets), policy-as-code rules, and deterministic state tracking. MCP integrations provide tool access for managed agents.

Result

8 core modules

Provider-agnostic governance kernel. 6 plugin domains, 7 governance frameworks. Open-source on GitHub.

Python MCP Firestore GitHub Actions