The way in opens the moment the set has loaded.

Architecture of IntelligenceDrawing set · Akshay Bajpai

Akshay BajpaiArchitect of systems · Builder of intelligence

This site is a drawing set. Every section is a numbered sheet on the plan. Open one, or press / for the index.Open one, or use the sheet index.

lib/plates.tsPLATES: Plate[] = 8, 7 placed on G-000plan 2080 × 900 units, 9 refs resolvedKeyPlan.tsx, client, no data fetch

Key plan7 sheets, stacked below

A-101The ArchitectBiography, trajectory, and operating principles1Elevation along the career datum2026Lead Full-Stack AI EngineerForward deployment2026AI Lead · video intelligenceDefense-adjacent2025Senior AI ConsultantFinance & health2025Founding EngineerRestaurant SaaS2023Data Scientist IIInsurance2021MSc Artificial IntelligenceDistinctionGrid A/1420 × 290Architecturalroute/about/sourceapp/about/page.tsxidaboutdisciplineA · Architecturalrectx 0 y 0 w 420 h 290refsR-301 W-400 C-700entries6Rev C1:1Open sheet →R-301ResearchPublished work and experimental directions2Benchmark plot, nine modelsML for Medical Diagnosis, Ch. 17Springer 2024Alzheimer’s classification thesisOASISMSc AI · 9.8/10, distinctionLviv PolyGoverned agentic retrievalCurrentGrid C/1420 × 270Researchroute/research/sourceapp/research/page.tsxidresearchdisciplineR · Researchrectx 0 y 310 w 420 h 270refsA-101 W-400entries4Rev B1:1Open sheet →S-201Structural PrinciplesThe decisions that outlast implementation3Section through a governed platformThe operator is the final authorityInvariantEvery output traces to a versionInvariantGateway-first, tiered routingPatternServices bounded by failure domainPatternLocal parity with productionRuleThe best dependency is the one you skipRuleGrid E/1420 × 290Structuralroute/architecture/sourceapp/architecture/page.tsxidarchitecturedisciplineS · Structuralrectx 0 y 600 w 420 h 290refsW-400 B-500 E-600entries6Rev C1:20Open sheet →W-400WorksCase studies, as built4Exploded axonometric of a platformW-401Forward-Deployed: Multi-Tenant Fertility & Surrogacy AI3 coordinated AI surfacesW-402AIDA: Health Programme Intelligence You Can Brief FromDeterministic KPI engineW-403Agentic Video Intelligence for 24/7 Operations~70% less analyst interventionW-404Neural Map Personal Site: Spatial Navigation as Homepage5 interactive clustersW-405AURIXA: Conversational AI Orchestration at Scale8 Python services + API gatewayW-406Alzheimer's Classification: Master's Thesis Research9 models comparedW-407Agentic Finance & Multimodal Healthcare AI~60% fewer manual touchpointsW-408Publishing AI Automation: Multi-Channel Support at Scale5 communication channelsW-409Restaurant SaaS Forecasting at Scale200+ restaurant pilotW-410Insurance Document Intelligence on AWS95%+ extraction accuracyW-411Clinical NLP from Unstructured EHRs47+ structured variablesGrid B/4740 × 400Worksroute/work/sourceapp/work/page.tsxidworkdisciplineW · Worksrectx 460 y 0 w 740 h 400refsS-201 R-301 C-700entries11Rev D1:50Open sheet →E-600EssaysLonger arguments about systems, cost, and trust5Detail of a leverage pointE-601The Model That Refuses to Draw2026.10E-602Minimalism as Engineering2025.03E-603The Architecture of Trust2025.02E-604Why Performance Is a Feature2025.02E-605The Cost of Convenience2025.01E-606What Systems Thinking Actually Is2025.01Grid D/4740 × 225Essaysroute/essays/sourceapp/essays/page.tsxidessaysdisciplineE · Essaysrectx 460 y 420 w 740 h 225refsB-500 S-201entries6Rev B1:1Open sheet →B-500Field NotesWhat the work taught, written down while it was fresh6Traverse of the field notesB-501Reinforcement Learning After the Reward Model2026.10B-502World Models, As Issued: The State of the Set in October 20262026.10B-503Experimental UI as an Engineering Discipline2025.03B-504Architecture Design for Healthcare AI2025.03B-505AI in Restaurant Automation2025.02B-506Systems Thinking for Founders2025.02B-507Performance Engineering on Static Hosting2025.02B-508Building SaaS with a Zero-Dependency Mindset2025.02B-509DNS-Level Ad Blocking. System Design2025.01B-510AI Infrastructure Philosophy2025.01Grid B/6460 × 400Field Notesroute/blog/sourceapp/blog/page.tsxidblogdisciplineB · Field Notesrectx 1240 y 0 w 460 h 400refsE-600 S-201entries10Rev C1:1Open sheet →C-700CorrespondenceOpen a line7Transmittal, in elevationhello@akshaybajpai.comEmaillinkedin.com/in/ax5hayLinkedIngithub.com/ax5hayGitHubGrid D/6460 × 225Correspondenceroute/contact/sourceapp/contact/page.tsxidcontactdisciplineC · Correspondencerectx 1240 y 420 w 460 h 225refsA-101 W-400entries3Rev BNTSWrite to me →

General Notes

Organisation names are generalised throughout. The engineering is specific.
Metrics are measured in production unless annotated otherwise.
This set is issued as a static export. No server is in the loop.
Drawings are live: switch Artifact / Annotated / Raw with the selector, or press D.

InstrumentsDrag to pan · Scroll to zoom · Click any sheet to open it

General arrangement

G-000 Key Plan — General arrangement of the complete set
A-101 The Architect — Biography, trajectory, and operating principles
R-301 Research — Published work and experimental directions
S-201 Structural Principles — The decisions that outlast implementation
W-400 Works — Case studies, as built
E-600 Essays — Longer arguments about systems, cost, and trust
B-500 Field Notes — What the work taught, written down while it was fresh
C-700 Correspondence — Open a line

Works · details

W-401 Forward-Deployed: Multi-Tenant Fertility & Surrogacy AI — Three coordinated chatbots, a governed NL-to-SQL reporting agent, and a shared LLM platform layer across multiple client programs, with a roadmap to production on AWS CDK.
W-402 AIDA: Health Programme Intelligence You Can Brief From — Turning facility assessment rows into screening rates, management gaps, and district rollups, with optional LLM narratives that never invent the numbers.
W-403 Agentic Video Intelligence for 24/7 Operations — Real-time CCTV triage with LangGraph and MCP: Kafka ingestion, sub-200ms paths, and defense-grade on-prem deployment.
W-404 Neural Map Personal Site: Spatial Navigation as Homepage — A scroll-driven Three.js constellation where clusters replace nav bars, with hover, fly-in, and iframe overlays for essays, work, and writing.
W-405 AURIXA: Conversational AI Orchestration at Scale — Multi-tenant microservices platform for real-time LLM routing, RAG, agent execution, safety guardrails, and voice, built as a production Turborepo monorepo.
W-406 Alzheimer's Classification: Master's Thesis Research — Benchmarking nine machine learning models on OASIS longitudinal biomarkers for dementia detection: rigorous preprocessing, grid search, and clinical interpretability.
W-407 Agentic Finance & Multimodal Healthcare AI — LangGraph workflows across portfolio logic and onboarding, plus QLoRA clinical imaging pipelines on HIPAA-aware AWS with hybrid RAG at sub-800ms p95.
W-408 Publishing AI Automation: Multi-Channel Support at Scale — Multi-channel author query automation with intent classification, hybrid RAG, unified identity across WhatsApp and email, and confidence-gated human escalation.
W-409 Restaurant SaaS Forecasting at Scale — Founding-engineer delivery for inventory and demand sensing: XGBoost and Prophet, Node APIs, Next.js ops dashboard, and 2M+ events/day pipelines.
W-410 Insurance Document Intelligence on AWS — Multimodal RAG, Claude and GPT-4 Vision, LayoutLMv3 extraction, and ensemble underwriting models: 95%+ accuracy at 10K+ queries/day.
W-411 Clinical NLP from Unstructured EHRs — BioBERT and spaCy NER pipelines extracting 47+ structured variables at 91.5% accuracy, across 5K+ documents/day, with risk scoring at scale.

Essays · details

E-601 The Model That Refuses to Draw — Generative models predict pixels; JEPA predicts what the pixels mean. Why the refusal to reconstruct is the most important architectural decision in world models, and what it teaches anyone who builds systems.
E-602 Minimalism as Engineering — Why less is more in system design: fewer dependencies, fewer features, fewer moving parts, and how to get there without sacrificing capability.
E-603 The Architecture of Trust — How system design either builds or erodes trust, and what to optimize for when the user can’t see inside the black box.
E-604 Why Performance Is a Feature — Performance is not a nice-to-have. It’s a product requirement that affects conversion, retention, and trust. Here’s the case and the practice.
E-605 The Cost of Convenience — Why every dependency and every abstraction has a price, and how to pay it consciously.
E-606 What Systems Thinking Actually Is — A long-form look at systems thinking: feedback loops, leverage points, and why it’s a discipline, not a buzzword.

Field notes · details

B-501 Reinforcement Learning After the Reward Model — How reasoning models are actually trained now: verifiable rewards instead of learned ones, GRPO and its descendants, RL compute that scales on a curve, and agents trained inside environments. With the engineering lessons for anyone shipping LLM systems.
B-502 World Models, As Issued: The State of the Set in October 2026 — A field survey of where world models actually stand: V-JEPA 2.1, LeJEPA, Dreamer 4, Genie 3, Marble and Atlas, Cosmos, and a billion-dollar bet in Paris. What shipped, what it cost, and what it is for.
B-503 Experimental UI as an Engineering Discipline — Why treating experimental UI and creative front-end as engineering, not “designer code”, raises the bar for both art and performance.
B-504 Architecture Design for Healthcare AI — How to design AI systems in healthcare: compliance, safety, and the primacy of the clinician in the loop.
B-505 AI in Restaurant Automation — Where AI actually helps in restaurant operations, order prediction, inventory, and kitchen flow, and where it’s hype.
B-506 Systems Thinking for Founders — Why founders who think in systems ship better products and make fewer irreversible mistakes.
B-507 Performance Engineering on Static Hosting — How to hit Lighthouse 95+ and sub-second FCP when you have no server: budgets, critical path, and discipline.
B-508 Building SaaS with a Zero-Dependency Mindset — Why minimizing dependencies is a strategic advantage in SaaS, and how to do it without reinventing the wheel.
B-509 DNS-Level Ad Blocking. System Design — How to design a DNS-based ad blocking system: architecture, tradeoffs, and what you give up when you block at the resolver.
B-510 AI Infrastructure Philosophy — Why the best AI systems treat infrastructure as a first-class product, and how to think about reliability, scale, and operator experience.