AI Model Layer
LLM workflows, retrieval, evaluation, tool use, and private-model planning when the project needs more control.
ClaudeOpenAIGeminiopen-model evaluationmodel routingRAGevalsfunction calling
AI infrastructure, software, and public proof
Technology that makes the work believable.
When the reviews are still building, credibility comes from code you can read. Below are the platforms, AI systems, cloud patterns, and public repositories behind the work.
Personal GitHub: PascalAI2024
Public engineering profile with recent systems work including JarvisNano, Verrow, Kintunnel, ZiggyZag, and Claude Video.
Open personal profileBusiness GitHub: Ingenious Digital LLC
Company engineering organization for Ingenious Digital, production deployments, and selected public infrastructure proof. Private client repos are represented through case studies.
Open business orgPortfolio Case Studies
Client-facing breakdowns that translate code, architecture, and automation into business outcomes.
View the workWhat we can actually build with
A stack for production systems, not a buzzword list.
Agent Infrastructure
Human-supervised agent systems that can research, code, operate tools, and keep context across real work sessions.
Claude CodeMCP serversJarvisNanoOpenClawHermesbrowser automationGitHub toolsapproval gates
Applications
Production web and mobile software that loads fast, holds up under real traffic, and ships on a deadline.
React 18.3TypeScript 5.9Vite 8Vite+Next.jsNodeFastAPIPhoenixFlutter
Data & Automation
Operational systems that connect CRMs, inboxes, forms, payments, documents, and internal dashboards.
PostgreSQLSupabaseRedisGoHighLevelHubSpotStripen8nMakeZapierwebhooks
Cloud & Ownership
Deployments designed around portability, observability, security, and the right amount of managed service.
DockerTraefikGitHub ActionsDokployregistry.igddev.comVercelAWSS3/MinIOhybrid cloud
Interfaces & Hardware
Experimental systems where agents meet devices, voice, video, robotics, and real-world inputs.
agent control loopsembedded AI prototypesESP32voice agentsvideo understandingWebRTCWebSockets
Applied labs
Emerging tools, evaluated with production judgment.
OpenClaw, NeMoClaw, Hermes, and similar tools are strongest when they are tied to a real workflow: private AI, agentic operations, hardware control, model evaluation, or customer-facing automation.
OpenClaw / Agent Control
Useful for robotics-style control loops, local assistants, hardware interfaces, and supervised tool execution.
NeMoClaw / NeMo-Class AI Ops
A lane for model customization, evaluation, guardrails, and deployment planning when the project justifies it.
Hermes / Open-Model Experiments
Private or local model exploration for teams that need portability, cost control, or more ownership of inference.
How this helps clients
The point is not the stack. The point is shipped software.
You get a team that reasons about architecture out loud, ships fast, and hands back code you can read six months after launch instead of mystery you have to pay someone to decode.
Start with the business workflow, then choose the stack.
Use managed platforms when speed matters and portable systems when control matters.
Keep AI systems observable, reviewable, and grounded in real company data.
Document architecture and tradeoffs so clients are not trapped by mystery code.
Workflow first Integrated systems Global delivery
Bring the hard technical proof into the sales conversation.
We can turn public repositories, prototypes, internal tools, and case studies into a clearer credibility trail for serious prospects.