Joint Cognitive Control & Intelligent Design Company
Defined systems. Intelligent control.
JCCIDC is a systems engineering company focused on one problem: making intelligent systems behave. Models are powerful. Agents are capable. Neither is trustworthy by default. The gap between a demo that works once and a system that survives real production is where we operate.
We design the architecture, write the constraints, and build the verification layers that turn raw capability into something a business can depend on. Every system we ship is constraint-first, production-first, and instrumented for verification — because correctness matters more than cleverness, and trust is earned in the logs, not the pitch deck.
Our work spans the full depth of software engineering: AI-integrated community platforms with Claude-driven admin consoles (23+ production tools, auth-gated WebSocket terminals), desktop AI workspaces combining cloud Claude with local Gemma 4 via Ollama, language implementation (compiler from scratch in TypeScript), desktop applications (Tauri v2 + Rust), autonomous content pipelines (n8n + AI), full-stack operations platforms (Express.js + Supabase), and payment/subscription systems. The common thread is systems thinking — every project is designed as an integrated system, not isolated features.
Incorporated 2023. Built on a decade of shipped systems. 11 production systems. 7 Claude integrations.
AI & Claude Integration
Local LLM & Automation
Systems & Languages
Platform & Infrastructure
How JCCIDC Works With AI
Claude as Primary Dev Tool
Every project in this portfolio was built with Claude Code as the primary development environment. Not as an assistant — as the tool our engineers think through. Custom skills encode engineering methodology into repeatable processes.
MCP & Tool Integration
Production MCP server integrations: Desktop Commander for system ops, n8n for workflow automation, custom servers for project-specific tooling. Claude interacts with external systems as a first-class capability.
Agent Architecture
Implemented all 7 patterns from Anthropic's agent guide. Built FORGE (pre-authorization policy engine for autonomous AI agents) and multi-channel AI command routing infrastructure. This is where AI engineering is heading.
The Journey
Origin. Community-focused, open-source script development for controller-input platforms. Constraint-driven from day one — 2KB memory budgets, 50ms execution frames, no room for waste. Work shared freely with the community, not commercialized. This foundation shaped everything that came after.
Script library depth. Shipped dozens of production scripts to an active community using state-machine architectures, adaptive input filtering, and OLED interface design. Built a reputation through technical contribution rather than marketing. All output open-source, freely distributed.
Community infrastructure. Built a production subscription bot with full PayPal webhook lifecycle, tiered Discord role provisioning, multi-tenant audit logging, and marketplace API synchronization. Systems that ran for years without intervention. Began moving into full web applications and cross-platform tooling.
Joint Cognitive Control & Intelligent Design Company formally incorporated. Focus shifted toward structured intelligence systems. Built the first Claude API integration into a Tauri + Rust desktop application — knowledge base injection, dynamic prompt assembly, domain-specific code generation in a constrained scripting environment.
Authorized developer milestone. Reached authorized developer status on the official community marketplace — 17+ shipped scripts, 60,000+ community downloads. Adopted Claude Code as the primary development environment across every project. Began building the production Claude tooling and deep pipeline work that would ship in 2025.
Delivery year. Shipped the autonomous content pipeline (11 sources → narrated video → multi-platform distribution, 180+ assets/month). Built a production TypeScript compiler pipeline with full language coverage for a constrained scripting environment. Shipped a full-stack CRM/TMS with multi-tenant Supabase RLS, .files (Tauri v2 + Rust Windows file manager replacement), FORGE (AI task runner with pre-authorization policy engine), a Smart Recommendation Engine for Claude Code plugins, and hands-on implementations of all 7 Anthropic agent patterns. Refreshed the Jimmy CC community platform with a streaming Claude admin assistant, 23 production tools, a WebSocket PTY terminal, and interactive script tooling.
Dual-mode AI + brand consolidation. Shipped Community Dashboard — a Tauri v2 desktop AI workspace with a dual-mode LLM runtime (cloud Claude for source-grounded drafting, local Gemma 4 via Ollama for private knowledge queries). Full brand refresh and jccidc.com rebuild.
Philosophy
1. Correctness before impressiveness
Software must behave correctly before it looks impressive.
2. Constraint-first engineering
Platform policies, API limits, and technical constraints are engineering inputs, not obstacles. The best solutions work within constraints rather than fighting them.
3. Production-first mindset
All systems built with production requirements from day one: logging, error monitoring, automatic recovery, graceful degradation.
4. AI as a system component
Not a novelty — a tool with defined inputs, outputs, and failure modes like any other system component. Integrated into architecture, not appended to it.
5. Verification as a feature
Nothing is “done” until its behavior is provable under load. Trust is earned in the logs, not the pitch deck.