Sub-second
Available for select product work · 2026
AI systems for the messy middle.
I’m Azmi Muwahid. I design and ship agentic workflows, RAG systems, and realtime interfaces where model behavior, product UX, and backend reliability have to agree.
Proof over promises
Reviewable
FutureLab AI outputs
Server-only
Portfolio CMS integration
Selected work · 01
Built systems.
Measured tradeoffs.
Not just final screens. Each case study traces the constraints, architecture, decisions, and operational details behind the outcome.
Live product 2023-2025 · Production B2B mentoring and learning platform
FutureLab AI Workflows
AI-assisted transcription, summarization, and workflow automation for mentoring operations and B2B delivery.
Outcome
Helped product and operations teams turn session data into summaries, follow-ups, and delivery visibility.
Ruby on RailsPostgreSQLAWSOpenAI
System / 02 AI-Powered Website Builder
2024-2025 · Production-ready AI-Powered Website Builder
Kilat.store
An AI-powered website builder allowing Indonesian small-medium businesses (UMKMs) to construct their business landing pages in 60 seconds.
Outcome
Successfully built a multi-tenant platform with visual editor capabilities and automated generation pipelines, lowering the digital commerce entry barrier.
Next.js 15Puck EditorAstro 4Ruby on Rails 8
System / 03 Real-time AI coaching platform
2025 · Shipped MVP Real-time AI coaching platform
Codexia Live
A real-time coding coach that watches friction signals and responds with progressive hints instead of handing over answers.
Outcome
Converted an open-ended AI tutor idea into a low-latency coaching loop with measurable intervention points.
SvelteKitTypeScriptWebSocketsGoogle Cloud Run
System / 04 Agentic B2B CRM
2026 · Active Beta Agentic B2B CRM
The Beddo AI-CRM
An agentic B2B CRM for the mattress and bedding industry that balances autonomous AI customer interactions with transparent telemetry.
Outcome
Engineered a next-generation CRM inbox where human operators oversee autonomous lead extraction agents via live Model Context Protocol streams.
Next.js 16tRPC v11Better AuthDrizzle ORM
Systems thinking · 02
An AI system is a loop.
Signals become context, policy, tool calls, interface feedback, and eventually a measurable product outcome. Select a layer to inspect the flow.
Active layer
User signal
Prompt, voice, pause, click, or business event enters the system.
Working stack · 03
Tools follow the system.
The tools I use when model behavior, product UX, backend reliability, and cost controls all matter.
TypeScript
React
SvelteKit
Node.js
Ruby on Rails
PostgreSQL
AWS
Docker
Tailwind CSS
OpenAI
TypeScript
React
SvelteKit
Node.js
Ruby on Rails
PostgreSQL
AWS
Docker
Tailwind CSS
OpenAI
The AI Edge
Agentic WorkflowsRAGTool CallingVector DatabasesLLM Orchestration
The Real-Time Layer
Binary Audio StreamingWebSocketsWhisper (Transcription)Live State Management
The Core Stack
TypeScript 5Ruby on RailsNext.js 15 (App Router)tRPCSvelteKit
The Infra
AWS (ECS/Lambda/S3)Google CloudTerraformDocker
Languages
TypeScriptRubyPythonGo
Databases
PostgreSQLRedisPineconeElasticsearch
Available for hire
Let's build
something intelligent.
Whether you want to talk about tool_calls, the future of RAG, or why Ruby on Rails is still a powerhouse for AI backends—reach out.
Email Me azmimuwahid@gmail.com
Location South East Asia (Remote)