AI SYSTEMS BUILDER & EXPERIMENTER
Robby Aliasa Akbar
Exploring AI systems, local LLMs, automation workflows, and practical tools
that actually work in real business operations.
Building what matters, and checking whether AI is truly useful in everyday work.
Local LLMs, API llms, Cloud LLMs, and Manymore.
I explore, build, test, and optimize AI systems, automation workflows, and LLM experiments to find what works in real conditions.
I also implement business automation leveraging AI and n8n workflows to streamline customer service and operational administration.
Selected Experiments
Selected Experiments
The 35B MoE model runs on an older architecture with 12GB of VRAM.
Testing whether 12GB of VRAM and an older GPU architecture can run open-source LLMs optimally without putting undue strain on the GPU.
Read EXP 001: 35B MoE on 12GB VRAMAutomation agent workflow for business research needs.
What does it actually take to optimally use AI as an autonomous research assistant? Is it just the model? As it turns out, no.
Read EXP 003: Automation Agent WorkflowCreating digital employees with the help of open-source LLMs.
Is it possible to set up customer service, operational admin, ads specialist, data analyst, and finance functions using only workflows and open-source LLMs, given adequate hardware and reasonable resource usage?
Read EXP 004: Digital EmployeesBuilding a Full Feature Services Business Website Using Only Local AI.
Can a full-feature business website with before-after slider, page animations, 44-item cost calculator, and full SEO be built end-to-end using only local open-source LLMs without cloud AI?
Read EXP 005: Full Feature Website Local AIBuilding a Self-Contained Invoice System Without a Database.
Can an internal invoice tool with live A4 preview, customer autocomplete, and selectable text-based PDF be built with only local LLMs — without MySQL, just .js + 44 lines PHP on shared hosting?
Read EXP 006: Invoice System No DatabaseFrom 30 Minutes to 5 Seconds: Automating Mass CV Screening Without In-System AI.
Can 1–5 CV PDFs be screened from 30-minute manual review to 5-second ranked shortlist — without hallucination — using pdf.js, 24-node n8n, and 70% rule on a private server?
Read EXP 007: Mass CV Screening 5sCapability
Capability
Business-Oriented Application
Directing AI capabilities toward real problems, practical workflows, and measurable value.
Technical Problem Solving
Investigating bottlenecks, testing variables, and iterating based on actual behavior.
AI Systems Building
Connecting model, infrastructure, tools, data, memory, and automation into usable systems.
AI Exploration
Exploring emerging AI capabilities and identifying practical limits.
Approach
Approach
I do not claim to know every answer in AI. I build, test, measure, investigate failure, and find what actually works.
Adaptive by Design
Adaptive by Design
AI systems are evaluated as complete systems: hardware, OS, runtime, inference engine,
model, context, and application.
The goal is not to limit experimentation to one platform, but to understand how AI
systems behave across different environments.
About
About
I'm a self-taught AI systems builder and experimenter. I explore local LLMs, inference, automation, agent architecture, and practical AI systems with a focus on finding what actually works.
Read Full ProfileContact
Have a problem worth exploring?
If you have a business problem, technical question, or AI opportunity that needs validation, feel free to reach out.