v1.3
Dashboard

Gabriel's AI Workspace

Your personal AI workflow hub — projects, learning, prompts, and logs in one place.

Total Projects
17
Work + Personal
Urgent Now
1
Hard deadline
Certifications
0/6
Completed
Prompts
In library
Sessions Logged
All time
Phase
1
Foundations

🔴 Immediate Focus

🔴 Urgent — Hard Deadline
W2 — Report Card Day Queue System
Deadline: 1 June 2026 · ~3 weeks remaining · Handle in dedicated session
🟠 High — After W2 Ships
W3 — Exam Results Analysis Tool + Awards Addon
Deadline: August 2026 · Existing Google Sheets as fallback
🟠 High — Parallel Task
W1 — Template Redesigns
No hard deadline · Can run alongside W2 in quiet moments

Tier Routing — Quick Reference

Local AI — Ollama
Unlimited · Free · Private
  • Formatting, rewriting
  • Grammar checks
  • Sensitive data tasks
  • Student / financial records
Gemini Free / Haiku
Fast · Low cost
  • General research
  • Google Docs drafting
  • Reminders, calendar
  • Short email drafts
Claude Projects
Your paid subscription
  • Project planning
  • Document consolidation
  • Moderate coding
  • Quality checking
Claude Sonnet / GPT-4
Reserve for these only
  • Initial app architecture
  • Complex analysis
  • Strategic planning
  • Difficult debugging
Never use Sonnet for
Wasted tokens
  • Formatting / summaries
  • Grammar checks
  • Template filling
  • Short email drafts

Standing Instruction: Before proceeding with any task, clarify all ambiguous assumptions and confirm understanding of the goal. Save this in every Claude Project system prompt so you never need to repeat it.

Projects

All work and personal projects, prioritised by deadline and dependency.

Learning Roadmap

Skills organised by project phase. Learn what each current project requires.

How to use this section: Each phase is timed around your project deadlines. Click a phase to expand it. Tick checklist items as you complete them — they save in your browser.

AI Tier Routing

Apply this before every AI message. This single habit extends your free-tier usage more than any other change.

Tier 0 — Local AI (Ollama)
Free · Unlimited · Private
  • Formatting, rewriting
  • Simple summaries
  • Data extraction
  • Grammar checking
  • Short translations
  • Message classification
  • ALL sensitive data tasks
Tier 1 — Gemini Free
Fast · Low cost
  • General research (no sensitive data)
  • Image descriptions
  • Google Docs drafting
  • Reminders + calendar checks
  • Quick factual lookups
  • Short email drafts
Tier 2 — Claude Projects
Paid subscription
  • Project planning
  • Document consolidation
  • Exam-related work
  • Lesson plan templates
  • Moderate coding
  • Structured analysis
  • Feedback analysis
  • Quality checking your writing
Tier 3 — Claude Sonnet / GPT-4
Reserve only
  • Initial app architecture
  • Complex multi-party analysis
  • Strategic planning
  • Difficult debugging
  • Resolving ambiguous requirements
  • Synthesising conflicting research
❌ Never Sonnet / GPT-4 For
Wasted tokens
  • Formatting
  • Simple summaries
  • Casual research
  • Template filling
  • Grammar checks
  • Short email drafts
  • File format conversion

Key Terms Glossary

AI Proficiency Certifications

Complete in sequence. Steps 1–4 during Phase 1 of the learning roadmap.

Your profile: You are an advanced AI Literacy and AI Tool Integration practitioner. Pursue certifications that reflect practical AI use, prompt engineering, and workflow automation — not engineering or data science.

Proficiency Record

How this stays updated (low-effort system):
1. Certification completions are logged automatically when you add a Session Log entry with a cert name.
2. Your Claude Project system prompt asks you to flag new completions each session.
3. LinkedIn auto-displays Microsoft and Google badges — screenshot and save to Obsidian /Certifications.
Update this record only when preparing your CV or before a job application.

Prompt Library

Click any prompt to view and copy. Filter by context, type, AI target, or source. Overlapping prompts are combined.

Logs

Quick notes per project and issues/decisions log.

Jot down quick observations per project. No formal structure required.

Reference

Setup guides, hardware specs, handover templates, and workflow prompts.

Full AI Stack

Subscribe to Claude Pro. Continue ChatGPT and Gemini on free tier. Google ecosystem automation handled by n8n + Gemini free. You do not need Gemini Advanced.
LayerToolCostPurpose
High ReasoningClaude Pro~USD 20/moApp frameworks, project planning, consolidation, complex analysis, debugging
High Reasoning (alt.)ChatGPT FreeFreeBrainstorming, negotiation analysis, initial prompts — keep as second opinion
Research + EcosystemGemini FreeFreeGeneral research, Google Workspace tasks, reminders, image gen, AI Studio
Teaching ContentNotebookLMFreeSlide decks, teaching videos, long doc synthesis, exam material prep
Coding IDEWindsurfFree tierApp refinement, debugging, deployment — receives framework from Claude
Local AIOllama + Open WebUIFree foreverLow-tier tasks, ALL sensitive data workflows — unlimited and private
Automationn8n (self-hosted)FreePayment alerts, WhatsApp logging, Gmail automation, Sheets updates
Version ControlGitHub DesktopFreeProtect app code; work with Windsurf
Knowledge BaseObsidianFreeHandover docs, SOPs, lesson templates, prompt library backups
Sensitive Data Policy: Student exam data and financial records (rental, tuition) must NEVER be sent to any cloud AI. Use local Ollama only. n8n automations involving this data must stay on the local home server and must not call external AI APIs.

Custom References

Step-by-Step Setup

Complete steps in order. Steps 1–4 on your main PC. Steps 5–8 on your OLD PC (home server). Copy-paste all terminal commands exactly.

Step 1 — Claude Pro + Projects

Go to claude.ai → profile icon → Upgrade to Pro → create Projects: (a) School & Teaching, (b) Rental & Tuition, (c) Project Coding. Add to every system prompt: "Before proceeding with any task, clarify all ambiguous assumptions and confirm your understanding of the goal."

Step 2 — GitHub Desktop

Download: desktop.github.com · Sign up at github.com · Create repository "my-ai-projects"

Step 3 — Windsurf

Download: codeium.com/windsurf · Sign up for free Codeium account · Connect to "my-ai-projects" folder

Step 4 — Obsidian

Download: obsidian.md · Create Vault "AI-Workspace" · Folders: /Handovers, /Prompts, /Projects, /SOPs, /Certifications

Step 5 — Docker on Old PC

Run on OLD PC only. Download: docker.com/products/docker-desktop · Enable WSL 2 · Restart · Verify:
docker --version

Step 6 — n8n

docker run -d --restart unless-stopped --name n8n -p 5678:5678 -v n8n_data:/home/node/.n8n n8nio/n8n
Access at http://[old-PC-IP]:5678 · Find IP: type ipconfig in Command Prompt → look for IPv4 Address

Step 7 — Ollama

Download: ollama.com/download · Then run:
ollama run mistral

Step 8 — Open WebUI

docker run -d --restart unless-stopped --name open-webui -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data ghcr.io/open-webui/open-webui:main
Access at http://[old-PC-IP]:3000 · Free, unlimited, private local AI interface

Old PC — Home Server Roles

RoleToolRAMNotes
Automation servern8n (Docker)~500MBRuns Gmail, WhatsApp, Sheets workflows 24/7
Local AI inferenceOllama + Mistral 7B~8GBGTX 1060 6GB VRAM — adequate for 7B models only
Local AI front-endOpen WebUI~200MBBrowser chat interface
Vector DB (future)Chroma / Qdrant~300MBFuture RAG for question bank and lesson plans
GTX 1060 has 6GB VRAM. Do not run models larger than 7B parameters on this hardware.

New Desktop — Generic Specification

ComponentMinimumPreferredReason
GPU12GB VRAM, CUDA16GB VRAMRun 13B+ local models and RAG pipelines
CPUModern multi-core, 2022+12+ coresDocker, IDEs, browser multitasking simultaneously
RAM32GB DDR564GB DDR5Multiple AI tools + Docker + browsers concurrently
Primary SSD1TB NVMe PCIe 4.02TB NVMe PCIe 4.0AI models and Docker volumes accumulate fast
Secondary2TB HDD4TB HDDBackups and archives
Motherboard2+ NVMe, Wi-Fi 6AM5 platformFuture CPU upgrade without replacing board
PSU750W 80+ Gold850W 80+ GoldBrand reliability critical — Seasonic recommended

Specific Recommendations (Malaysia ~RM10,000)

ComponentProductEst. Price (MYR)Reason
GPUNVIDIA RTX 4060 Ti 16GBRM 1,800–2,40016GB VRAM sweet spot for local AI
CPUAMD Ryzen 7 7700X / 7800X3DRM 900–1,400AM5 platform, long upgrade lifespan
RAMCorsair/Kingston 32GB DDR5-5600RM 400–550Upgradeable to 64GB later
SSDSamsung 990 Pro 2TB / WD Black SN850XRM 500–700Top endurance for AI model loading
HDDSeagate Barracuda 4TBRM 350–450Bulk backup storage
MotherboardASUS PRIME X670-P / MSI MAG X670ERM 700–1,000Wi-Fi 6E, 2 NVMe slots
PSUSeasonic Focus GX-850RM 500–650Most reliable brand — do not compromise
CoolerDeepCool AK400 / Thermalright PA120RM 150–250Excellent air cooling
CaseFractal Pop Air / Lian Li LANCOOL 216RM 250–400Airflow + quiet
Windows 11 HomeMicrosoft official licenceRM 450–600Check if old PC licence transfers first
Total Est.RM 6,000–8,400Within budget with buffer

How the Handover System Works

Rule: This dashboard and master document are your reference. The handover document is your session memory — paste it into new sessions, not the full document. You do NOT need to include this file when prompting for a handover.

This Dashboard

Permanent reference manual. Does not change between sessions. Reference by name only in new sessions.

Handover Document

Session memory. Short, specific, regenerated every session. Paste this into new sessions.

Handover Generation Prompt

Paste at the end of every session
"We are ending this session. Please generate a handover document based on everything we discussed and worked on today. Use this structure exactly:

---
HANDOVER DOCUMENT
Project: [fill in]
Date: [today's date]
Session AI: [Claude / ChatGPT / Gemini]
---

## Current State
[What exists right now — what works, what does not]

## Completed This Session
[Bullet list of what was accomplished]

## Known Problems or Blockers
[Errors, unresolved questions, things that failed]

## Decisions Made
[Choices that are now locked in]

## Pending Tasks (priority order)
1.
2.
3.

## Files Modified
[File name — location]

## Assumptions Made
[Anything assumed that should be verified]

## Risk Areas
[Things that could go wrong]

## Recommended Opening Prompt for Next Session
[Write the exact message to paste at the start of the next session]
---

Be specific and complete. The person reading this will have no memory of today's session."

Context Restoration Prompt

Paste at the start of each new session
"I am continuing a project from a previous session. Here is my handover document:

[PASTE YOUR HANDOVER DOCUMENT HERE]

Please:
1. Confirm you understand the current state, pending tasks, and known problems
2. Ask me one clarifying question if anything is unclear
3. Do not begin any work until you have confirmed your understanding

My standing instruction: clarify all ambiguous assumptions before proceeding with any task."

App Development Pipeline

Paste into Claude Projects → Project Coding
You are helping me build a desktop application for Windows. I will describe what I want the app to do. Produce a complete, structured app framework I can take into Windsurf for refinement and deployment.

For every app I describe:
1. Confirm your understanding before writing any code
2. Ask 3–5 clarifying questions about functionality, users, and edge cases
3. Once confirmed, produce:
   (a) a clear file structure
   (b) all necessary files with full code
   (c) a README with setup instructions
   (d) a PyInstaller command to build the .exe
4. Flag any assumptions you made
5. Highlight areas Windsurf will likely need to refine

My app idea: [DESCRIBE IN PLAIN LANGUAGE]

Multi-Option Analysis

For vendor comparisons, tool evaluations, proposal analysis
You are helping me evaluate and compare [NUMBER] options for [BRIEF PURPOSE].

Evaluation criteria:
1. Price and value for money
2. What is included and excluded
3. Reliability and track record
4. Quality of communication and responsiveness
5. Flexibility or customisation options
6. Any red flags or concerns

I will provide details one at a time. After all options are given:
1. Build a structured comparison table
2. Identify the top two with clear justification
3. Flag missing information to request
4. Suggest 3 questions to ask each provider
5. Give a recommended decision with reasoning

Confirm you understand before I begin.

Feedback Analysis

For survey responses, event feedback, student feedback
You are helping me analyse [TYPE OF FEEDBACK].
I will paste [NUMBER] responses below. After reviewing all:
1. Top 3 positive themes with examples
2. Top 3 concerns / improvement areas with examples
3. Urgent or sensitive issues requiring immediate attention
4. 3 concrete action items based on the feedback
5. 2-paragraph summary for [AUDIENCE]

Do not invent or infer beyond the responses. Flag unclear items.

Feedback: [PASTE HERE]