---
id: video/jWJc_D67Vfw
type: video
title: 20260518 - Learning AI the Way I Learned NAV
summary: Areopa webinar (May 2026) in which Nabil Bammou, CEO of Azure Services, explains how he adopted AI using the habits he used to learn NAV. His three lessons are a green, orange, red rule for what to share, going deep on one tool for 90 days, and directing AI instead of chatting with it. He demos a Claude skill that builds a Business Central sales invoice layout from a customer PDF.
tier: community
language: en
tags:
  - ai adoption
  - learning patterns
  - privacy concerns
  - chatgpt
  - consultant workflow
  - hands-on learning
  - ai mindset
  - claude
  - mcp protocol
  - prompting strategy
  - deep learning methodology
  - 90-day iterations
system: copilot
review:
  state: reviewed
  by: opus
  at: "2026-10-07T23:20:39.334Z"
  flags: []
generated:
  at: "2026-10-07T23:20:39.417Z"
  pipeline: 0.2.0
  prompts:
    extract-video: 1
    summarize-video: 2
  input_hash: 47d43357dd0dbec67b53a4b8e2bbcadf6f88dfc7611f9f0d00ad3fe9387de6fb
evidence:
  - kind: video
    url: https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1353s
    title: "Claude Code: preview"
    date: "2026-05-19T09:59:16.000Z"
    commit: null
    t: 1353
    quote: Claude Code came out as a research preview, which took things to a whole new level
  - kind: video
    url: https://www.youtube.com/watch?v=jWJc_D67Vfw&t=322s
    title: 20260518 - Learning AI the Way I Learned NAV
    date: "2026-05-19T09:59:16.000Z"
    commit: null
    t: 322
    quote: my friend eventually gives me a tired look and says nabil i have no idea what
  - kind: video
    url: https://www.youtube.com/watch?v=jWJc_D67Vfw&t=420s
    title: 20260518 - Learning AI the Way I Learned NAV
    date: "2026-05-19T09:59:16.000Z"
    commit: null
    t: 420
    quote: That moment changed everything. I remember thinking, this is how a pro does it. I need to learn this, and I want to do
  - kind: video
    url: https://www.youtube.com/watch?v=jWJc_D67Vfw&t=454s
    title: 20260518 - Learning AI the Way I Learned NAV
    date: "2026-05-19T09:59:16.000Z"
    commit: null
    t: 454
    quote: All 400 pages. The more I read, the more the system made sense, and the more I wanted to go deeper.
  - kind: video
    url: https://www.youtube.com/watch?v=jWJc_D67Vfw&t=775s
    title: 20260518 - Learning AI the Way I Learned NAV
    date: "2026-05-19T09:59:16.000Z"
    commit: null
    t: 775
    quote: Even with all the resources I have, I cannot build a private AI that protects my data better than the big labs.
  - kind: video
    url: https://www.youtube.com/watch?v=jWJc_D67Vfw&t=850s
    title: 20260518 - Learning AI the Way I Learned NAV
    date: "2026-05-19T09:59:16.000Z"
    commit: null
    t: 850
    quote: I opened ChatGPT and I just start typing. I I'm Nabil. I am the CEO of Azure Services. We help ...
links:
  learn: []
  objects: []
  features: []
  topics: []
  localizations: []
  videos: []
  posts: []
  guidelines: []
video_id: jWJc_D67Vfw
channel: yt-areopa
source_name: Areopa webinars
url: https://www.youtube.com/watch?v=jWJc_D67Vfw
published_at: "2026-05-19T09:59:16.000Z"
duration_s: 3136
captions: derived
audience:
  - functional consultant
  - developer
  - decision maker
chapters:
  - t: 0
    title: Introduction and housekeeping
  - t: 269
    title: The Pedro Pascal moment - learning NAV through observation
  - t: 433
    title: Deep learning and career trajectory
  - t: 551
    title: The pattern that shapes careers
  - t: 645
    title: Three key learnings - the framework
  - t: 689
    title: From privacy-first to all-in with AI
  - t: 906
    title: Green, orange, red zone framework
  - t: 1030
    title: The skimming problem and AI journey
  - t: 1175
    title: Tool selection and the Rome crossroads moment
  - t: 1409
    title: The 90-day deep focus technique
  - t: 1569
    title: "Working with AI: from doer to director"
  - t: 1715
    title: The replacement ladder and director role
  - t: 2081
    title: AI-generated invoice layout in action
  - t: 2297
    title: Marathons over chats - working with AI as a partner
  - t: 2532
    title: Q&A - tools and deep learning approaches
  - t: 2765
    title: Wrap-up and personal stories
features:
  - name: AI as development partner
    status: unclear
    t: 689
    verified: false
    status_source: video
  - name: Deep learning methodology for complex systems
    status: unclear
    t: 433
    verified: false
    status_source: video
  - name: ChatGPT
    status: unclear
    t: 1030
    verified: false
    status_source: video
  - name: Claude Desktop
    status: unclear
    t: 1337
    verified: false
    status_source: video
  - name: Claude Code
    status: preview
    t: 1353
    verified: true
    status_source: video
  - name: MCP Protocol
    status: unclear
    t: 1337
    verified: false
    status_source: video
  - name: Code review agent pattern
    status: unclear
    t: 1677
    verified: false
    status_source: video
  - name: Business Central print layout skill
    status: unclear
    t: 1926
    verified: false
    status_source: video
  - name: Marathon conversation technique
    status: unclear
    t: 2297
    verified: false
    status_source: video
  - name: Meta prompting
    status: unclear
    t: 2468
    verified: false
    status_source: video
  - name: AI director mindset
    status: unclear
    t: 2502
    verified: false
    status_source: video
  - name: Orchestrator for knowledge management
    status: unclear
    t: 2620
    verified: false
    status_source: video
  - name: 90-day deep learning methodology
    status: unclear
    t: 2852
    verified: false
    status_source: video
objects_mentioned:
  - other code review agent
  - other Open Claw
  - other Hermes AI
  - other Obsidian
  - other Deep Seek
quotes:
  - t: 322
    text: my friend eventually gives me a tired look and says nabil i have no idea what
    check: fuzzy
  - t: 420
    text: That moment changed everything. I remember thinking, this is how a pro does it. I need to learn this, and I want to do
    check: exact
  - t: 454
    text: All 400 pages. The more I read, the more the system made sense, and the more I wanted to go deeper.
    check: exact
  - t: 775
    text: Even with all the resources I have, I cannot build a private AI that protects my data better than the big labs.
    check: exact
  - t: 850
    text: I opened ChatGPT and I just start typing. I I'm Nabil. I am the CEO of Azure Services. We help ...
    check: exact
---

# 20260518 - Learning AI the Way I Learned NAV

> Areopa webinar (May 2026) in which Nabil Bammou, CEO of Azure Services, explains how he adopted AI using the habits he used to learn NAV. His three lessons are a green, orange, red rule for what to share, going deep on one tool for 90 days, and directing AI instead of chatting with it. He demos a Claude skill that builds a Business Central sales invoice layout from a customer PDF.

[Watch on YouTube](https://www.youtube.com/watch?v=jWJc_D67Vfw) · Areopa webinars · 2026-05-19 · 52:16 · tier community · reviewed (checked by Opus)

## Overview

Nabil compares learning AI to learning NAV by reading all 400 pages of documentation. He describes moving from privacy-first caution to using ChatGPT with real company and project context, then testing Claude Desktop with MCP and using Claude Code (a research preview) for full-stack work.

He presents a framework: pick one tool and go deep for 90 days, treat AI as a co-worker who needs context, and act as a director who sets standards and verifies output. A demo shows a Business Central print layout skill that builds an invoice layout from a PDF mockup, produced in one long conversation, which he calls a marathon. The session ends with Q&A on tools and deep learning approaches.

## Key points

- Privacy rule (green, orange, red): share public info freely, decide quickly on internal strategy or client names, and never share bank details, passwords, credentials or NDA material. Your caution costs more than the risk.
- Pick one AI tool and go deep for 90 days. Do not evaluate competitors until you hit a real ceiling. Skills such as prompting and review loops carry over to other tools.
- Use a marathon conversation instead of one-off questions: explain the full task and context, define a good result, and work end to end in one conversation.
- Demo: a Claude skill for Business Central print layouts read a customer's PDF invoice, measured it to the millimeter, mapped invoice fields automatically and pushed the layout to a QA environment. The user then checked it side by side against the PDF. It took under 12 minutes of AI time and 2 minutes of the user's time.
- Director mindset (the replacement ladder): AI does the low-level work while you give context, set the standard, review and ship. AI can hallucinate confidently, so always verify.
- Have AI spawn a code review agent to audit its own scripts for cross-platform issues, such as Mac vs Linux grep differences, and for edge cases.
- Claude Desktop with MCP connects to tools like an Obsidian vault and Airtable. Claude Code came out as a research preview in early 2025.

## Chapters

- [0:00](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=0s) Introduction and housekeeping
- [4:29](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=269s) The Pedro Pascal moment - learning NAV through observation
- [7:13](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=433s) Deep learning and career trajectory
- [9:11](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=551s) The pattern that shapes careers
- [10:45](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=645s) Three key learnings - the framework
- [11:29](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=689s) From privacy-first to all-in with AI
- [15:06](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=906s) Green, orange, red zone framework
- [17:10](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1030s) The skimming problem and AI journey
- [19:35](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1175s) Tool selection and the Rome crossroads moment
- [23:29](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1409s) The 90-day deep focus technique
- [26:09](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1569s) Working with AI: from doer to director
- [28:35](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1715s) The replacement ladder and director role
- [34:41](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2081s) AI-generated invoice layout in action
- [38:17](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2297s) Marathons over chats - working with AI as a partner
- [42:12](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2532s) Q&A - tools and deep learning approaches
- [46:05](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2765s) Wrap-up and personal stories

## Features

| Feature | Status | At | Evidence |
|---|---|---|---|
| AI as development partner | status not stated, demoed | [11:29](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=689s) |  |
| Deep learning methodology for complex systems | status not stated | [7:13](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=433s) |  |
| ChatGPT | status not stated | [17:10](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1030s) |  |
| Claude Desktop | status not stated | [22:17](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1337s) |  |
| Claude Code | preview, demoed | [22:33](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1353s) | "Claude Code came out as a research preview, which took things to a whole new level" ([22:33](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1353s)) |
| MCP Protocol | status not stated | [22:17](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1337s) |  |
| Code review agent pattern | status not stated | [27:57](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1677s) |  |
| Business Central print layout skill | status not stated, demoed | [32:06](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1926s) |  |
| Marathon conversation technique | status not stated, demoed | [38:17](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2297s) |  |
| Meta prompting | status not stated | [41:08](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2468s) |  |
| AI director mindset | status not stated | [41:42](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2502s) |  |
| Orchestrator for knowledge management | status not stated | [43:40](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2620s) |  |
| 90-day deep learning methodology | status not stated | [47:32](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2852s) |  |

## AL objects mentioned

As heard in the captions. A name that matches one object page by exact type and name links to it; the others stay as named.

- other "code review agent" at [28:09](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1689s)
- other "Open Claw" at [43:04](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2584s)
- other "Hermes AI" at [43:15](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2595s)
- other "Obsidian" at [43:40](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2620s)
- other "Deep Seek" at [44:44](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2684s)

## Quotes

- [5:22](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=322s) "my friend eventually gives me a tired look and says nabil i have no idea what"
- [7:00](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=420s) "That moment changed everything. I remember thinking, this is how a pro does it. I need to learn this, and I want to do"
- [7:34](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=454s) "All 400 pages. The more I read, the more the system made sense, and the more I wanted to go deeper."
- [12:55](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=775s) "Even with all the resources I have, I cannot build a private AI that protects my data better than the big labs."
- [14:10](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=850s) "I opened ChatGPT and I just start typing. I I'm Nabil. I am the CEO of Azure Services. We help ..."

## Disclaimers in the video

- [22:33](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=1353s) preview: Claude Code came out as a research preview
- [43:15](https://www.youtube.com/watch?v=jWJc_D67Vfw&t=2595s) other: Hermes AI is described as the new kid in the block, mentioned as something to check out

Presenters (as heard): Nabil, Nabil Bammou, Nabeel, Luke van Vught, Dennis Storøy, Dan, Luke, Claude, Tina.