I turn ERP data into one view for leadership, with every metric defined once. Then I automate the work around it, and a person approves every change.

How I work

From the question to the decision.

Two ways I work, step by step. Tap a step to see what happens there, with a real example.

Dashboards, from question to decision

  1. Step 1

    Ask the right question

    I start with the decision, not the chart. Who reads the report, what they decide, and which number tells them.

    Real example12 business areas

    Leadership needed one view of the business. The first executive dashboard covers 12 business areas.

    See the case
  2. Step 2

    Pull ERP data

    Reports run on live ERP data, the company’s core business records. No exports pasted by hand.

    Real exampleData up to 5 days old → live

    Leadership had been reviewing sales data up to 5 days old. The report now runs on live ERP data.

    See the case
  3. Step 3

    One model

    One shared data model holds the business definitions. Every report reads from it, so a metric means the same everywhere.

    Real example1 model, every production report

    Every production report now uses one shared model. Standard metric names ended conflicting numbers between departments.

    See the case
  4. Step 4

    Build the dashboard

    The first page answers the question. Each figure shows where it stands against plan, and the detail sits behind it.

    Real example10+ dashboards and reports

    10+ Power BI dashboards and reports, from sales and invoicing to inventory and production.

    Open the dashboards
  5. Step 5

    Check against SQL

    Before a report goes out, its totals are checked against SQL on the source data. Numbers get checked before they get published.

    Real example3 to 4 days → under an hour

    The monthly sales meeting report went from 3 to 4 days to under an hour, checks included.

    See the case
  6. Step 6

    Leadership decides

    The report is there for a decision. It shows the gap, who owns it, and what to fix first.

    Real example~25M AED at-risk stock found

    The inventory risk analysis flagged 26% of raw material items as high risk, with ~25M AED of stock at risk, early enough to act.

    See the case

AI automation a person signs off

  1. Step 1

    Plain-language request

    Work starts from a normal request. No special format and no form to fill in.

    Real exampleCustomer change requests

    The pricing engine starts from customer change requests on modified HVAC units, such as a bigger fan or a new casing.

    See the case
  2. Step 2

    AI reads and proposes

    AI reads the request and proposes what to change. It never does the fixed math.

    Real example37 contradictions found

    A review found 37 contradictions in the method documents. The old AI handled about 70% of fixed calculations unreliably.

    See the case
  3. Step 3

    Python does the math

    Every calculation runs in Python. Automated tests check the rules each time the code changes.

    Real example446 automated tests

    The pricing engine now runs on 446 automated tests. It closed a ~97K AED material costing gap.

    See the case
  4. Step 4

    A person approves

    The proposal goes to a person, who approves or rejects it. Anything a person must confirm is flagged.

    Real exampleEvery change signed off

    AI use stays inside company security rules: approved connectors, tools that run locally, and a person signing off every change.

    See the case
  5. Step 5

    Scheduled run

    Recurring work runs on a schedule. Data pull, checks and the finished output, every time.

    Real example3 to 4 days → under an hour

    The monthly sales meeting report runs as a scheduled AI workflow. Prep went from 3 to 4 days to under an hour.

    See the case
  6. Step 6

    Output anyone can audit

    Each run ends in an Excel workbook anyone can audit. Anything a person must confirm is flagged in it.

    Real example10 AI automations

    Manual costing work became 10 AI automations. They pull live ERP data, build Excel workbooks anyone can audit, and flag anything a person must confirm.

    See the case
See the full workflow

Business Intelligence

One model. Every metric defined once.

A shared data model on ERP data, the company’s core business records. Every production report now uses it.

See the case

The gap, not just the number.

Each figure shows where it stands against plan.

See the case

The trend behind it.

10+ Power BI dashboards and reports on ERP data, from sales and invoicing to inventory and production.

Open the dashboards

One view for leadership.

The company’s first executive dashboard: 12 business areas in one view.

Open the dashboard
Net sales 2026
599.6K
to 30 Sep
vs target
95.8%
4.2% below target
Net sales by month
Verdict

Net sales sit 4.2% below target, to 30 September.

Checked against SQL

Demo data: Bean & Brew, a made-up coffee chain. Bar heights are illustrative. Open the full report

Open the full report

AI Automation

AI reads and proposes.

It reads a plain-language request and suggests what to change.

Open the demo

Tested code does the math.

Every calculation runs in Python, backed by 446 automated tests.

See the case

A person approves.

Nothing changes until someone signs off.

Open the demo
Change requestExample
Customer wants the bigger fan and a stainless steel casing on unit A-12.
AI proposal2 changes
fan size Lcasing stainless
Python · pytestpricing rules
446tests passed
ReviewYou decide
ApproveRejectApproved

Illustration of the method. The real tool is internal.

Try it

Try the Pricing Assistant demo

Pick a change request. See what the AI proposes, what validation rejects, and how the quote moves when you approve.

Open the demo
MSc research

My MSc research

Can machine learning spot a late order on the day it is entered? Measure, explain, predict, then warn planners early.

Proposal defended, November 2026Read about the research
Dashboards

Open the dashboards. Use the filters.

Five working rebuilds of reports I build. Change the period, tap a figure, open an area.

All data is made up. The real dashboards are internal.

Results

Less time building. More time deciding.

3 to 4 days
< 1 hour

Monthly sales meeting report. Data pull, checks and the finished deck run as a scheduled AI workflow.

See the case
two weeks
three days

One Power BI report build, using AI-assisted development I brought to the team.

See the case
Data up to 5 days old
Live

Sales performance report on live ERP data. New views ship in hours.

See the case
446

Automated tests behind an AI pricing tool I rebuilt. A review had found 37 contradictions in its method documents.

See the case
~25M AED

At-risk stock surfaced early enough to act, from 100,000+ inventory, financial and operational records.

See the case
~97K AED

Material costing gap closed when I rebuilt the pricing tool.

See the case
Selected work

What I built, and what changed.

AI automationPending IT deployment

Custom unit pricing engine

An AI pricing tool rebuilt so tested code does the math and a person confirms every change. ~97K AED costing gap closed.

Open the demo
AI automationOwn tool

Table Extractor

An offline Windows tool that turns tables in PDFs and scans into Excel. 100% of cells right on a real catalog page’s original PDF, 96.7% on an office copier scan.

Open the demo
Training

I teach what I use at work.

I run sessions for colleagues, and I am open to freelance training with institutes.

Delivered

  • Sessions for colleagues in engineering and HR.
  • An AI rollout for a non-technical team: account setup, use cases and data-handling rules. See the case
  • Wrote staff training on using AI tools well.

Topics for institutes

  • Power BI
  • DAX, the formula language of Power BI
  • Data modelling
  • AI automation with Claude Code and MCP, a standard way to connect AI to tools
Ask about training
Tools

The tools I use every day.

The software behind the dashboards and automations on this page.

Credentials

Certified, and still learning.

Neo4j · 2026

Neo4j & Generative AI Certification

Timed exam on RAG (AI that answers from your own documents), vector search and data modelling.

Education

  • MSc Business AnalyticsUniversity of Sharjah, UAE, 2025 to 2028Proposal defended, Nov 2026. Analysis in progress.Part-time, in progress. Thesis: machine learning and agentic AI (AI that carries out steps on its own) to measure, explain and predict order-to-delivery lead time, and to warn planners before an order runs late.Read about the research
  • BEng Mechanical EngineeringUniversity of Sharjah, UAE, 2018 to 2022

Award

Employee of the Quarter, Q1 2025SKM Air Conditioning

Courses and learning (18)

Microsoft & LinkedIn 2026

  • Career Essentials in Generative AI (Professional Certificate)
  • AI for Organizational Leaders

Microsoft Learn 2026

  • Azure AI Fundamentals modules (AI concepts, NLP or natural language processing, computer vision, generative AI and agents, RAG)

Google Cloud 2026

  • Introduction to Generative AI
  • Introduction to Large Language Models
  • Responsible AI

OpenAI Academy 2026

  • Apply AI at Work pathway (AI Foundations, Agents and Workflows, Scope AI Solutions, AI Leadership)

Anthropic Academy 2026

  • Building with the Claude API
  • Model Context Protocol (Intro and Advanced)
  • Claude Code in Action
  • AI Fluency: Framework & Foundations

Hugging Face 2026

  • AI Agents Fundamentals
  • Fundamentals of MCP

IBM (Cognitive Class) 2026

  • Machine Learning with Python

MongoDB 2026

  • Building AI Agents with MongoDB (skill badge)

LinkedIn Learning 2024

  • Requirements Elicitation and Analysis
  • Predictive Analytics: Data Mining
  • SQL: Data Reporting and Analysis
Career

From engineering to data.

SKM Air Conditioning, Sharjah, UAE One of the UAE’s largest HVAC (air conditioning) manufacturers, serving projects across the GCC (the six Gulf states).

  1. Jul 2022 to Nov 2022

    R&D Engineer

    Technical documentation and 3D models, plus a tool that generates drawings automatically.

  2. Nov 2022 to Feb 2024

    Cost Engineer

    Priced 100+ HVAC projects across the GCC. Automated pricing in Excel VBA, cutting proposal turnaround by 30 to 40%.

  3. Feb 2024 to now

    Business Intelligence Analyst

    The only BI person on the team, serving directors and managers across the business. Power BI on live ERP data, and AI automation a person signs off.

    See the work
Contact

Hiring for BI or AI automation, or need a Power BI or AI trainer? Send me a message.