Energy retail data analysis & reporting
Here's what AI can do for this role — and what still needs a human. Built straight from ENSEK's own job advert, running live on my_db.ensek_demo.energy_customers_360 — 27,640,145 real rows via MotherDuck (DuckDB). Not a slide about AI. The job, getting done.
Every line on the left is lifted from ENSEK's actual job ad. If a card lacks a harvested JD line, it is omitted. On the right is the AI doing it — with eligible cards running live against the warehouse and offline inspection clearly labelled in the workspace.
“Translate business questions into clear analytical problems with defined scope and expected outcomes.”
What does the national property estate look like by region — how do average bills, EPC quality and property counts vary?
bar chart“Build, maintain, and document data pipelines, transformations, and reporting layers across operational and analytical systems.”
What was the average settlement imbalance price by month — which months carried the highest market stress for ENSEK?
bar chart“Develop self-serve dashboards and reporting tools that reduce ad-hoc data requests and empower non-technical stakeholders.”
What are all the Ofgem price cap rates — unit rates and standing charges across every quarter?
table“Present findings clearly to technical and non-technical audiences, structuring insights to support decisions rather than just describe data.”
How is the national property estate distributed across EPC bands — what proportion is below the recommended efficiency threshold?
bar chart“Identify opportunities where AI, data and automation can improve analytical accuracy and reduce exception handling.”
How do average bills and CO2 emissions vary by affluence band — which households face the most affordability and sustainability pressure?
tableThe honest other half. AI does the analysis; a person owns the decision — especially where regulation, fairness and accountability bite.
A plain-English question — the same one the job ad describes — is translated to SQL by the agentic backend.
Curated cards run server-side against MotherDuck when eligible. The workspace separately labels any local inspection path.
Runs against my_db.ensek_demo.energy_customers_360 (27,640,145 rows declared by the manifest). No synthetic numbers.
Each figure carries a falsifier — recomputed from the result set, not a stored number, so it can't quietly drift.
It's the role getting done: curated questions run live server-side against the warehouse; local inspection is labelled inside the workspace.
Open the live workspace →Provenance. Three live ENSEK datasets: my_db.ensek_demo.energy_customers_360 (27.6M enriched properties, sampled 500 rows offline), my_db.ensek_demo.settlement_imbalance (4,320 half-hourly settlement rows), my_db.ensek_demo.ofgem_price_cap (16 quarterly price cap rows). Offline degrade uses the same pre-projected slices in-browser.
It's Sorted — I took ENSEK's job ads and didn't write a report on what AI could do. I built it. Get the rest sorted →
I'm trained on this proof and the real ENSEK: the Ignition meter-to-cash platform (seven modules), the move under Centrica in 2024, 7M+ energy accounts migrated for suppliers like British Gas and Utility Warehouse, and the Ofgem framing. Ask me how the Data Analyst function changes shape, or which open roles map to which Ignition module.