Customer Success Manager · vacancy
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.customer_tickets — 500 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.
“Drive product adoption across our customers ensuring users are actively engaged and extracting value from our products.”
What is the ticket volume and resolution rate by category — where is the support backlog concentrated?
bar chart“Monitor usage metrics and engagement data to identify adoption gaps and expansion opportunities.”
How long does it take to resolve tickets by category — and what is the average customer satisfaction score?
table“Develop comprehensive success plans for each account including customer objectives, success criteria, milestones, adoption roadmap, and mutual action plans.”
What does the open ticket backlog look like by priority — how many critical and high-priority tickets are open right now?
deviation“Collect, synthesize, and advocate for customer feedback including feature requests, product gaps, and improvement suggestions.”
What is average customer satisfaction by subcategory — which ticket types are generating the lowest CSAT scores?
table“Participate in product roadmap discussions representing the customer perspective.”
How does ticket volume by category trend month by month — is the support workload growing or shifting?
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.customer_tickets (500 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. Live ENSEK customer ticket data: 500 tickets across billing, account-management and technical categories. Three categories, fifteen subcategories, four priority levels, seven status values. Schema: my_db.ensek_demo.customer_tickets. Offline degrade uses the same pre-projected slice 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.