EENSEK · AI Workforcebuilt by It's Sorted
Open vacancy · ENSEK is hiring this

Product Manager — API

Product Manager — API · 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.accounts27,640,145 real rows via MotherDuck (DuckDB). Not a slide about AI. The job, getting done.

What the AI does

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.

Their job ad asks

“Own the strategy, vision and roadmap for both the API-as-a-product programme — engaging stakeholders across engineering, commercial, and customer teams to define, validate and iterate it continuously.”

AI delivers, live

What is the API resource volume by region — account and meter count per region (the payload scale the API must serve)?

bar chart
Their job ad asks

“Define and drive a consistent framework for API definition and management across three tiers: internal domain APIs, cross-NSEC internal APIs, and external APIs for customers, brokers, and third parties.”

AI delivers, live

What is the monthly consumption data volume — kwh and bill totals per month (the data transfer volume the API handles for monthly reporting integrations)?

bar chart
Their job ad asks

“Make evidence-based prioritisation decisions, estimating effort and value of roadmap items using AI-powered estimation tools, and communicating trade-offs transparently with stakeholders.”

AI delivers, live

Which customer segments have the most accounts and highest consumption — the priority API consumer profiles?

bar chart
Their job ad asks

“Define and track key product outcomes — implementing dashboards for real-time performance visibility and using data to drive continuous improvement.”

AI delivers, live

What is the smart vs traditional meter API payload complexity — meter_tech distribution (smart = high-frequency reads, traditional = manual-read orchestration)?

bar chart
Their job ad asks

“Build long-term stakeholder relationships, implementing communications strategies and influencing effectively to drive alignment and outcomes.”

AI delivers, live

What is the dual fuel account share — main_fuel mix among active accounts (dual fuel customers need two meter API calls — the doubled-payload case)?

kpi

What stays human

The honest other half. AI does the analysis; a person owns the decision — especially where regulation, fairness and accountability bite.

How it works

Ask in English

A plain-English question — the same one the job ad describes — is translated to SQL by the agentic backend.

LIVE — computed now against 27.6M rows

Curated cards run server-side against MotherDuck when eligible. The workspace separately labels any local inspection path.

Real data, live

Runs against my_db.ensek_demo.accounts (27,640,145 rows declared by the manifest). No synthetic numbers.

Self-falsifying

Each figure carries a falsifier — recomputed from the result set, not a stored number, so it can't quietly drift.

Where it plugs in

Function / Ignition surface: API payload scale · Data transfer volume · API consumer profiles · API contract complexity · API payload doubling. Grounded in the real ENSEK: Ignition — a real-time, event-driven meter-to-cash SaaS platform for energy suppliers · 7M+ accounts · regulated by Ofgem.

Watch it do the job — for real

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. Representative ENSEK-style operational dataset (480 accounts · 728 meters · 5,676 monthly consumption records). Schema mirrors my_db.ensek_demo.accounts/meters/consumption_monthly. Seed 20260609 — reproducible. No real ENSEK or customer data. Live server-side path: my_db.ensek_demo.accounts (27.6M rows). Dormant until operator provisions MOTHERDUCK_TOKEN.

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 →