Energy

Energy Procurement Agent

Two days to the meeting. Market price, remaining volume and clauses are spread across four files.

Uses data to sharpen energy and materials procurement.

Uses data to sharpen energy and materials procurement.

Open agent

Enlarge demo

Public administration

Four processes that take up the most time today

Developed in Germany · Hosted in the EU

Developed in Germany · Hosted in the EU or on-premises

Delivered together with

Sovereign hosting in Germany, single-tenant from the first user.

Sovereign hosting in Germany, single-tenant from the first user.

Legal, tax and compliance expertise for legally sound deployment.

Legal, tax and compliance expertise for legally sound deployment.

Advisory and implementation for the public sector, starting with the AI readiness assessment.

Advisory and implementation for the public sector, starting with the AI readiness assessment.

Four supply contracts, three price sources, one meeting on Thursday.

The demand forecast comes from the ERP, the price series from the market data service, and the terms sit in the contract files. Anyone preparing a tranche copies these three sources into a spreadsheet by hand and works through two or three variants. If the price moves before the meeting, it all starts again.

4

supply contracts

Four current contracts with different index clauses cover the annual demand.

3

price sources

The forward curve, the last round of offers and the price of the current tranche each give a different figure.

15

scenarios

Three volume paths times five price assumptions make fifteen calculations per meeting.

2 days

lead time

That is the time between the market data snapshot and the procurement committee's meeting.

On Thursday, the committee walks into the meeting with fifteen calculations based on a single market data snapshot and four contract clauses compared side by side, and makes a 20% better purchasing decision.

The 20% improvement in purchasing decisions is this agent's headline figure. The numbers of contracts, price sources and scenarios sketch a typical tranche date in energy purchasing; they are not measured values.

Three steps through the process.

The head of energy purchasing decides whether to buy the tranche; the agent runs the scenarios and sets the contract clauses alongside them.

1.

1.

Bring demand and market position together

The agent pulls the demand forecast from the ERP and sets the current price series next to it. It records a timestamp for every source.

The agent pulls the demand forecast from the ERP and sets the current price series next to it. It records a timestamp for every source.

Data as at 07:15, demand 148 GWh for 2027, 3 price sources

2.

2.

Compare the clauses of the four supply contracts

The agent reads the four supply contracts and sets index linkage, minimum offtake and notice period side by side. It quotes any divergent wording with its source reference.

The agent reads the four supply contracts and sets index linkage, minimum offtake and notice period side by side. It quotes any divergent wording with its source reference.

Contract comparison EVU-2027-B, clause 4.2 differs in one of four contracts

3.

3.

Present the scenarios to the meeting

The agent combines each volume path with each price assumption and sorts the results by annual cost. The paper goes to the procurement committee with assumptions and source references.

The agent combines each volume path with each price assumption and sorts the results by annual cost. The paper goes to the procurement committee with assumptions and source references.

beschaffungsvorlage_2027-b.xlsx, 15 scenarios sorted by annual cost

What the agent does not do.

It does not buy a tranche.

It does not buy a tranche.

It presents the calculated scenarios with their assumptions. The head of energy purchasing signs off the order.

It does not make its own price forecasts.

It does not make its own price forecasts.

It works with the price assumptions set by the committee and makes every assumption visible in the paper. Purchasing decides which assumption is sound.

It does not update the index level for the price adjustment clause in contract C.

It does not update the index level for the price adjustment clause in contract C.

Clause 4.2 ties the energy price to an index the market data service does not supply and that purchasing enters by hand in the contract database. The value held there dates from 31 August 2026, and all fifteen scenarios use it for contract C until the head of energy purchasing enters the new one.

Connected systems

ERP system

contract database

market data service

Operations

Deployment model

EU cloud or private cloud

EU cloud or private cloud

Data processing

GDPR-compliant, no model training on your data

GDPR-compliant, no model training on your data

Responsible teams

Purchasing, supply chain

Purchasing, supply chain

The questions that come up before the first meeting.

How quickly is the Energy Procurement Agent ready to use?

Where is the data processed?

Where does the figure “20% better purchasing decisions” come from?

Related agents.

All agents

Platform

Industries

Services

Resources

Company

Pricing

From AI strategy to a running platform: we show you the way.

Talk to us

Log in

DE

EN

English

Platform

Industries

Services

Resources

Company

Pricing

From AI strategy to a running platform: we show you the way.

Talk to us

Log in

DE

EN

English
neuland.ai

The AI management and orchestration platform from Cologne.

Developed in Cologne. Operated in the EU or in your data center.

Certifications and compliance: ISO 27001, ISO 9001, GDPR, EU AI Act, DORA, StBerG, and BRAO
WirtschaftsWoche Best of Technology 2026 seal, 2nd place in the Process Management category for neuland.ai

© 2026 neuland AI AG