ZenCTRM™

Commodity trading platform built for the agentic era.

Physical and financial trades, from capture to invoice. AI agents extend it, operate it and act within it. Each one acts under an explicit human mandate, with segregation of duties enforced exactly as it is for people.

See the trade lifecycle
An AI assistant working in ZenCTRM through MCP. How it works
Physical and financial, one system
  • Power
  • Gas
  • Oils and softs
  • Agriculturals
  • Metals
  • Emissions
  • Derivatives

Built for physical and financial trade.

Grade, brand, origin, delivery port, contract form, Incoterm and tolerance on every physical trade. Settlement on recorded deliveries. Futures, swaps and forwards on the same book, valued together.

An AI-ready CTRM, built API and MCP-first.

Every screen runs on the same REST API your own systems can call, and the main trading operations are MCP tools your AI agents can use. Tailor ZenCTRM to the way you work, with your own extensions in C# or Python that leave the core unchanged. AI agents hyper-accelerate delivery. They build your extensions and the deployment packages for you, in a fraction of the usual time. A person approves each one.

ZenCTRM Trade View: palm oil trades with state, counterparty, product, quantity, price, period and book

From trade capture to invoice.

One system for the front, middle and back office. Each step can need its own permission.

  1. CaptureA form per trade type
  2. ApproveFour-eyes, its own permission
  3. ConfirmConfirmation from your template
  4. Cash flowsReceivables and payables from payment terms
  5. DeliverFull or partial shipments, or fixings
  6. SettleFinal cash flows
  7. InvoicePer shipment or monthly, with netting
  8. LedgerJournal export
Market data and price curves · valuation, exposure and P&L · every step recorded with who, for whom and when

  • Trade capture

    A form per trade type, quality and delivery terms, templates, fees and your own validation rules.

  • Market data and curves

    Every publication kept, corrections versioned. Connectors for leading market data providers.

  • Valuation and P&L

    Reproducible end-of-day runs. P&L explained by new trades, amendments, deliveries and price moves.

  • Settlement and invoicing

    Cash flows from payment terms, netting by agreement, credit notes and a journal for your ledger.

Everything ZenCTRM does

What happens when the agent gets it wrong?

A trade nobody sanctioned, or an invoice nobody approved. In ZenCTRM, the controls you already use apply to AI agents too. Here are three controls you can defend to an audit committee.

1. Every agent acts for a named person

An agent never uses a trader's password or a shared service account. It holds only the permissions that both it and the trader hold, and every action names both.

2. Segregation of duties, for people and agents

Any lifecycle step can need its own permission, so the person or agent that captures a trade need not be the one who confirms it. The same rules govern both.

3. Every earlier version is kept

Every economic amendment is a new version, and earlier versions are kept. A cancellation is a recorded step, not a deletion. An agent cannot quietly tidy up after itself, because there is nowhere to tidy to.

Version 1Kept
Change
Captured
Detail
50 MW at 85.00 EUR/MWh
By
A. Trader
Version 2Kept
Change
Price amended
Detail
85.00 to 86.20 EUR/MWh
By
A. Trader
Version 3Current
Change
Quantity amended
Detail
50 to 75 MW
By
AI assistant, for A. Trader

Customise without changing the core.

Your fields, rules, screens and code live beside the core, and each release checks them before it is installed.

Built on the Zengentic platform

  • Configuration first

    Screens, fields, lifecycles and approval steps changed on screen, with no release.

  • Code in C# or Python

    Validation, derived values, curve calculations and feeds at declared points. A second person activates each change.

  • Checked before every upgrade

    Extensions are checked for compatibility with a new release before it is installed.

Questions we are often asked.

Who is ZenCTRM for?

Commodity trading firms, and producers or consumers with a trading desk, in power, gas, oils, agriculturals, metals and emissions.

Where does it run?

On your servers, in your cloud, or both. It runs on Windows Server with SQL Server. Your data stays in your own database.

Do we have to use AI agents?

No. Everything works through the screens without an AI assistant. Agents are optional, and an administrator decides which people and agents may use them.

What information reaches an AI provider?

Only through an assistant a person chooses to use. When someone works through an AI assistant such as Claude, their messages and the results of the tools the assistant calls go to that assistant’s provider, and the tools return only what that person may see. ZenCTRM itself does not send your data to an AI provider. An administrator decides which assistants and people may connect, and any model keys are held in your own Azure Key Vault.

How does implementation work?

We start with a short workshop on your trade types, approvals and reports. We configure first, and write code only where it is needed. Your team tests in its own environment before go-live.

Can we change it ourselves?

Yes. Administrators change screens, fields, lifecycles and approval steps without a release. Developers add extensions in C# or Python. Every extension is checked for compatibility before an upgrade.

Do you work on other trading systems?

Yes. Zengentic consulting covers implementation, testing, migration and integration on the system you already have.

Bring a real trade. We will book it live.

In 30 minutes an AI assistant books your trade in ZenCTRM, a person approves it, and you see the record of both.

Request a demo