Governed Negotiation
Management · Sales director
A discount outside the rule stops in the queue, with reason and margin in view.
The rep negotiates up to the ceiling of their role. Above it, the order goes up for approval before it becomes a transaction, and the director approves or rejects it with the coded reason.
Illustrative scene with a real CWS Platform screen in a demo version. People, stores and on-screen data are fictitious.
Operations · B2B sales rep
Sales Copilot builds the offer. The rep decides, within their own ceiling.
The quote arrives ready, with the reason to call that customer today and the suggested discount on each line, already within what the company authorized. Approving, editing or discarding stays with the rep.
Illustrative scene with a real CWS Platform screen in a demo version. People, stores and on-screen data are fictitious.
Customer · Buyer
She closes on invoice, within the limit and terms her contract grants.
Payment is a negotiated dimension too. At checkout, she sees the company's credit limit, what is outstanding, what is left and the contract terms before confirming.
Illustrative scene with a real CWS Platform screen in a demo version. People, stores and on-screen data are fictitious.
Management · CTO
Each AI Agent has its band: acts alone, proposes or never acts.
The Autonomy Gradient matrix is the company's configuration, action by action, on the same rules engine as the human rep. The AI does not grant what the rule does not allow.
Illustrative scene with a real CWS Platform screen in a demo version. People, stores and on-screen data are fictitious.
Concept
In complex B2B commerce, price, delivery, payment, quantity and composition aren't fixed, they're negotiable. CWS Platform treats the cart as a negotiation table, where each of these dimensions moves within intelligent rules. This is what we call Governed Negotiation.
Why it isn't e-commerce
E-commerce is the front end, the storefront that records a fixed price. CWS Platform is the infrastructure beneath it: a B2B Commerce Platform for Governed Negotiation. It doesn't swap B2B negotiation for a rigid checkout, it digitizes the entire negotiation, with the company's rules built in.
Governed Negotiation in 1 minute
The freedom to negotiate, with every concession auditable
Governing the negotiation isn't about straitjacketing it. It's about letting the rep, or the AI agent, move within rails the company defines and that record every decision. Four mechanisms make this concrete:
Approval Workflows
Approval limits: what passes straight through and what escalates to a one-click confirmation.
Pre-Submission Guardrails
Locks before submission and prevents the order that would be born dead (Dead-on-Arrival).
Discount Stacking Prevention
Stops the stacking of discounts that erodes margin without anyone noticing.
Reason Codes
Every concession carries its why.
And the margin?
Margin becomes something auditable, not a mystery at month's end.
Several reps on the same order, each inside their own limit
The authority limit doesn't belong to the order, it belongs to whoever is negotiating inside it. More than one rep can work the same cart at the same time, and each moves only as far as their own limit reaches: whoever answers for one warehouse doesn't price an item shipping out of another. That is what makes it safe to invite a partner, a reseller or a rep to sell inside your own portal — every ceiling is already written before the conversation starts.
Discount and payment terms are the same currency
A rep who controls only the percentage will spend the percentage, because it's the only lever they have. Price and payment terms are convertible into each other: part of the discount the buyer asks for can come back as terms, and part of the terms can come back as price. Handing over both levers, each with its own ceiling, protects margin more cheaply than tightening a single one, and the trade is recorded in the Reason Code alongside the rest of the concession.
Persona · Legal and procurement manager
I can audit every concession with its reason on record, whether a rep or the AI made it.
In Governed Negotiation on CWS Platform, Approval Workflows and Reason Codes record every decision, and the AI Agents follow the same rules as a human seller.
Persona · Chief executive officer
I started with the portal, with no margin risk, and reached AI on the same platform.
In Governed Negotiation on CWS Platform, adoption usually climbs a ladder, from the classic portal to trading with AI, under the same rules engine.
Why the platform resembles a risk desk
CWS Platform did not start as e-commerce. It started from an observation its founder made while working as a trader at an investment bank: if there is software to transact currency, equities and energy, there would be software to transact any product, and especially the ones that behave like commodities, from tyres to grain, from spare parts to chemical inputs. The platform was built on that logic from the outset, in production since 2013 and already multi-warehouse, with the catalog held separately from stock.
And what does that change in governance?
It is why governance here does not take the shape of an approval queue bolted on afterwards. On a trading desk the limit is not a step in the process, it is the condition of operating: whoever negotiates moves fast because the system already knows how far they may go. The Commerce Rules Engine is that same idea applied to product, and the seller is the one operating under it.
The entry spectrum
Almost nobody starts by negotiating. Adoption tends to climb a ladder, and each rung creates the need for the next, which is what matters to a decision-maker: you can enter at the first level with no margin risk and reach the last without changing platforms along the way.
- 1
Classic portal
Catalog and checkout, with pricing by profile, and no active seller in the journey.
The operation notices that the large order still arrives by phone.
- 2
Seller present
The same portal, now with the seller visible: name, photo, a conversation available. They help, but do not yet negotiate.
The operation wants to give the seller real autonomy, without opening up the margin.
- 3
Governed negotiation
Shared cart, approval thresholds, mandatory justification. The seller negotiates within rails, and every concession is recorded.
The operation wants to scale without hiring in the same proportion.
- 4
Trading with AI
Agents operating under the same rules engine that constrains the human, with replenishment and enrichment anticipating demand.
It is the state in which negotiation governance applies to person and agent without distinction.
The first two levels are B2B Digital Selling; from the third onwards, Assisted Selling.
Determinism plus AI, under the same rules
The deterministic Core executes the rules by code, at zero inference cost. The AI Agents interpret intent and orchestrate that Core via MCP (Model Context Protocol), under exactly the same rules as a human seller. If the AI goes down, negotiation continues. And the AI never hallucinates a business rule, because it doesn't invent a rule, it consumes one.
Governed concession
Past the range, the discount goes for approval, and the rep sees where the limit comes from.
In Governed Negotiation, the authority comes from the rule, by category group, store or tag: in the cart, the rep sees the maximum discount on the item, the total order discount and the range in which the order goes up for approval, on record.
Discount and terms
The chosen payment date recalculates the price, within the contract terms.
In the Credit-First B2B Checkout (Checkout & Payments), payment-on-terms methods are configurable, with the dates and number of installments the store sets. The buyer picks the contract terms and the date, and the price adjusts with an early-payment discount or late-payment interest: terms are part of the negotiation too.
Not a lab concept
Governed Negotiation has been running in real production since 2013. At Tracbel, portal orders carry 10 extra points of operating margin, with 100% of the portfolio available (about 131k SKUs). At Imdepa, the B2B portal led to 3x more customers activated in three years, without growing the team in the same proportion.
See the 5 dimensions in detail
Price, delivery, payment, quantity and composition, one by one.
Frequently asked questions
Does governing the negotiation straitjacket the rep?
No. Governing means letting the rep, or the AI agent, move within rails the company defines and that record every decision (Approval Workflows, Reason Codes). It's the freedom to negotiate with every concession auditable, not a rigid checkout.
How is it different from a CPQ or a B2B e-commerce?
In e-commerce the storefront records a fixed price; in a CPQ, the quote is an isolated step. In Governed Negotiation, the five dimensions (price, delivery, payment, quantity and composition) move at the same time, in the same order, under the same Commerce Rules Engine.
Does the AI negotiate outside the same rails as the rep?
No. The AI Agents query the rules engine via MCP, under exactly the same rules as a human seller. They interpret intent and suggest; the rule itself is executed by the deterministic Core, and the human decides what gets escalated for approval.
Approval matrix
Each role's ceiling, by customer and price list.
Each role's ceiling comes from a matrix written in the Commerce Rules Engine (CDL Workspace), by customer type and price list, with the payment terms each role can grant.
See the Commerce Rules Engine →