Sales and pricing
Freight & Supplier Quoting
Inbound requests and supplier quotes read and normalized, a predicted buy rate or fair price for each, and a drafted response waiting for approval.
The problem
Quote requests and supplier offers arrive as emails and PDFs in every format. Reps retype them, compare offers by hand, and answer slowly, so business goes to whoever responds first and margins depend on who happened to quote.
Who owns it
The head of sales or procurement, with the reps and buyers who send the quotes and awards.
What it learns from
- Inbound quote requests in email and PDF
- Supplier and carrier quotes
- Past quotes, awards, and their outcomes
- Buy rates, lanes, and landed costs
- Customer and supplier history
How it works
Predict, decide, act, measure
The same four steps in every solution, in this order, each one visible to the team that owns it.
- 01
Reads the request and predicts the rate
Language models extract each request and offer into structured fields, with a confidence for each. Models predict the buy rate or a fair price from past quotes, awards, and market history.
- 02
Decides the response through a policy
Margin floors, target rates, and limits on counters set the drafted quote, award, or counter. Fields extracted with low confidence and responses outside the limits go to a person.
- 03
Acts as a draft for approval
The drafted quote, award, or counter lands in the inbox, CRM, or transport management system your team already uses. A person approves before anything is sent.
- 04
Measures against the current process
Quote response time, quotes per rep, margin per load, and landed-cost savings are compared with the current process in a phased rollout or a holdout of lanes or accounts.
What it moves
The business levers
Response time
Quotes out while the customer is still choosing.
Rep capacity
More quotes per rep, with no retyping.
Margin per load
Prices set from what the lane actually costs.
Landed cost
Supplier offers compared on the same terms.
Proof
How the return is proven
The return is the change in response time, margin per load, and landed cost against the current process, stated against the return model agreed up front. Extraction accuracy is reported beside it.
What you see: the ROI readout
Every solution produces the same readout, assembled from the system's own records rather than built by hand.
Correctness
The checks the pipeline passed on your own data: leakage, point-in-time, and entity resolution.
Incrementality
The incremental effect against the holdout or equivalent design, with its confidence interval.
Return
The measured return against the investment, set beside the return model agreed before work started.
Guardrails
Complaints, cost, margin, fairness, and contact limits, each shown against its bounds.
Audit extract
Every score, action, and outcome, with the model and policy versions behind it.
Governance
What is governed
Access, approvals, and the audit trail are part of the solution, not a review step added at the end.
Identity-scoped access
Requests, quotes, and rates are visible by role through your single sign-on.
Approval gates
Every quote, award, and counter is approved by a person before it is sent.
Audit trail
Every draft is logged with its extracted fields, their sources, and the model and policy versions.
Explainable rates
Each predicted rate shows the history and drivers behind it.
Why it holds up
Trained on your data, framed by the outcome
This solution trains models on your own data, checks every stage from data to decision, and is measured against the outcome it was built for. Because its predictive power is measured, it also shows the drivers behind the metric, so your team can fix causes as well as act on scores.
Why solutions hold upStart with one decision
Bring the problem and the systems your team works in. We scope the first solution with you, agree how its return will be measured, and run it in production with your people.