← Back to portfolio

Tender Savings Engine

From a client's raw shipment file to a bottom-up savings plan for a tender, in about a week: the engine cleans the data, re-plans the network with an optimisation solver, sizes every lever and has an AI agent draft the proposal.

Synthetic-data replica of a tool I built in production.

  1. Data checkquality score, network mapped
  2. Baseline12 months of spend, by mode and flow
  3. Optimisationsolver re-plans the road network
  4. Sizingevery lever, bottom-up and calibrated
  5. AI draftproposal written, every figure verified

Four expert gates: the tender lead approves the baseline, the levers, the calibration and the final plan.

An AI agent drafts the proposal

Tested on 30 synthetic clients