Use case · Cold Drink Equipment

Every cooler is a capital bet. Right now it is placed on judgement.

Visi-cooler capex is one of the largest controllable investments a bottler makes, and one of the least measured. The question is not “how many coolers do we buy”, it is “which outlets, and what does each one return”.

Step

03 of 03

Answers

what should we do

Engine

Optimization Engine

Status

on the roadmap

Step 03 · Optimization Engine

On the roadmap

What should we do?

Allocate this year’s cooler budget across 40,000 outlets to maximize incremental volume.

A constrained allocation: budget cap, per-territory minimums, servicing radius, outlet credit standing. Solver returns the outlet list, provably the best allocation under those constraints, not the most defensible one.

Incremental volume from the same cooler budget Illustrative figures
Judgement
Optimized

Same capex, +23% incremental volume

Terms on this page

Per-territory minimum
The fewest coolers each sales territory must receive.
Servicing radius
How far an outlet can be from service coverage and still get a cooler.
Solver
An optimization algorithm that finds the best plan satisfying every constraint.

How the Optimization Engine gets there

  1. 01The same proprietary agentic structure as prediction, applied to prescriptive questions, starting from forecasts the Prediction Engine already produced.
  2. 02The agent translates the business problem into a formal model: decision variables, constraints, and an objective.
  3. 03Exact methods (linear and mixed-integer programming solvers) run where provable optimality is achievable.
  4. 04Heuristics and metaheuristics take over where problem scale demands fast, high-quality approximate solutions.

On the roadmap. Turns Prediction Engine output into constrained, actionable decisions.

Explore the Optimization Engine

What changes

The relay today

The relay often never starts. OR talent is rationed to a handful of flagship projects.

With Theovya

Solver-grade decisions on every planning question, not just the six-month engagements.

Same budget. Different outlets. The delta between a judgement-based allocation and an optimized one is the entire argument for the third engine.

Prove it on your data before you commit to anything.

The Analytics Engine is live and connects read-only to systems already in place. There is no migration, no warehouse project, and nothing to rip out to find out whether this works.

Request a conversation

Use case · Cold Drink Equipment

Every cooler is a capital bet. Right now it is placed on judgement.

Visi-cooler capex is one of the largest controllable investments a bottler makes, and one of the least measured. The question is not “how many coolers do we buy”, it is “which outlets, and what does each one return”.

Step

03 of 03

Answers

what should we do

Engine

Optimization Engine

Status

on the roadmap

Step 03 · Optimization Engine

On the roadmap

What should we do?

Allocate this year’s cooler budget across 40,000 outlets to maximize incremental volume.

A constrained allocation: budget cap, per-territory minimums, servicing radius, outlet credit standing. Solver returns the outlet list, provably the best allocation under those constraints, not the most defensible one.

Incremental volume from the same cooler budget Illustrative figures
Judgement
Optimized

Same capex, +23% incremental volume

Terms on this page

Per-territory minimum
The fewest coolers each sales territory must receive.
Servicing radius
How far an outlet can be from service coverage and still get a cooler.
Solver
An optimization algorithm that finds the best plan satisfying every constraint.

How the Optimization Engine gets there

  1. 01The same proprietary agentic structure as prediction, applied to prescriptive questions, starting from forecasts the Prediction Engine already produced.
  2. 02The agent translates the business problem into a formal model: decision variables, constraints, and an objective.
  3. 03Exact methods (linear and mixed-integer programming solvers) run where provable optimality is achievable.
  4. 04Heuristics and metaheuristics take over where problem scale demands fast, high-quality approximate solutions.

On the roadmap. Turns Prediction Engine output into constrained, actionable decisions.

Explore the Optimization Engine

What changes

The relay today

The relay often never starts. OR talent is rationed to a handful of flagship projects.

With Theovya

Solver-grade decisions on every planning question, not just the six-month engagements.

Same budget. Different outlets. The delta between a judgement-based allocation and an optimized one is the entire argument for the third engine.

Prove it on your data before you commit to anything.

The Analytics Engine is live and connects read-only to systems already in place. There is no migration, no warehouse project, and nothing to rip out to find out whether this works.

Request a conversation