Basenews
Planning by eye: a luxury you pay for without realizing it
Published on 24 September 2026 par David Beauchemin, Ph. D.
For the past two years, Quebec businesses have been absorbing costs over which they have zero control. US tariffs reaching up to 50% on certain products. A climate of uncertainty causing deferred investments. Labor that is hard to recruit and paid more. Meanwhile, clients are unwilling to pay more.
What remains under their control lies within their own walls. Work allocation on an assembly line or in a shop. Schedules for a team of teachers, nurses, or drivers. The sequence of maintenance stops on an equipment fleet. Delivery truck routing, material cutting, electrical network layout in a building. These decisions are still made manually, in a spreadsheet, by someone who knows their job and does the best they can with the time they have.
As long as margins were comfortable, approximate planning went unnoticed. Not anymore. What was left on the table without being noticed now makes the difference between a profitable contract and one fulfilled just to avoid losing the client.
This gain cannot be bought off the shelf. No software knows your collective agreement, nor the reason why a specific machine or crew never works on Fridays. The gain comes from an approach tailored to your problem, and no one can tailor it for you without spending time at your facility.
We will demonstrate this with numbers.
What We Did
A solver is a program that builds a plan for you. You describe the decisions to be made and the rules to be respected, give it a cost to minimize, and it searches for the best solution within the time granted. The search method itself is already built into the box.
How do you know if a solver is good? The domain has its standardized tests, benchmarks: collections of problems published by the research community, called instances, each with the best solution ever found. Competitors have made it their showcase: solvers undergo a series of tests of varying size and complexity to compare their performance. Anyone can repeat the exercise. We did it on three of them.
Electrical Grid Maintenance (RTE). The challenge set by the French grid operator RTE: Plan electrical grid maintenance while exposing it to the smallest possible risk. The task consists of assigning a start date to each maintenance operation over a horizon of up to 365 periods, keeping each team's workload within allowable limits, and without simultaneously launching two jobs that cannot overlap during that season. For each period, organizers provide a range of possible grid situations with their associated risk. The plan is evaluated on average risk and worst-case scenario risk. 45 instances and up to 706 maintenance operations.
Flexible Job Shop. Process all parts through a production shop, finishing as early as possible. Each part must follow its production steps in a fixed order, and each machine performs one task at a time. The same operation can be performed on multiple machines. You must choose which machine handles each operation and in what sequence. 336 instances, up to 100 parts, 25 steps per part, 500 operations, and 60 machines.
Assembly Line Balancing. An assembly line moves at the same pace for everyone. Each workstation has the same allocated time to do its part, the cycle time, and the part advances whether it is finished or not. Tasks must therefore be distributed among stations without any station exceeding this cycle time, respecting operation precedence, and using as few stations as possible. 525 instances with 100 tasks and 525 with 1,000 tasks.
In all three cases, we took their exact benchmark problems: same constraints, same objective, same calculation budget of one minute, and 8 CPU cores. Our solver starts from a common foundation and AI techniques, which we tune to the specifics of each problem.
A notable difference: Hexaly ran its benchmarks on a server equipped with an AMD Ryzen 7 7700 @ 3.8 GHz. Ours ran on a mid-range laptop, an Intel i5-1340P. For the same 60 seconds, we had roughly half their computing power.
The Numbers
The table presents unedited numbers published by the competition. A blank cell means the solver published no data for that line. In the average gap lines, a negative gap means the solution beat the best-known solution. Each of our solutions was re-validated by an independent checker, and RTE maintenance by the official challenge checker.
| Problem Size | Description | Baseline | Hexaly | CP Optimizer | Gurobi |
|---|---|---|---|---|---|
| RTE Maintenance: minimize risk. Three datasets of 15 instances. | |||||
| Small | % of solutions found across the 15 instances | 100% | 100% | 100% | |
| within 5% of best-known solution | 100% | 93% | 73% | ||
| within 1% of best-known solution | 87% | 73% | 67% | ||
| Large | % of solutions found across the 15 instances | 100% | 80% | 33% | |
| within 10% of best-known solution | 100% | 73% | 0% | ||
| within 5% of best-known solution | 73% | 60% | 0% | ||
| Very Large | % of solutions found across the 15 instances | 93% | 80% | 27% | |
| within 10% of best-known solution | 93% | 67% | 0% | ||
| within 5% of best-known solution | 80% | 33% | 0% | ||
| Assembly Line Balancing: minimize number of workstations. Two datasets of 525 instances. A negative gap is better. | |||||
| 100 tasks | within 1% of best-known solution | 523 | 515 | 470 | 373 |
| average gap to best-known solution | -1.1% | 0.2% | |||
| 1,000 tasks | within 1% of best-known solution | 525 | 525 | 304 | 0 |
| average gap to best-known solution | -1.9% | 0.2% | |||
| Flexible Job Shop: minimize total production time (makespan). Average gap to best-known solution, in percent. A negative gap is better. | |||||
| 1 to 100 operations | 194 instances | -0.6% | 0.3% | 1.3% | |
| 101 to 200 operations | 48 instances | 0.0% | 1.0% | 8.0% | |
| 201 to 300 operations | 73 instances | -2.8% | 1.0% | 38.5% | |
| 301 to 400 operations | 6 instances | 0.7% | 1.5% | 74.3% | |
| 401 to 500 operations | 15 instances | -25.0% | 0.5% | over 100% | |
| Across all sizes combined | % of solutions beating the best-known solution (113 out of 336) | 33.6% | |||
This table shows that an approach tailored to a given problem achieves real gains on large-scale problems using modest hardware. Every percentage point gained isn't a laboratory detail. On an assembly line, one less station means one less workstation to staff, every shift, all year long. In a shop, a few percentage points off total duration means machine hours recovered on every order.
The Real Takeaway
A generic engine must perform reasonably well across thousands of unknown problems, whereas a tailored approach leverages everything unique about your specific scenario. Your real-world problems carry far more constraints than the three benchmarks shown above. Each of these constraints is another leverage point to maximize profitability. Our approach starts from a foundational solver on which we perform custom tuning, making this work accessible to SMEs and large enterprises alike. Below are three real client cases where we applied it.
REAL CLIENT RESULTS
College Schedule Planning: Building a course schedule at the college level used to take around 520 hours per year. Baseline built an engine with the client that places 550 courses, 500 instructors and 140 rooms, then assigns 29,000 course registrations per semester, under roughly thirty types of constraints from 19 departments. The calculation runs in under two minutes, produces zero scheduling conflicts, and satisfies pedagogical requests significantly better than before.
Commercial Electrical Routing: The wiring of a commercial building or office tower almost never gets optimized. The electrical engineer only has time to place the major equipment, the electrician runs cables as best they can on site, and every detour costs meters of copper. Baseline built the optimization engine for the electrical module of a client specializing in building design. It shortens cable runs while respecting construction constraints and the Canadian Electrical Code, because a shorter circuit is worthless if it isn't compliant.
Fleet Management: On mining sites, hundreds of kilometers of service roads appear on no digital map. Vehicles get assigned day by day, in Excel files, department by department. Baseline reconstructed a site map from millions of telemetry data points, then delivered the optimization engine that builds routes from that map for a Quebec-based vehicle telematics specialist. Over 400 light vehicles, several hundred operators, under constraints of schedule, capacity, workforce availability and more. The improvements made to the telematics solution and the optimization engine together remove around sixty vehicles from the site fleet.
Going Further
This optimization approach was designed and written in Quebec by a local cooperative. The expertise that stands toe-to-toe with global optimization giants exists in Canada, and it works for local organizations, on their shop floors, with their data. Before sending your optimization budget abroad for an engine that doesn't know your plant, take a look at what is being done locally.
If one of your operations costs more than it should—a schedule, a delivery route, a production line—drop us a line. We spend time with your team to understand your business goals, build a baseline model on your data, and quantify the gap between your current approach and what is achievable. When you're ready, we deploy the solution into production. Software engineering is our core trade just as much as AI.