About
Baramind is a data and software firm. We build our own products for planning and AI, and help companies build theirs.
The team
Planning projects usually fail in the gaps — between the model and the data, or the tool and the planner. Our team covers all three sides, so nothing gets lost in hand-offs.
Data science
Forecasting and optimisation that hold up in production.
Statistical and machine-learning forecasting, optimisation and the discipline to test them honestly.
Supply chain
Years inside planning teams, not just around them.
Demand, inventory and supply planning, and the S&OP routines that tie them together.
Software engineering
Systems built to be run, not just demoed.
Data platforms, APIs and the applications people use every day — built to be operated and changed.
Data is infrastructure, not a project. The organisations that get value from AI treat their data layer like production software: versioned, tested, monitored and continuously improved.
Trust beats accuracy on paper. A slightly less accurate forecast that planners understand and use beats a better one they override.
Ship working software. We deliver something you can run at every step. Documentation is a by-product, not a milestone.
Build what we sell. We make our own products on the same foundations we build for others, so we live with the consequences of our choices.
What we do
Demand planning that shows its working.
Forecasts by item and location, with the drivers and the uncertainty in plain view — so planners can adjust with confidence instead of overriding blind. Demand first; inventory, supply and S&OP next, on the way to end-to-end supply chain planning.
A Python desk for long-running AI agents.
A persistent, controlled Python runtime agents reach over MCP. Packages, files and processes stay put between sessions, for days or weeks — no servers to babysit.
agent → python.exec("import pandas as pd") agent → python.exec("df = pd.read_parquet('orders.parquet')") # next day, same desk agent → python.exec("df.shape")Visit pysmith.com ↗
Pipelines, platforms and data models your team can trust — from ERP and warehouse extracts to a clean, governed layer that analytics and AI can stand on.
Forecasting, optimisation and machine learning that survive contact with production — tested, monitored and explainable to the people who rely on them.
End to end: demand, inventory, supply and S&OP. We design the process and build the tooling together, so the plan and the system that produces it actually match.
Get in touch