Vector 1
AI Strategy & Economics

Source, Scope, Ship: A Practitioner’s Guide to ML and AI Projects

Brian J. Curry
Brian J. Curry
September 9, 2026 · 2 min read

Finding use cases, building the plan, and setting expectations that survive contact with reality

Most failed AI and ML projects were lost before a single line of training code was written. The model was fine. The problem was the wrong problem, or the right problem framed wrong, or the right problem framed right but delivered into a workflow nobody had agreed to change.

Scoping decides more than any other phase, and it is the one practitioners are least trained for. Coursework teaches you to optimize a loss function on a fixed dataset. Nobody hands you the dataset at work. Somebody hands you a vague complaint about churn, and everything between that complaint and a well-posed learning problem is your job.

This is a practitioner’s guide to that gap: how to source candidate use cases, how to triage them, how to frame the ones that survive, how to build a plan that holds up under uncertainty, and how to set roles, responsibilities and expectations so the project doesn’t quietly die of ambiguity.

Part 1: Finding Use Cases

Read the full article on my substack: https://brianjamescurry.substack.com/

About the Author

Brian Curry is a Kansas City–based Machine Learning & AI Strategist, Marketing Economist, and Applied Researcher. He drives Vector1, a personal open-source research initiative advancing marketing economics, causal inference, cognitive AI architectures, and the economics of intelligent automation.

He has led advanced data science and analytics initiatives across major enterprises including Koch Industries, Tractor Supply, Hallmark, Garmin, and AT&T. His work applies economic thinking and causal inference to connect marketing investment to outcomes, operational decisions to economic value, and AI adoption to competitive advantage.

Key Research & Open-Source Projects (GitHub: @Bodhi8):

  • PyCausalSim — A Python framework for causal discovery and inference through simulation. Enables testing of counterfactual scenarios to identify true structural drivers.
  • Papilon — A complex system and causal discovery library for Media Mix Modeling (MMM) and adaptive systems.
  • Regimecast — Applied research and tooling for time-series regime detection and forecasting.
  • CarryNet — Open-source research and modeling focused on commodity carry trade analysis.
  • Foodmesh-ml — Machine learning, optimization, and simulation framework for modeling distributed food systems.
  • Memory-Node Encapsulation (MNE) — A cognitive AI architecture and novel data structure for artificial episodic memory.
  • The Autonomy Economy — A macroeconomic framework projecting the dual impacts of massive productivity growth and extreme price deflation in an AI-automated world.
  • Meaning-Flow — Research focused on semantic content modeling and automated coverage gap analysis.

Contact: brian at vector1.ai | Vector1 | GitHub | LinkedIn

This article may be shared with attribution under Creative Commons Attribution 4.0 International (CC BY 4.0).

Related research