AI Copilot
An AI copilot is a model-powered assistant embedded in a workflow—code editor, email client, design tool—that suggests next actions while a human retains control. GitHub Copilot, which autocompletes code in VS Code, is the canonical example. The copilot pattern works because it keeps the human in the loop: the AI proposes, the human disposes. This is a deliberate design choice that sidesteps the hardest problems in AI deployment (accountability, error correction, trust) by never removing the operator. The limitation is also the point. Copilots augment speed on tasks the user already understands. They are less useful when the user cannot evaluate the suggestion—a junior developer accepting copilot code they do not understand is not augmented, they are automated without knowing it.
Related terms:
Structured Output
Structured output occurs when a language model returns data in predictable, machine-readable formats—such as JSON, XML, or typed objects—rather than free-form prose, enabling software systems to reliably parse fields like names, dates, and dollar amounts. By using constrained generation to enforce a JSON schema, structured output transforms AI from a conversational interface into a dependable system component.
Fine-Tuning
Fine-tuning continues training a pretrained language model on a smaller, task-specific dataset so it internalizes particular behaviors, styles, or domain knowledge. While it yields more consistent formatting and terminology than prompting alone, it requires curated data, additional training time, and can lead to loss of general capabilities.
Gravity Wells
Gravity wells describe economic dynamics where scarce resources flow disproportionately to entities with the greatest ability to pay and deploy, creating self-reinforcing concentrations of power. In the AI economy, they form around critical bottlenecks in compute, power, and talent, determining who captures resources and who scrambles for scraps.