Glossary
Glossary
Essential terms in plain language.
| Term | Definition |
|---|---|
| LLM (Large Language Model) | The AI "brain" that reads text and generates text by predicting what comes next based on patterns learned from training data. |
| Agent Loop | The cycle that makes an agent autonomous: read instructions → decide → act (use a tool) → observe the result → repeat. |
| Tool | A specific capability an agent can use during its loop — browsing a website, reading a file, sending an email, generating an image. |
| System Prompt (Instructions) | The standing orders the agent reads on every turn of the loop — your workflow descriptions, quality standards, and rules. |
| Context Window | The agent's working memory — the limited amount of text it can "see" at once, including instructions, conversation history, and tool results. |
| Step (Primitive) | A single, repeatable action in your workflow. |
| Constant | A part of your workflow that stays the same every time (the template). |
| Variable | A part that changes with each new input (the data). |
| Parameterization | Extracting the template from your manual process — identifying constants and variables. |
| Composability | Connecting steps so the output of one feeds the input of the next. |
| Named Workflow (Abstraction) | A reusable, packaged sequence of steps with a name you can invoke. |
| Signal | Information that changes your decision or improves your execution. |
| Noise | Information that consumes attention without changing outcomes. |
| Signal-to-Noise Ratio | How much useful information you get per unit of attention spent. |
| Human-in-the-Loop | AI does the mechanical work; you review, decide, and act. |
| Autonomy Level | How much independence the agent has for a given step (full, propose-and-approve, or human-only). |
| Friction | Repeated manual effort that slows you down without adding value. |
| Knowledge Compounding | The system getting better over time as workflows accumulate context, patterns, and refinements. |
| Decomposition | Breaking a large workflow into smaller, testable steps. |
| Exception Handling | Rules for what happens when data is missing, ambiguous, or unexpected. |
| Iterative Refinement | Improving results by repeatedly tightening instructions based on real output. |
| Runbook | Short instructions for when and how to run a workflow. |