Terms & explanations
Our knowledge base with plain-language explanations of common terms from software development and IT.
Agent evaluation (Evals)
Agent evaluation (evals) measures an AI agent against fixed test cases with a defined correct result, before rollout and continuously in production.
Agent graph
An agent graph is the written-down structure of an AI agent: its steps as nodes, its permitted transitions as edges. A route you can test and limit.
Agent memory
Agent memory is how an AI agent keeps information beyond one model call: the current case, stable company knowledge, and lessons from earlier cases.
Agentic workflow
An agentic workflow is a process where an AI system knows the goal but works out the route itself, breaking the task into steps and calling tools along the way.
AI agent
An AI agent breaks a goal into steps on its own, uses tools such as databases or inboxes to carry them out, and hands over to a person once its remit ends.
AI governance
AI governance is the set of rules defining who may use AI for what, which data may flow where, and who is accountable for the results.
AI Overviews
AI Overviews are Google's generated answer boxes above the search results. They answer directly, changing how much traffic search passes on.
AI pilot
An AI pilot tests on one real process whether an AI application holds up in daily operation. It ends in a decision, not a demo.
Amazon Web Services (AWS)
A short explanation of AWS in our glossary
Android
A short explanation of Android in our glossary
Answer engine
An answer engine responds to a question with composed prose instead of a list of links. ChatGPT, Perplexity and Google AI Overviews all work this way.
Ant Design
A short explanation of Ant Design in our glossary
What work could agents take off your team?
Bring one recurring workflow or a product idea. Thirty minutes, an honest assessment, a clear next step.