What is API?

Explained

An API is a set of protocols and tools that allows different software systems to communicate. For AI, APIs enable applications to call LLMs (OpenAI, Claude, etc.), retrieve embeddings, and integrate AI capabilities into existing workflows.

Decision guides that use this term

• MCP vs custom API integrations: how should your AI agents connect to your systems?

Further reading

• Enterprise AI Strategy: The New Moat Beyond the API

Related terms

• API Specification Formal description of endpoints, schemas, and errors—e.g., OpenAPI—used for docs, mocks, and validation.
• Automation Executing tasks without human intervention, often with AI for complex decisions.
• Autonomous Systems Systems that operate without continuous supervision, making decisions in real time.
• Cloud AI AI services hosted in the cloud (Azure OpenAI, AWS Bedrock, etc.).
• Downtime Period when systems are offline; predictive AI helps avoid it (Zero Downtime AI).
• Edge AI Running inference on devices or local nodes to reduce latency and data egress.