Operations — how data is queried, observed, governed

AI Interfaces

2 open standards for AI Interfaces in a modern data architecture, each with an opinionated judgement: Adopt, Situational, Assess, or Caution.

Start with MCP.

Adopt 1 standard

The standard to reach for in new work. Proven, multi-vendor, clearly the default for its slot.

  • MCP — Model Context Protocol

    Became the AI tool-integration default in 2024–2025.

    Linux Foundation (created by Anthropic; multi-vendor steering)

Situational 1 standard

The right answer in some contexts but not others. Pick deliberately based on the constraint.

  • A2A — Agent2Agent Protocol

    Agent-to-agent protocol; right when you have multi-agent orchestration, otherwise overkill.

    Linux Foundation (created by Google; multi-vendor steering)

More in Operations

Operations covers how data is queried, observed, governed.

See AI Interfaces in context

These standards are one panel of the interactive Data Landscape, which maps every open standard a modern data architecture is built on. The underlying data is a single JSON file; disagree with a judgement? Open an issue.