Generative AI Technologies

Agents

A concise overview of Agents, how it relates to Generative AI Technologies, key considerations, and conditions to confirm.

Scope

For Agents, we define applicability from the purpose and constraints, including conditions where it should not be used. The relationship to Generative AI Technologies remains visible so the reasons behind each decision can be reviewed.

Design decisions

For Agents, we avoid locking the design to one model or platform, separate data, integration, and monitoring, and record the reasons for each choice. The relationship to Generative AI Technologies remains visible so the reasons behind each decision can be reviewed.

Validation

For Agents, we use repeatable inputs and criteria and inspect failure cases as well as expected behavior. The relationship to Generative AI Technologies remains visible so the reasons behind each decision can be reviewed.

Operational review

For Agents, we track changes, quality shifts, and use patterns while keeping a path for rollback. The relationship to Generative AI Technologies remains visible so the reasons behind each decision can be reviewed.

Human governance

For Agents, we do not leave consequential decisions to automation alone and define accountable review points. The relationship to Generative AI Technologies remains visible so the reasons behind each decision can be reviewed.