Agentic AI Safety exit conditions
Candidate exit conditions for the Agentic AI Safety type. See the catalog overview for how to adopt these.
This type covers the safety of an agent or LLM feature the service exposes — prompt-injection resistance, output handling, bounded autonomy, and the transparency and risk-classification obligations of regimes such as the OWASP LLM and Agentic risk lists and the EU AI Act.
|
This is a defined, tiered Definition-of-Done type, but it ships no default-library conditions yet. Today it is satisfied by Akka’s own agent controls — guardrails, classifiers, sanitizers, and evaluations — which enforce these invariants inside the platform. The ids below are candidates for inspiration. |
Prompt and input safety
| Exit condition | What it checks |
|---|---|
|
User and tool input is screened for prompt-injection before it reaches the model, by an Akka guardrail or classifier. |
|
The system prompt and tool definitions cannot be extracted through crafted input. |
|
Inbound content is classified for policy-violating or unsafe categories before use. |
Output and action safety
| Exit condition | What it checks |
|---|---|
|
Model output is sanitized before it is rendered, executed, or forwarded to another system. |
|
The agent may call only the tools its task authorizes, within their granted permissions. |
|
No high-impact action runs without a bound — a budget, a confirmation, or a human gate. |
|
Actions classified as high-risk require recorded human approval before they proceed. |
Governance and transparency
| Exit condition | What it checks |
|---|---|
|
The feature is assigned a documented risk classification under the governing regime. |
|
Users are told they are interacting with an AI system where the regime requires it. |
|
Agent behavior is measured against a recorded evaluation set before ship. |
|
Each agent action is logged with enough context to reconstruct what it did and why. |