How it works
Observe. Detect. Understand. Decide. Enforce.
Aegis becomes the control layer between your agents and the real world. Here is exactly what happens on every action.
The agent acts
An autonomous agent decides to call a tool — a database, a browser, a shell, an external API. It cannot execute yet.
Aegis intercepts
Through the Python SDK, REST gateway or MCP Security Gateway, the action is submitted to Aegis before execution.
Identity is verified
The Permission Engine checks the agent's registration, tool bindings and user delegation. The Trust Engine scores the agent and session trust class.
Policies decide
The deterministic Policy Engine evaluates active rules with strict precedence. No matching policy means deny — the default is closed.
Risk and threats are scored
An explainable Risk Engine produces a 0–100 score from operation sensitivity, environment and trust. Threat detectors scan payloads for injection and dangerous patterns.
The decision is enforced
ALLOW, BLOCK or REVIEW — with every reason recorded. REVIEW creates a human approval request that pauses the action until a person decides.
Everything is audited
Every evaluation lands in an append-only audit trail with redacted parameters, full provenance and correlation IDs for end-to-end reconstruction.
The evaluation pipeline, in code order.
This is the real sequence implemented in the Aegis evaluator: permission and trust run first and can short- circuit to BLOCK; policy sets the base decision; risk and threat thresholds can escalate it; human approvals resolve REVIEW outcomes.
Read the docsACTION
Agent intent is intercepted
CONTEXT
Agent, tool and session verified
THREAT ANALYSIS
Deterministic detectors run
RISK SCORE
Explainable 0–100 assessment
POLICY
Rules evaluated with precedence
DECISION
ALLOW · REVIEW · BLOCK