AI Agent Governance

When an autonomous agent can call tools, spend budget, and chain actions, the risk is not the model output — it is the side effect. EVE governs the moment before a tool executes: it can block or require approval before a tool runs, block individually-permitted actions that combine into a prohibited sequence, and enforce deterministic budget limits.

Controls for agent behavior

Tool-call governance — route each agent tool call through a deterministic ALLOW / BLOCK / MODIFY decision before execution.
Action-sequence governance — actions that are each permitted alone can still be blocked when they form a prohibited sequence.
Budget and resource limits — a permitted call executes until the configured limit is reached, then further calls are blocked.
Behavioral anomaly detection — deterministic statistical detectors (rolling/robust z-score, EWMA, CUSUM) flag deviations from a window baseline.
Signed monitoring envelopes — summarize agent behavior over a window, signed for later review.

SDK example

Route an agent's tool call through governance (Python, pilot/private distribution):

from eve_coreguard import EVE

eve = EVE()

def governed_call(tool, arguments):
    result = eve.govern_tool_call(
        tool=tool,
        arguments=arguments,
        context={"tenant_id": "org_abc", "principal_id": "agent_alpha", "session_id": "sess_1"},
    )
    if result["action"] == "BLOCK":
        raise PermissionError(result["reason_codes"])
    return run_underlying_tool(tool, arguments)  # only reached on ALLOW/MODIFY

TypeScript (ESM, Node >= 18):

import { EVE } from "@eve/coreguard";

const eve = new EVE();
const result = await eve.governToolCall({
  tool: "delete_records",
  arguments: { table: "invoices", filter: "all" },
  context: { tenantId: "org_abc", principalId: "agent_alpha", sessionId: "sess_1" },
});
if (result.action === "BLOCK") throw new Error(result.reasonCodes.join(","));

Readiness

Agent governance controls (sequence, budget, anomaly detection, monitoring envelopes) are PILOT_READY and part of the pilot-validated core governance architecture. The Python SDK entry point (from eve_coreguard import EVE) is a release-candidate core client. Framework adapters other than the generic adapter are experimental.

Limitations

Behavioral anomaly detectors are advisory unless wired to a deterministic enforcement action.
Sequence state is per-session and in-process in the pilot; durable multi-instance state is a deployment concern, and durable cross-instance budgets require a shared store.
Wrapper-enforced framework adapters can be bypassed by a direct call to the underlying tool. Hard enforcement requires a gateway or sidecar; cooperative hooks are not an unbypassable boundary.

Next step

Bring your own agent and policies into a pilot and see which tool calls, sequences, and budgets get blocked — with signed evidence for each decision.