Opencontroller by Lyzr
Opencontroller blog
Answers to the questions enterprises ask about governing AI agents
Agent governance basics
All in this topicDiscovery and shadow agents
All in this topicHow often should AI agent discovery scans run?
Run full AI agent discovery daily plus event-driven detection from cloud audit logs. Cadence by asset type, rate-limit tactics and delta rules.
What should you do with a shadow AI agent once you find it?
Contain the risk, find an owner, then decide within a deadline to register, block or retire it. A triage workflow with states, criteria and deadlines.
What permissions does AI agent discovery need in AWS, Azure and Google Cloud?
Read-only, metadata-level access: AWS SecurityAudit or ViewOnlyAccess, Azure Reader, Google Cloud Asset Viewer. Never secret values or write access.
Runtime control
All in this topicWhen should an AI agent be automatically quarantined?
A three-tier severity model for AI agents: which signals trigger automatic quarantine, which alert a human, which open a ticket, plus a pre-launch checklist.
How do you redact PII from LLM prompts at the gateway?
Redact, mask or block PII in LLM prompts at the gateway: a decision table by data type, layered detection and how to handle false positives.
How do you route AI agent policy violations into ITSM and incident tickets?
Route by severity: digest, owner ticket, on-call page, or automatic quarantine plus incident. Include agent, owner, policy and evidence in every ticket.
How do you enforce data residency for LLM and AI agent traffic?
Classify each request, route it only to model endpoints approved for that data class, and block or redact when no compliant route exists, at the gateway.
Gateways and cost
All in this topicHow do you route AI agents to self-hosted or internal models through an LLM gateway?
Register an OpenAI-compatible internal model with your LLM gateway, add health checks, and set routing and fail-closed fallback rules. Five steps.
Can an LLM gateway sit behind your existing API gateway?
Yes. Which layer handles auth, routing, token budgets and cost attribution, what breaks (streaming, timeouts) and the latency budget for both hops.
How do you attribute LLM costs to individual AI agents?
Tag every model call with agent ID and version at the gateway, record input, cached and output tokens, price them per model, and roll up by agent and team.
Evidence and frameworks
All in this topicHow do you red-team AI agents with multi-turn attacks?
Script multi-turn attacks on goals, tools, privileges and memory, map them to OWASP Agentic Top 10 IDs, and score each against clear pass/fail rules.
How do you replace AI governance spreadsheets and questionnaires with continuous evidence?
Turn each questionnaire item into a check answered from live data: inventory, identity, gateway logs, evals. Keep forms only for purpose and risk acceptance.
Buying and comparison
All in this topicPlatform Guides
All in this topicPut the framework into practice