Video How-To Guides
Each video shows one control end to end, on a real Netzilo Server, in about two minutes: the policy, what the person or the agent sees, and where the result is recorded. Every video links the guide that covers the same task step by step.
Pick by where the control runs. The browser extension governs AI apps and web pages, the AI Gateway governs every agent that calls through it, the Netzilo client governs every AI tool on a device, and the SDK governs an agent from inside its own process. The last group is for detection engineers and analysts: writing rules, testing them on recorded sessions, and following what an agent did.
Browser
AI apps and web pages, governed by the browser extension.
Browser · 1:47
Govern ChatGPT and Claude in the browser
Redact a customer ticket and block a private key in ChatGPT and claude.ai, with only the extension installed.
Browser · 1:45
Govern the tools a page gives to AI agents
A web app offers WebMCP tools to its assistant: results are redacted and a refund is stopped before it runs.
Browser · 1:59
Bring web apps' AI calls under the gateway
One routing guardrail sends a web app’s model calls through the AI Gateway as the signed-in user, on an approved model.
AI Gateway
Models, MCP servers and guardrails for every agent that calls through the gateway.
AI Gateway · 2:34
Govern model access, budgets and spend
Keep provider keys in the gateway, grant a team only its approved models and cap its daily spend.
AI Gateway · 1:59
Redact secrets and personal data
Apply redaction guardrails to a team and watch Claude Code finish its task while the model only sees placeholders.
AI Gateway · 2:07
Approve the MCP tools agents can use
Publish MCP servers through the gateway and grant a team one tool instead of a whole server.
AI Gateway · 1:43
Reroute instead of refuse
Serve requests for an unapproved model with an approved one, so developers keep working within budget.
Endpoint
Every AI tool on a managed device, governed by the Netzilo client.
Endpoint · 1:30
Govern every AI tool on a laptop
Claude Code and a homemade script with a personal API key get the same guardrails, on the device itself.
Your agents
The agents your teams build, governed from inside the process or through the gateway.
Your agents · 1:20
Govern the agents you build, through the gateway
Point an Anthropic SDK agent at the gateway with its own service identity, and its guardrails follow.
Your agents · 1:28
Govern the agents you build, from the inside
Two lines of the Netzilo SDK put an agent under the guardrails, with its processes and files in its session.
Detect & investigate
Write rules, test them on recorded sessions, and follow what an agent did.
Detect & investigate · 1:40
Investigate what an agent did
Go from a team to a person to a session, replay it on a timeline and see the behavior graph.
Detect & investigate · 1:56
Write your own detection rule
Turn a company policy, no agent may read payroll data, into a few lines of rule and enforce it.
Detect & investigate · 2:54
Keep agents on task
Use System One and an LLM as the judge to stop an agent from drifting outside the job it was built for.
Detect & investigate · 1:22
Test a guardrail before you turn it on
Replay a new guardrail on recorded agent sessions and see exactly what it would have stopped.
New videos land on the Netzilo YouTube channel ↗ first.
New to the building blocks in these videos? Start with the AIDR overview and the AI Agent Lifecycle, then follow the videos in the order of your rollout: the browser and devices people already use first, then the gateway, then your own agents.