The PII Detection Tool
Scan text for personally identifiable information — names, emails, SSNs, card numbers — and return what and where, so an agent can catch sensitive data before it flows into a prompt, log, or output.
Autonomy without guardrails is a liability
An agent that can act can also leak PII, expose a secret, exceed permissions, or run up cost — silently. Putting agents in production means baking in detection, redaction, permission checks, and traceability, or the first incident ends the program.
Data leakage
PII and secrets slip into prompts, logs, and outputs.
Over-permissioned
Agents act beyond what their role should allow.
No accountability
Without a trace, you can’t explain what an agent did or why.
Runaway cost
Unbounded tool use burns budget with no early warning.
PII Detection, without the risk
Capability
What it does
Find personal data before it leaks.
it scans text for personally identifiable information and returns the type and location of each match.
Assignable to any agent
How it works
Predictable, inspectable behavior
Designed to be reliable.
detection runs inside your perimeter across many PII categories, returning precise spans, so an agent can gate, redact, or route sensitive data before it moves.
Every call logged
Governance
Private, governed, on-premise
Runs inside your perimeter.
These controls run inside your perimeter and feed a single audit trail, so detection, redaction, permission checks, and cost limits are enforced locally — the governance layer that makes agent autonomy defensible to security and compliance.
Per-tenant, logged
Parameters
The pii_detect tool accepts these inputs when an agent calls it. Required inputs are flagged.
default: 0.5 Optional Minimum confidence to report a match.
How the PII Detection tool works in practice
PII Detection is a security, governance & ops tool you assign to a VDF AI agent. It scans text for personally identifiable information and returns the type and location of each match. Its hallmarks — Detect, PII, Located — let an agent rely on it as a dependable step in a larger task rather than a brittle one-off script.
Under the hood, detection runs inside your perimeter across many PII categories, returning precise spans, so an agent can gate, redact, or route sensitive data before it moves. It expects text as required input, so calls are explicit and easy to audit. Every call is scoped to the requesting tenant and written to an audit log, so the capability is safe to run inside a regulated, on-premise environment — the same governance model behind every VDF AI tool.
Teams reach for PII Detection when they need to handle prompt hygiene, log safety, and compliance. It rarely works alone — pair it with PII Redaction, Secrets Scan, and Audit Trail Query to build a complete, governed workflow, then compose those steps into an on-premise VDF AI Network.
Where PII Detection pays back
Prompt hygiene
Catch PII before it enters a model prompt.
Log safety
Detect sensitive data before it’s logged.
Compliance
Locate PII to meet privacy requirements.
Routing
Flag records that need special handling.
Assigned to agents, orchestrated as networks
On VDF AI, an industry’s use cases map to agents, and you assign tools like this one to those agents. Compose multiple agents into a governed, on-premise network.
What changes after you assign it
Questions about the PII Detection tool
What is the PII Detection tool?
It scans text for personally identifiable information and returns the type and location of each match. Assigned to a VDF AI agent, it runs under role-based policy with full audit logging so the capability is safe to use in production.
What PII does it detect?
Common categories such as names, emails, phone numbers, national IDs, and payment cards, with configurable types.
Does the text leave our environment?
No. Detection runs on-premise, so sensitive text is never sent out.
What inputs does the PII Detection tool need?
It requires text, and optionally accepts entity_types and min_confidence. Each parameter is validated when an agent calls the tool, and the full call is logged for audit.
Which tools pair well with PII Detection?
PII Detection is commonly assigned alongside PII Redaction, Secrets Scan, and Audit Trail Query. On VDF AI you compose several tools and agents into a single governed, on-premise network.
Does it run on-premise?
Yes. Like every VDF AI tool, it can run on-premise or in your sovereign cloud, scoped per user and audit-logged, so your data never leaves your perimeter.
How do agents use it?
You assign the tool to an agent under a role-based policy; the agent calls it as one step in a task, and several agents and tools can be orchestrated together as a governed VDF AI Network.
Assign PII Detection to these agents
These VDF AI agents can be assigned this tool. Open an agent to see the full toolkit it can run.
Tools that work well alongside this one
Where this tool delivers value
Put PII Detection to work
See the PII Detection tool assigned to an agent and orchestrated in a governed, on-premise network.