Code Execution & Workspace Tool

The File Search Tool

Search the agent’s workspace for filenames or text content and get back matching paths and lines — so an agent can locate the exact code or config it needs without reading everything.

Explore VDF AI Agents
SandboxedRuns in an isolated workspace
GovernedEvery action logged
AssignableTo any engineering agent
100%On-premise capable
The Execution Gap

A suggestion isn’t a shipped change

An agent that can only propose code still leaves all the work to a human. To actually deliver, it needs a real, governed workspace where it can run code, edit files, test, and use Git — safely, and without touching anything you didn’t allow.

01

Read-only agents

Suggestions still require a human to run, test, and commit everything.

02

Unsafe execution

Running agent-generated code on real infrastructure is a security risk.

03

No verification

Without tests and builds, an agent can’t know its change works.

04

Ungoverned Git

Direct repo access with no policy or audit is a non-starter in the enterprise.

How the Tool Works

File Search, without the risk

Capability

What it does

Find files and text across the workspace fast.

it searches the workspace for a filename pattern or text content and returns matching paths and lines.

Tool
File Search

Assignable to any agent

SearchGrepMatchesFast

How it works

Predictable, inspectable behavior

Designed to be reliable.

search runs over the sandboxed workspace and returns ranked matches with context, so an agent finds the right place to act quickly and precisely.

Governed
Policy + Audit

Every call logged

ScopedLoggedGovernedOn-prem

Governance

Private, governed, on-premise

Runs inside your perimeter.

Execution runs in an isolated, on-premise sandbox scoped per tenant with full command and file audit logging, so an agent can do real work on your code without unsafe access or anything leaving your perimeter.

100%
On-Prem

Per-tenant, logged

On-premRBACAudit logSovereign
Inputs

Parameters

The file_search tool accepts these inputs when an agent calls it. Required inputs are flagged.

Name Type Required Description
query string Required Text or pattern to search for.
path string
default: .
Optional Directory to search within.
is_regex boolean
default: false
Optional Treat the query as a regular expression.
max_results integer
default: 50
Optional Maximum matches to return.
In depth

How the File Search tool works in practice

File Search is a code execution & workspace tool you assign to a VDF AI agent. It searches the workspace for a filename pattern or text content and returns matching paths and lines. Its hallmarks — Search, Grep, Matches — let an agent rely on it as a dependable step in a larger task rather than a brittle one-off script.

Under the hood, search runs over the sandboxed workspace and returns ranked matches with context, so an agent finds the right place to act quickly and precisely. It expects query 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 File Search when they need to handle locate code, config hunting, and refactor scoping. It rarely works alone — pair it with File Read, File List, and RAG Grep to build a complete, governed workflow, then compose those steps into an on-premise VDF AI Network.

Where it pays back

Where File Search pays back

Locate code

Find where a function or symbol is used.

Config hunting

Grep for a setting across the project.

Refactor scoping

List every file touching a term before changing it.

Debugging

Trace a string from an error back to its source.

How VDF AI connects it

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.

ROI Snapshot

What changes after you assign it

Faster
From suggestion to shipped
Verified
Changes tested before merge
Traceable
Every command audited
100%
Code never leaves your perimeter
FAQ

Questions about the File Search tool

What is the File Search tool?

It searches the workspace for a filename pattern or text content and returns matching paths and lines. 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.

Does it support regex?

Yes. Set is_regex to true to search with a regular expression instead of a literal string.

How is this different from RAG grep?

File search scans the live workspace directly; rag.grep searches an indexed repository snapshot for retrieval.

What inputs does the File Search tool need?

It requires query, and optionally accepts path, is_regex, and max_results. Each parameter is validated when an agent calls the tool, and the full call is logged for audit.

Which tools pair well with File Search?

File Search is commonly assigned alongside File Read, File List, and RAG Grep. 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.

Put File Search to work

See the File Search tool assigned to an agent and orchestrated in a governed, on-premise network.