Who can customise Fieldproxy through AI?

Only administrators, and only when the workspace has Allow build switched on and the connection has the build scope.

Can a customisation be undone?

Yes. Apps can be rolled back and automation versions restored, and builds only ever add tables and columns, never drop them.

Customise the software · Fieldproxy MCP

Change the software itself, by asking

From Claude, ChatGPT or Copilot in Teams, on your live field service data, with a confirm step before anything changes.

Book a demo How it connects

Reply to Claude...

Fieldproxy

ClaudeChatGPTCopilot in Microsoft Teams

Illustration of Fieldproxy's MCP tools inside Claude, ChatGPT and Copilot. Names and data are examples.

Short answer

Customise the software from ChatGPT, Claude or Copilot: how does it work?

With Fieldproxy's MCP server, an administrator can ask Claude, ChatGPT or Copilot to add a field, build a screen, create a table, or set up an automation or a voice or text agent. Each change is built as a draft in a sandbox copy of the workspace, checked against the database, and promoted to live only when approved. No other field service AI connector we checked can do this.

Last verified September 27, 2026

Real requests

What people ask, and the tools it calls

You ask	Fieldproxy tools	You get
“Add a warranty expiry date to every job”	add_column, validate_app	A new field on the job screen and list, as a draft
“Build a subcontractor compliance screen that flags missing insurance”	create_table, create_app, validate_app	A new table and screen on your real data
“Email the service manager 30 days before a warranty expires”	save_automation, simulate_automation	An automation, simulated and saved switched off
“Make a tool that lists a customer's overdue invoices”	save_workspace_tool, test_workspace_tool	A saved SQL tool every AI connection can call
“Push the sandbox changes to live”	plan_promotion, confirm_promotion	A promotion plan, applied on your confirm

Guardrails

Your AI proposes. A person confirms.

Built for operations with branches, teams and an IT review, not a single login.

Nothing changes on one call

Every write, send or action is a proposal the user confirms within 30 minutes. Writes can be undone. More than 5 rows needs bulk permission, and more than 1,000 is refused.

Keys scoped like API keys

Limit a key to certain tables, certain rows ("only the North region's jobs"), hidden columns, insert/update/delete, and an expiry from 1 hour to 90 days. Postgres enforces the row limits.

Builds save as drafts

Apps and automations are checked against the database before they save, new automations and agents are saved switched off, and public apps are never changed.

Sends are limited

Email goes only from the user's own mailbox, at most 20 sends an hour per key, inside the workspace's quiet hours. A sandbox never sends.

Everything is logged

Every call is written to an audit log with the tool, key, person and outcome. Administrators see every key and connected app, and revoking one applies on the next request.

FAQ

Questions

Who can customise Fieldproxy through AI?: Only administrators, and only when the workspace has Allow build switched on and the connection has the build scope.
Can a customisation be undone?: Yes. Apps can be rolled back and automation versions restored, and builds only ever add tables and columns, never drop them.

Customise the software, from the chat

Book a demo