DEMO MODE Reset Exit Demo
F FieldOps

Import Data

Select a data type, validate required fields, map columns, then review before importing.

LLM API settings Download sample CSV
1 Select data type 2 Upload CSV 3 Validate fields 4 Map columns 5 Review and import
Imports run as a dry-run validation first. LLM assistance can suggest column mappings, but imported customer, invoice, team, job, and quote data is never sent to a model unless the tenant explicitly approves it.

1. Select Data Type

Mandatory fields and validation rules change based on what you are importing.

Customers
Client names, contact details, addresses, and account notes.
Jobs
Field service work orders, statuses, schedule dates, priorities, and locations.
Quotes
Quote numbers, customers, totals, validity windows, and approval state.
Invoices
Invoice numbers, customers, amounts, due dates, and payment state.
Team
Technicians, supervisors, managers, office users, roles, and contact details.
Timesheets / payroll
Approved labour hours, payroll rates, job links, and cost-center references for profitability.

2. Upload CSV

CSV only. Validate headers before mapping rows into FieldOps.

Validation checks required headers, row values, formula-like cells, dates, statuses, and safe CSV protocol rules before any write happens.

3. Mandatory Fields

Customers import schema.

Required
name
Recommended
email phone address_line_1
Optional
company_name address_line_2 town_city postcode notes status

Validation Preview

Sample headers for this type are validated before import.

name email phone address_line_1
Validation status
Ready to map
Missing required
0
Unknown headers
0
Mandatory headers are present. The next step is row-level validation and field mapping.

LLM Mapping Assistant

Optional AI support for header matching and validation explanations.

Import mapping assistant
OpenAI · gpt-4.1-mini
sandbox_ready
Enterprise import reviewer
Azure OpenAI · tenant-deployment-name
endpoint_required
Quote wording reviewer
Anthropic · claude-sonnet-4-5
owner_approval_required
Private model endpoint
Custom compatible endpoint · custom-model
https_endpoint_required
OpenAI
ready_for_api_key
Azure OpenAI
ready_for_endpoint_and_key
Anthropic
ready_for_api_key
Google Gemini
ready_for_api_key
Custom compatible endpoint
requires_https_endpoint
Add or manage LLM API

Import Protocol

CSV format
Use RFC 4180-style CSV: comma-separated fields, first row headers, double quote escaping, and consistent line endings.
Encoding
Use UTF-8 text without executable macros, scripts, or binary content.
Safety limits
Validate file extension, MIME type, size, row count, headers, and row-level values before import.
Dry run first
Run field mapping and validation before writing any customer, job, quote, invoice, or team record.
Auditability
Store import type, header map, validation summary, idempotency key, user, tenant, and row error report.
Formula neutralisation
Treat cells beginning with =, +, -, or @ as unsafe for export and review before import.

AI Safety Guardrails

Do not send full imported files to an LLM by default.
Use headers and a small redacted sample for mapping suggestions only after user approval.
Never include API keys, passwords, payment card data, or private notes in prompts.
Store prompt and response hashes for audit instead of raw customer data.
Require human review before applying model-suggested mappings or row fixes.