Skip to main content
Help Centre Support Contact
Partners
Create Free Account
Create Free Account Book a Demo

AI in ComplyFlow

AI That Reads Against Your Criteria, and Shows Its Working.

A 40-page safety manual graded against your requirements in seconds, with the reasons on the record. Agents you build yourself. An assistant that answers from the live data, read-only if you want it to be.

Book a Demo See the Three Jobs
  • Safety & HSE
  • Procurement
  • Contractor Admins
  • Operations
  • IT & Data
AI usage included in Enterprise plans since 24 March 2026

What AI in ComplyFlow Does.

AI in ComplyFlow does three jobs. It reviews the documents contractors submit against the criteria you set and records the grade and reasons. It drafts checklists and inductions from your material. And through MCP it answers questions from your live record, changing nothing unless you allow it.

  • Review. A safety plan, SWMS, certificate, or prequalification answer read against the criteria you set, and graded with the reasons.
  • Draft. An inspection checklist that fits the site, and an induction drafted from your own material.
  • Ask. ChatGPT, Claude, or GitHub Copilot reads your incidents, inspections, suppliers, Workers, risks, plant, sites, and permits through MCP. Read-only if you want it to be.
  • You build the agent, without code. Pick a form type, choose the questions, keep or edit the criteria the product drafts for you.
A safety manager at a site office desk reading a thick printed safety manual beside a laptop, with a pen in hand and sticky notes on the pages

How the AI Works

Your Criteria in the Middle. Documents In. Decisions Out.

Read it left to right: what your people and contractors put in, the criteria you set that everything is read against, and what comes out for a person to act on.

What goes in

A safety plan or method statementUploaded by the contractor against a requirement review
A prequalification answer and its evidenceA text, text area, or file upload question with an agent on it review
A licence, ticket, or insurance certificateThe document a Worker or supplier submits
Your own procedures and documentsThe material a course or induction is drafted from draft
A question in plain EnglishAsked in ChatGPT, Claude, Claude Code, or GitHub Copilot ask
Integrate any existing system and hardwareIf it has an API, it belongs on this drawing: access control, CMMS, ERP, identity, BI Universal
PrequalificationWorkforce ComplianceTraining & InductionSite AccessVisitor Sign-InSite DocumentsDigital PermitsInspections & AuditsPlant & EquipmentIncident ManagementRisk Management Your Criteria. Read by AI.

What comes out

A grade per requirement, with the reasonsOn the document, for the approver and the audit
A score on the submissionThe reviewer sees the answer and the assessment together
The expiry read and the approver’s queueThe approver still decides; the AI recommends
A draft checklist or courseFrom your own material, edited by you draft
The answer, from the live recordWithin the user’s own permissions ask
Email and mobile alertsThe people who need to act hear about it where they already are Real-time

The AI reads against criteria you set, per form type and per requirement. Nothing it produces changes a record on its own; a person approves, rejects, publishes, or closes.

How It Works

Six AI Features & What Each One Does.

One feature at a time: what goes in, what the AI does with it, and what a person still decides.

AI Document Review: Expiries Caught at Upload.

A Worker or Supplier uploads a licence or insurance certificate. Before it reaches the approver, where you turn it on, the AI has read it against your criteria for that document type, pulled the expiry off the page, and recorded what passed.

  • Criteria set per document type
  • The expiry read from the document itself
  • The approver still decides

AI Document Review, in full

AI Agents: Submissions Scored Before They Are Read.

Name the agent, choose the form type and the questions, and keep or edit the criteria the product drafts. From then on every answer on that form is scored against your criteria before your reviewer opens it.

  • Criteria suggested by the product, marked as such
  • A custom criterion in your own words
  • One agent per form type; several on one question

AI Agents, in full

AI Prequalification: Suppliers Approved Sooner.

A Supplier answers a prequalification question and attaches the evidence. The agent on that question scores it against your criteria and names the gaps, so what reaches your reviewer is already better.

  • Text, text area, and file upload questions
  • The assessment recorded on the submission
  • A person reviews every response

AI Prequalification, in full

AI SWMS Review: Gaps Caught Before Work Starts.

A contractor attaches their SWMS to the permit. Before the supervisor approves the work, where you turn it on, the AI has read it against your criteria and told the contractor what would fix each gap.

  • Read against your criteria, not a generic standard
  • Feedback the contractor can act on
  • The supervisor approves or rejects

AI SWMS Review, in full

AI Course Creator: Training in Minutes.

Point the course creator at your site rules and procedures. It drafts the screens and the quiz; you edit, then publish in Training and assign by Worker category or site.

  • Drafted from your own documents
  • Edited and published in Training
  • Assigned by category; completions chased

AI Course Creator, in full

AI Assistants via MCP: Ask Your Record, Skip the Report.

A safety manager asks which sites reported incidents this month. Through MCP the assistant reads the register within the scopes on their token and their own site permissions, and answers with the rows.

  • ChatGPT, Claude, Claude Code, and GitHub Copilot
  • Read-only if you want it; write scopes if you want it to act
  • Tokens scoped per module, expiring within a year

AI Assistants via MCP, in full

What It Covers

Three Jobs: Review, Draft, Ask.

Everything below is in the product today. Nothing here is a roadmap.

Review

  • AI document review

    A document graded against your requirements, with reasons, before approval.

    • Per requirement
    • Graded

  • AI agents on form questions

    An agent reviews a text or file answer as it is submitted.

    • Per form type
    • Several per question

  • AI prequalification

    A supplier’s questionnaire and evidence assessed against your criteria.

    • Suppliers

  • AI SWMS review

    A contractor’s SWMS read against your criteria before the work is approved.

    • Permits
    • Review

  • Criteria drafted for you

    The wizard suggests criteria; you keep, edit, or add your own.

    • Wizard
    • Custom criterion

  • The decision on the record

    Grade, reasons, and criteria stay with the document for the audit.

    • Audit trail

Draft

  • Inspection checklists

    A checklist that fits the site, with corrective actions suggested.

    • Per site
    • Actions

  • Course and induction creator

    An induction drafted from your procedures, then published in Training.

    • Training module

  • Custom agents

    An agent for any review you run: form, questions, criteria.

    • No code

  • Feedback the contractor can act on

    The gaps and what would meet each criterion, downloadable.

    • Download

Ask

Each feature with its own page is linked from its name; the rest link to the Help Centre article that documents them.

Model Context Protocol

The Third Job: Ask. Your Assistant Reads ComplyFlow.

What it is
MCP is the open standard that lets an AI assistant work with another system safely. ComplyFlow ships an MCP server, so ChatGPT, Claude, Claude Code, or GitHub Copilot can work with your compliance record.
What it lets you do
Ask which sites reported incidents this month, who on site is not cleared, or what is overdue on the risk register, and get the answer from the live record, in the assistant you already have open.

Read-only if you want it to be. The assistant sees what you may see, at your assigned sites; give its token write scopes and it can act on the answer as well.

Our own MCP server, live since June 2026. The first among the contractor compliance platforms we track. Read the MCP Guide
MCP Claude and Claude CodeGitHub CopilotChatGPTGemini
  • Which sites reported incidents this month?
  • Who is on site today with an expired licence?
  • Which inspections are overdue, and whose?
  • Summarise the open risks at Marlow Point

Who It Is For

What AI in ComplyFlow Means for Me.

Find your job. The three lines under it are what the three AI jobs change for you.

ComplyFlow Is Already Trusted.

Documents at property, transport, resources, manufacturing, government sites, and more are already reviewed on ComplyFlow.

  • Toll
  • National Intermodal
  • BlueScope
  • ISPT
  • Maersk
  • NSW Planning, Industry and Environment

Contact Us

Tell Us About the Documents You Dread Reviewing. We Will Tell You What Is Possible.

Describe what your team reads by hand and what you need out of it. Someone who has set AI grading up for procurement and safety teams will come back to you.

  • What your requirements would look like as grading criteria
  • Which of your form questions suit a review agent, and which do not
  • What an assistant could and could not read through MCP, and on whose permissions
Book a Demo Instead

A straight answer from someone who has set this up before, not a brochure.

Send Us a Message

Tell us what you need and who you are.

Send Message

The form loads from HubSpot. If it does not appear, the button takes you to the contact page.

A stack of contractors’ safety documents and method statements in ring binders on an office desk, sticky notes and a highlighter on top, a monitor asleep behind

How It Stacks Up

Where AI Review Usually Lives, and What Each Misses.

Most teams read documents themselves, paste them into a general chatbot, or use AI bolted onto a system that does not hold the record.

Reading it yourselfThorough on a good day; 40 pages at 4:30 on a Friday is notA general chatbotKnows nothing about your requirements or your contractorAI bolted onto another systemThe result lives somewhere other than the record ComplyFlowOne record, your standard
Reads against your requirements, not a generic standard PartlyPartlyPartly Criteria you set, per form type and per requirement
The grade and the reasons on the Worker or supplier record PartlyNot therePartly On the document, visible to the approver and the audit
Consistent from the first document to the thousandth Not therePartlyBuilt in The same criteria, every time
You build the agent without a developer Not therePartlyPartly A four-step wizard; criteria drafted for you
Answers questions from the live compliance data Not thereNot therePartly MCP into ChatGPT, Claude, and Copilot, on your permissions
Changes your data only if you allow it PartlyBuilt inPartly Read-only tokens unless you add write scopes; the approver still decides

This compares kinds of approach, by how they are sold, not named vendors. Named comparisons, with dates and sources, live on the comparison pages.

What You Get

What the AI Delivers, in Plain Words.

Fewer hours reading, the same standard applied to every document, and answers without opening a dashboard.

A safety manager in a site office leaning back from two monitors, typing a question on a laptop, with a hard hat and a two-way radio on the desk

The 40 Pages, Read Before You Open Them

A grade per requirement and the passages that earned it. Your approver decides in minutes.

The Same Standard, Every Document

The criteria you set are the criteria applied, on the first submission and the thousandth.

Agents Built by the People Who Know the Work

A safety manager builds a review agent in four steps. No developer, no ticket.

Drafts, Not Blank Pages

A checklist or an induction, drafted from your material and edited by you.

Answers in the Assistant You Already Use

Which sites had incidents, who is not cleared, what is overdue: asked in ChatGPT, Claude, or Copilot.

Nothing Changed Unless You Allow It

The assistant is read-only unless you give it write scopes. Review agents recommend. Your people approve, reject, and close.

Getting Started

We Set It Up With You. We Stay With You.

You are not handed a login and left to it. Our onboarding team turns your requirements into criteria, builds the first agents with you, and stays on hand once the first documents are graded.

  • Mitch Bourne, ComplyFlow
  • Jessica Morgan, ComplyFlow
  • Sam Bourne, ComplyFlow
  • Phil Wallach, ComplyFlow
  • John McCann, ComplyFlow
  1. 1 We Read Your Requirements

    What each type of Worker and supplier must hold, and what a good document looks like to you, becomes the criteria the AI reads against.

  2. 2 We Build the First Agents

    Document review on the requirements that take your team longest, and an agent on the prequalification questions that matter most.

  3. 3 We Connect Your Assistant

    A scoped token, the MCP server configured in Claude Code or Copilot, and the first questions answered from your data.

  4. 4 You Go Live, We Stay Close

    Training for your approvers, a Help Centre for everyone, and a support team that picks up the phone.

  • ISO 27001 certified ISO 27001Certified 2019
  • AWS Qualified Software Certified 2023
  • GDPR, General Data Protection Regulation Compliant 2020
  • Microsoft Okta Single sign-on

Security & Data

Certified, Audited & Hosted in Australia.

Your compliance record is the evidence you rely on when somebody asks, so where it lives and who can reach it matters. ComplyFlow is ISO 27001 certified, runs on AWS in Australia, and your people sign in with the accounts they already have.

Questions

Questions People Ask About the AI Before a Demo.

Does the AI approve documents on its own?

No. It reads a document against your criteria and records a grade with the reasons. Your approver sees both alongside the document and decides. Agents on form questions assess; a person decides.

What does it read against?

Your criteria. When you build an agent the product suggests criteria for the kind of document it will review, marked as drafted by AI, and you keep, edit, or replace them. The founders describe the review routes as database driven: what the AI checks is what you configured.

Which AI assistants can connect, and what can they do?

ChatGPT, Claude, Claude Code, and GitHub Copilot, through the ComplyFlow MCP server, and any other assistant that speaks MCP. They can look up and summarise incidents, inspections, suppliers and contractors, Workers, the risk register, plant, sites, and permits, within the token’s scopes and the user’s permissions. Give the token read scopes only and they cannot change anything; add write scopes and they can act on the answer as well.

How is the connection secured?

Four layers: a personal API token that expires within a year and is revoked the moment you confirm it; scopes that limit the token to named modules, read-only unless you add write access; the permissions and site assignments of the staff user who created it; and isolation between organisations.

What does the AI cost?

AI usage has been included in Enterprise plans since 24 March 2026. Other plans pay as they go, with usage measured in tokens and shown in real-time in the billing dashboard.

Is our data used to train anything?

That question deserves a written answer from us rather than a line on a web page. Ask for the Information Security Policy and the AI data-handling statement as part of your security review, and we will provide both.

See It on Your Own Documents.

Book a 30-minute demo. Bring a safety plan or a SWMS you would rather not read again; we will build the criteria live, grade it, and show you the reasons. No slides, no hard sell.

Book a Demo Speak to Us
  • ISO 27001
  • Hosted on AWS
  • Microsoft & Okta SSO
  • API & MCP
  • Data in Australia

Compliance you can prove, instantly.