Hire an AI order fraud and bot-access planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A chargeback watch line, with the rates that matter to your processor
• Rules by order risk level, saying what to do with low, medium and high risk orders and when to cancel
• A review checklist for held orders and a monthly loop to tune the rules
• A policy to permit, verify, challenge or prevent each type of visitor, with limits per account and per address
• Alerts on simple signals, and the exact wording for sign-in and reset messages

How it does the job well

• Name the asset, the threat and the impact before recommending controls.
• Rank findings by real risk (likelihood and impact), with evidence for each.
• Prefer fixes that remove a problem over warnings that rely on people.
• Cite the exact law, standard or clause for compliance and legal points, and recommend qualified review.

Mistakes it avoids

• Long lists of generic issues with no evidence they apply.
• Testing or scanning systems without permission.
• Presenting a legal opinion as final.

What a good result looks like

An example, not your task: You see chargebacks, repeated small card charges, fake sign-ups or odd traffic, and want rules in place before they cost you.

• Fraud rules setter file. A chargeback watch line, rules for low, medium and high risk orders, extra card check settings and a review checklist.
• Monthly loop. A routine to tune the rules each month using your blocked and disputed orders.
• Bot and AI agent access plan. Which people, bots and AI agents may reach each page, with a permit, verify, challenge or prevent choice.
• Limits and alerts. Limits per account and per address for sign-in, reset and checkout, plus alerts on simple signals.
• Sign-in and reset wording. The exact messages to show on sign-in and password reset pages.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Set the fraud rules. Checks you have enough orders to tune rules, sets a chargeback watch line, writes a rule for each risk level, uses an extra card check only for higher-risk orders, and adds a review checklist.
• Plan bot and agent access. Takes step 1's rules and your export from two to four weeks of running them. Names the attack from your data, such as stolen passwords or card testing, sets alerts, lists which bots and agents reach each page, and gives an allow, check or block policy with limits at the edge.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id stop-fake-orders-card-testing-and-bot-abuse only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/stop-fake-orders-card-testing-and-bot-abuse/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your orders per month and average order value
• Your chargebacks over the last 3 months (count and rate)
• Your payment setup, such as Shopify Payments or another gateway
• How many hours a week someone can review held orders
• Which pages bots can reach (cart, checkout, sign-in, sign-up, reset, gift card check)
• After two to four weeks, your blocked, held and disputed orders, failed sign-ins and repeated small card charges

Tools and access

• Shopify Flow: It runs the rules above on the order risk rating, using free fraud templates you can edit.
• Any good chat AI: Any current chat AI can write the rule set from your numbers.
• Your platform's own bot protection: On a hosted store this is usually the first and main layer. Turn it on before adding anything else. Check your plan to see what it includes at no extra cost.
• Cloudflare: A common edge service with bot and rate-limit settings. It suits stores with a technical person. Some bot and rate-limit settings need a paid plan. Check the price before you commit.
• Any good chat AI: Any current chat AI can write the policy and wording from your description. A free plan is enough for a first draft.

Functions and deliverables

• Order fraud and bot-access planner: Share order patterns, payment setup and incident evidence. Get proposed fraud rules, a review routine and a later bot-access plan.
  • A chargeback watch line, with the rates that matter to your processor
  • Rules by order risk level, saying what to do with low, medium and high risk orders and when to cancel
  • A review checklist for held orders and a monthly loop to tune the rules
  • A policy to permit, verify, challenge or prevent each type of visitor, with limits per account and per address
  • Alerts on simple signals, and the exact wording for sign-in and reset messages
• Store fraud rules planner: Share your order volume and payment setup. Get fraud rules, a review routine and a chargeback watch line.
  • A rule set by risk level, ready to build in your platform
  • A manual review checklist and a 24-hour release-or-cancel routine
  • A chargeback watch line with a warning level before the processor's limit
  • A monthly loop to tune the rules, and a list of checks it could not make
• Bot and AI agent access planner: Plan which bots and AI agents to allow, check or block on your store. Give it your traffic and flows. You get a policy, limits and alerts.
  • A one-page policy: who is allowed, checked or blocked at each step
  • A rules table per flow with what to count, the limit and what happens next
  • Exact wording for sign-in, reset and sign-up messages
  • Alerts to set, a monthly review list and a plan by week
• Order risk review rule planner: Share order numbers, payment disputes and review time. Get draft risk rules, checks of current defaults and limits to confirm with your payment provider.
  • Rules for low, medium and high risk
  • A review checklist for held orders
  • A chargeback watch line
  • A monthly loop to tune the rules
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up

Tasks you can use it for

• You see chargebacks, repeated small card charges, fake sign-ups or odd traffic, and want rules in place before they cost you.
• Your processor has warned you about your dispute rate.
• You want to decide whether AI shopping assistants may browse and buy from your store.

Limits to check before starting

• Your store has very few orders a month: there is too little data to tune rules, so check each order by hand and ask your payment provider for its basic fraud settings.
• Nobody has time to review held orders: set no hold rules yet, and use only the block rules your payment provider already offers.
• You need to recover money from a chargeback you already got: reply to the dispute through your payment provider, with your order and shipping proof.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Give it your order numbers, chargebacks and how much review time you have. It will not hold orders nobody can review.
• Turn the rules on and run them for two to four weeks. Export the blocked, held and disputed orders, failed sign-ins and repeated small card charges.
• Bring those back, and say if you want AI shopping assistants allowed, partly allowed or blocked.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/stop-fake-orders-card-testing-and-bot-abuse for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.