iGamingReview Prompt

ChatGPT Prompt for Responsible Gambling Risk Checks

This review prompt analyzes player activity data against four families of problem gambling indicators, session behavior, financial patterns like loss chasing and deposit velocity, gameplay escalation, and self-exclusion circumvention, then grades each player from LOW to CRITICAL with a recommended intervention. Every finding is mapped to a regulatory basis, including the UKGC LCCP Social Responsibility Code, the MGA Player Protection Directive, Curacao license conditions, and Australia's National Consumer Protection Framework, making it useful for responsible gambling analysts and compliance teams at iGaming operators.

How to use this prompt

1
Paste the prompt into your deepidv dashboard agent, Claude, ChatGPT, or Gemini, then provide anonymized player activity data: sessions, deposits, withdrawals, bet sizes, and limit-change history.
2
Trim the regulatory mapping to the licenses you actually hold, for example UKGC and MGA only, so recommendations cite the right obligations.
3
Expect a per-player table listing each risk indicator, its severity from LOW to CRITICAL, the supporting evidence, the recommended action, and the regulatory basis.
4
Route MODERATE flags into proactive player communications and HIGH or CRITICAL flags into your documented intervention workflow, keeping records for license reviews.
5
Use the findings to tune your automated monitoring thresholds, and never paste personally identifiable player data into third-party AI tools.

The prompt

You are a responsible gambling analyst. I will provide player activity data. Analyze it for behavioral indicators of problem gambling and recommend intervention actions based on regulatory requirements.

Evaluate against these risk indicators:

1. SESSION BEHAVIOR — Duration exceeding 60min, unusual hours (2am-6am), >3 sessions/day, increasing frequency week-over-week

2. FINANCIAL PATTERNS — Deposit velocity (multiple deposits in a session), deposit escalation, loss chasing (immediate re-deposit after depletion), spend-to-income ratio (flag at >5%), reversal of withdrawals

3. GAMEPLAY INDICATORS — Bet size escalation, switching low-to-high stakes rapidly, multiple simultaneous games, chasing losses with larger bets

4. SELF-EXCLUSION AND LIMITS — Modified/removed deposit limits, re-registration attempts after self-exclusion, repeated support contacts to increase limits

For each indicator:
- 🟢 LOW: Normal recreational behavior
- 🟡 MODERATE: Early warning — recommend proactive communication
- 🔴 HIGH: Strong indicators — recommend mandatory intervention
- ⚫ CRITICAL: Immediate action — recommend account restriction

Map each to: UKGC LCCP Social Responsibility Code, MGA Player Protection Directive, Curaçao conditions, Australia National Consumer Protection Framework.

Present as: Player ID, Risk Indicator, Severity, Evidence, Recommended Action, Regulatory Basis.

I will now provide the player data.

Pairs with on deepidv

Sources & further reading

FAQ

What are the behavioral indicators of problem gambling that operators must monitor?

Regulators expect operators to watch for extended or late-night sessions, rising play frequency, deposit velocity and escalation, loss chasing such as immediate re-deposits after a depleted balance, withdrawal reversals, rapid bet-size escalation, and attempts to remove limits or re-register after self-exclusion. Under the UKGC LCCP Social Responsibility Code and similar regimes, operators must identify these patterns and intervene, not merely record them.

Can AI be used to screen players for responsible gambling risk?

Yes. AI can review session, deposit, and gameplay data against known risk indicators and grade severity far faster than manual review, which helps teams triage which players need proactive contact versus mandatory intervention. Operators remain responsible for the final decision and for documenting actions, and player data should be anonymized before it is shared with any external AI tool.

Run it with live verification data

These prompts work in any LLM. Inside the deepidv dashboard, Luna, Arbiter, and Arc run them against your real sessions, screening lists, and audit trails.

Book a Demo