# Examples & Best Practices The Intelligems MCP server gives AI assistants access to your test results, personalization data, and Sitewide Analytics — all queryable in plain English. The examples below are organized by how you use Intelligems: as a **brand** managing your own store, or as an **agency** managing tests and performance for clients. ## For Agencies **1. Monthly Client Performance Review** *Use when preparing for monthly client calls* ``` For [CLIENT NAME], give me a comprehensive analysis of all tests completed this month. Include: 1. Which tests reached statistical significance and their winners 2. The estimated revenue impact of implementing winners 3. Key insights to share with the client 4. Any tests that should be ended early or extended ``` **What you'll get:** List of completed tests with win/loss status, revenue per visitor and gross profit uplift percentages, statistical confidence levels, and actionable recommendations for client discussion. *** **2. Cross-Test Pattern Analysis** *Use to find winning strategies that work consistently* ``` Analyze all completed tests for [CLIENT NAME] over the past 3 months. What patterns appear across multiple winning tests? What concepts (urgency, trust, social proof, simplification, etc.) consistently win or lose for this customer base? ``` **What you'll get:** Patterns across winning variations, concepts that resonate with the client's audience, and strategic direction for future testing. *** **3. Customer Segment Intelligence** *Use to understand how different customer types respond* ``` For [CLIENT NAME], compare how these segments respond across all tests: - Mobile vs Desktop visitors - New vs Returning customers Are there segments consistently outperforming? Should we be running segment-specific tests? Where's the biggest opportunity gap? ``` **What you'll get:** Conversion rates by device type, performance differences between new vs returning visitors, and recommendations for segment-specific optimization. *** **4. Profit Trap Detection** *Use to catch tests where more conversions = less profit* ``` Review all tests for [CLIENT NAME] and identify any "profit traps" - tests where conversion rate improved but revenue per visitor or gross profit per visitor decreased. Flag any tests where we might be winning the battle but losing the war. ``` **What you'll get:** Tests where conversion went up but profit went down, warnings about implementing harmful "winners", and true profit-focused recommendations. *** **5. Quarterly Test Roadmap** *Use for strategic planning* ``` Based on [CLIENT NAME]'s test history: 1. What test categories have delivered the best ROI? 2. What areas haven't been tested yet (blind spots)? 3. Based on winners, what specific follow-up tests should we run? 4. Prioritize 5 test ideas for next quarter by potential impact. ``` **What you'll get:** Analysis of highest-performing test categories, untested areas, and a prioritized test roadmap for the next quarter. *** **6. Cross-client performance scan** *Use to quickly identify which clients need attention* ``` Across all my clients, which accounts have seen the biggest drop in revenue per visitor or conversion rate over the past 30 days? Rank them by urgency so I know where to focus. ``` **What you'll get:** A prioritized list of clients showing performance deterioration, so you can triage proactively rather than waiting for clients to flag issues. *** ## For Brand Operators **1. Weekly Test Pulse Check** *Use for quick status instead of reviewing dashboards* ``` Give me a quick status on all my running tests: - Which have reached statistical significance? - Which are trending positive vs negative? - Any that should be ended early (clear winner/loser)? - Any that need more time to reach significance? ``` **What you'll get:** Status of all running tests, statistical significance levels, clear winner/loser identification, and recommendations for early stopping or extension. *** **2. Profit Opportunity Scan** *Use to find biggest revenue opportunities* ``` Looking at my completed tests from the past 6 months: 1. Which winning variations had the highest revenue per visitor lift? 2. Which had the highest gross profit per visitor lift? 3. Are there any winners I haven't implemented yet? 4. Rank my top 3 profit opportunities by potential monthly revenue impact. ``` **What you'll get:** Ranked list of winners by revenue impact, un-implemented winners leaving money on the table, and a prioritized implementation list. *** **3. My Best Customer Segments** *Use to know where to focus optimization efforts* ``` Across my tests, which customer segments perform best? Compare response rates by: - Device (Mobile vs Desktop) - Customer type (New vs Returning) - Traffic source (if available) Where should I focus my optimization efforts for maximum ROI? ``` **What you'll get:** Performance breakdown by device type, new vs returning comparison, and recommendations for resource allocation. *** **4. Testing Strategy Health Check** *Use to evaluate testing program effectiveness* ``` Review my testing history and tell me: 1. How many tests have I completed in the past 3 months? 2. What's my win rate (% of tests with significant winners)? 3. What types of tests am I running most? What am I missing? 4. Am I building on previous learnings or testing randomly? 5. What's my testing velocity compared to best practices? ``` **What you'll get:** Test completion count, win rate analysis, test type distribution, and recommendations for improving your testing program. *** **5. Price Sensitivity Analysis** *Use to understand customer price tolerance* ``` Based on my price tests and offer tests: 1. What have I learned about my customers' price sensitivity? 2. Are there products or categories that are more price-sensitive? 3. Do new vs returning customers respond differently to pricing? 4. What's the optimal discount threshold based on test data? ``` **What you'll get:** Price sensitivity insights from test data, segment-specific price response differences, and data-backed discount recommendations. *** **6. Store health check** *Use for a quick pulse on overall performance* ``` How did we perform last month vs the month before? Summarize the key changes — visitors, conversion rate, revenue per visitor, and AOV. Flag anything that moved meaningfully in either direction. ``` **What you'll get:** Period-over-period comparison across core KPIs with automatic flagging of notable changes. *** **7. Channel quality ranking** *Use to understand which traffic sources are actually driving revenue* ``` Which marketing channel is bringing in the most valuable customers right now? Rank all active channels by revenue per visitor and conversion rate. Flag any channels where traffic is growing but revenue quality is declining. ``` **What you'll get:** Channel-by-channel RPV and CVR breakdown, quality vs. volume analysis, and identification of any channels showing efficiency deterioration. *** **8. Mobile vs desktop gap** *Use to diagnose device-level conversion issues* ``` How does mobile compare to desktop in terms of conversion rate and revenue per visitor? Has the gap between the two changed over the past 30 days? Which device is driving most of our visitor growth? ``` **What you'll get:** Side-by-side device performance metrics, trend direction for each device, and context on where growth is coming from. *** **9. New vs returning customer analysis** *Use to understand retention health relative to acquisition* ``` Compare new vs returning visitors: - Conversion rate and revenue per visitor for each - How has the mix shifted over the past 30 days? - Are returning visitor sessions growing or declining? ``` **What you'll get:** Segment-level performance metrics, new/returning mix trends, and signals on whether retention is keeping pace with acquisition. *** **10. AOV and discount trend** *Use to catch margin compression early* ``` Is our average order value trending up or down over the past 8 weeks? How has units per order changed in the same period? Are we discounting more than we used to, and is it affecting revenue per unit? ``` **What you'll get:** AOV and units-per-order trend data, discount rate changes, and revenue-per-unit movement that can signal margin pressure before it shows up in reports. *** ## Best Practices ### Organization Context * Always specify the `organization` parameter when working with multiple organizations * Use `getOrganizationsList` first to see available organizations * Cache organization IDs in your workflow to avoid repeated lookups ### Security * Never share your access tokens * Tokens are scoped to all organizations you have access to * Revoke access immediately if compromised