Custom Reporting Tools

How can you create a custom report showing users' device types and their conversion rates? (Custom reports can transform how you understand your audience’s behavior.) Here’s your simple step-by-step guide: Step 1: Access Google Analytics ◾ Log in to your Google Analytics account. ◾ Navigate to the property and view where you’ll create the report. Step 2: Go to Customization ◾ In the left sidebar, click Customization. ◾ Select Custom Reports. Step 3: Create a New Custom Report ◾ Click the + New Custom Report button. Step 4: Set Up the Report ◾ Report Name: Name it something descriptive like "Device Types and Conversion Rates." ◾ Tabs: Start with one tab for simplicity. Metric Groups: ◾ Add metrics like: ◽ Goal Completions. ◽ Conversion Rate (specific goal conversion rates if you have multiple goals). Dimension Drilldowns: ◽ Add Device Category to break down data by desktop, mobile, and tablet. Step 5: Add Filters (Optional) ◾ To refine the report, use filters (e.g., by specific goals, campaigns, or user segments). Step 6: Save Your Report ◾ Click Save to finalize. Step 7: Analyze the Data ◾ Go to the Custom Reports section and open your new report. ◾ Compare conversion rates across device types to spot trends. Step 8: Export and Share (Optional) ◾ Use the export options (PDF, CSV, etc.) to share your findings. Pro Tip: If mobile conversion rates lag behind desktop, it’s a signal to optimize your mobile user experience. Use these insights to shape responsive design strategies and target marketing efforts for each device type. With this simple process, you’ll unlock actionable insights and drive better results for your website. What’s your favorite custom report to build? Share below! P.S. Save this guide for your next reporting session. 

📊 Enhancing Power BI Reports with Custom Visuals 🚀 Unlock the full potential of your Power BI reports by incorporating custom visuals! Here are key considerations for a successful integration: Data Compatibility: Ensure your chosen custom visual aligns with your data source, handling data types effectively. Reliability and Support: Opt for well-maintained visuals with active support to avoid issues down the line. Performance: Test the visual's performance with your data to prevent slowdowns in report rendering. Accessibility: Prioritize visuals that adhere to accessibility standards for an inclusive user experience. Data Security: Confirm compliance with your organization's data security policies to safeguard sensitive information. License and Cost: Be mindful of any licensing costs associated with custom visuals, as they can add up. User Training: Provide training or documentation for users to navigate custom visuals effectively. Customization Options: Ensure visuals can be tailored to match your report's branding and requirements. Integration: Verify seamless integration with Power BI features like filters and cross-filtering. Compatibility with Updates: Keep visuals up to date with Power BI's latest versions for smooth operation. Community and Documentation: Leverage user communities and documentation for troubleshooting and best practices. Vendor Reputation: Trust reputable vendors for reliable and well-maintained custom visuals. Scalability: Confirm that visuals scale efficiently as your reports and datasets grow. Legal Compliance: Ensure compliance with legal regulations and licensing agreements. User Feedback: Continuously gather user feedback to refine and optimize custom visuals. #PowerBI

I recently shared some insight on when to buy vs when to build a reporting tool. But that’s only one half of the equation — you also need to understand the process that goes into turning your decision into action. So let’s weigh the practical steps you must take to build vs buy: 🧱 3 Steps to Building a Customer Reporting Tool Constructing a reporting solution from ideation to execution is a daunting task. Let’s cover what goes into it: 1. Extract, transform, and load — aka, ETL You’ll need to extrapolate data from all of your sources and convert it into an analysis-friendly format. From there, you need to upload it into a data warehouse (more specifically, a large central repository). This will take about a week and you’ll need to onboard a data integration engine and a warehousing solution. 2. Select your data visualization software Now, you must find the right software to turn your data into engaging visuals. Your options will range from simple drag-and-drop software to more coding-heavy tools. 3. Hire data scientists/engineers for maintenance and execution Someone needs to be focused on product upkeep. A small team of engineers will execute reporting code and address maintenance issues. Expect this to cost you about 12-20 labor hours a week. 💵 3 Steps to Buying a Reporting Tool Unlike building, buying only requires your brand to be involved in discovery and onboarding. 1. Discovering solutions Use platforms like G2 or Capterra to identify the right reporting solutions that align with your business’ reporting goals. 2. proof of concept This is the opportunity for the vendor to learn about your business, challenges, and ideal reporting solutions. They should also share a short proof of concept to give you a sample of what may be to come in a working relationship. 3. Launch your solution Once both sides sign the dotted line, you’re up and running with a new reporting solution from the jump. Building a reporting solution takes time, energy, and resources — that which could be saved and optimized by just buying a solution in the first place. Take these steps into account before you make your decision for your business. And if you want Tydo to show you what a reporting solution could look like at the highest level, reach out today, and we’ll get that intro call on the books!

My last 2 days of posting have lead up to this post: 𝗛𝗼𝘄 𝘁𝗼 𝗾𝘂𝗶𝗰𝗸𝗹𝘆 & 𝗲𝗮𝘀𝗶𝗹𝘆 𝗶𝗻𝗰𝗿𝗲𝗮𝘀𝗲 𝗰𝗹𝗶𝗲𝗻𝘁 𝗿𝗲𝘁𝗲𝗻𝘁𝗶𝗼𝗻. The answer: client-tailored reporting dashboards. If a client ever emails you and says "How is this product doing since we last talked?" -- 𝘁𝗵𝗲𝗻 𝘆𝗼𝘂'𝘃𝗲 𝗮𝗹𝗿𝗲𝗮𝗱𝘆 𝗳𝗮𝗶𝗹𝗲𝗱. The client should have a reporting dashboard that answers that question before they ask. The biggest mistake agencies make is "generalized" reporting that is the same for all their clients. What's worse? The managers report read out the metrics without interpreting & explaining the performance (e.g., "The CVR decreased by 5%") What?? How does that help the client at all. The client needs agencies to give them intelligence that leads to an action plan. Here's a simple format to help you with that: 🔸 What happened? 🔸 Why did it happen? 🔸 What happens next? Here's a better example of good reporting: 🔹 CVR decreased by 5% 🔹 This was due to increasing bids on higher-funnel keywords, which have far more volume and substantially increased our traffic 🔹 We have to do some optimizations around these keywords to continue growing visibility without spiking ACOS -- so we're going to optimize bids, placement settings, and adding additional negative keywords. That's much better communication. And then the "hack" to client-tailored dashboards is simply giving a custom report that answers all of the client's burning questions before they ask them. From my experience, clients often want to know how each product category is doing. For example, they might have their "flagship" products, their "B-Tier" middle-of-the-range products, and then their "new launch" products. You need a dashboard that breaks all 3 product categories out so clients can quickly & easily see all of the spend, keywords / search terms, CVR and ACOS broken out. This should also be a "live" dashboard that clients can check back on throughout the week so that they never have to ask "how is performance?" That's why AdLabs is soon releasing fully customizable reporting dashboards: 🔹 Tag, group, and organize any data point imaginable (campaigns, search terms, etc.) 🔹 Visualize the data with pie charts, bar charts, etc. 🔹 Compare & contrast performance trends across several groups/categories 🔹 Quickly see top performers / bottom performers from any data set If you can build a dashboard that the client 𝙙𝙚𝙥𝙚𝙣𝙙𝙨 𝙤𝙣 to make business-critical decisions, and further help them interpret that data -- then there's not a chance in the world they would leave you. Sound interesting? Check out AdLabs so you can set up your own custom dashboards and see how client retention goes through the roof 🚀

The biggest bottleneck in building a great AI product is iteration speed. And the biggest drag on iteration speed? Generic, off-the-shelf annotation tools. Many teams default to these tools because it seems like the path of least resistance. Counterintuitively, It's often path of most friction. Every second a reviewer spends fighting a clunky UI, switching contexts to find necessary data, or trying to interpret a generic data dump grinds progress to a halt. This is why we often advise teams to build their own custom annotation tools. It's the single most impactful investment you can make in your AI evaluation workflow. I've seen teams that do this iterate up to 10x faster. Why? Two main reasons: 1. Frictionless Review = Exponential Gains: A custom tool is designed for your specific workflow. You can add keyboard shortcuts for common actions, custom filters for your metadata, and bring all the context a reviewer needs from multiple systems into one screen. A tiny reduction in friction for a single review, multiplied by hundreds or thousands of reviews, translates into a massive increase in the volume and quality of feedback you can process. 2. Domain-Specific Rendering: A custom interface lets you render data in a way that's intuitive for the domain. Evaluating AI-generated emails? Render them to look like emails. Reviewing code output? Use syntax highlighting. Assessing a RAG system for medical content? Display the retrieved sources alongside the generated summary in a clear, readable format. When you present data in a product-specific way, your reviewers can give you higher-quality feedback, faster. Below is a screenshot of a custom annotation app one of our students, Christopher Lovejoy, MD built for a medical use case. This is just one of the high-leverage strategies we teach in our AI Evals for Engineers & PMs course. For those interested in the full evaluation toolkit - from error analysis to production monitoring. Get 35% off with code evals-info-url. Next cohort kicks off Oct 6: https://bit.ly/4nahFmu