Overview
Moby is your AI-powered data analyst that understands your business and unlocks the flexibility to simply ask for the data you need and build workflows to accelerate your growth. Generate complex dashboards using plain English, easily build forecasts, and gain insights and personalized recommendations.
Moby understands your data and can convert natural language into SQL queries better than any other LLM in the world. And then, it can help you analyze that data to make better decisions.
Best Practices
Writing a quality prompt is key to getting the most value out of Moby. Here are some best practices for writing effective prompts:
Define your need: Start by clearly identifying the specific information or metrics you’re looking for, such as total sales, new customer counts, or channel-specific ad spend.
Specify your data source: Specify whether the data should come from your Shop data, a specific ad platform, first-party pixel data, an email/SMS provider, or elsewhere. Moby will interpret your prompt to choose the best data source, but it's best to be specific.
Specify the time frame: Clearly define the time-period for your query, such as "last 7 days," "yesterday," or "Q2 2023" to ensure the data is relevant and actionable.
State your output preference: Decide how you want the information presented —whether as a list, a summary, broken out by day or aggregate, in tables or charts, to suit your analysis needs.
Finally, combine the details you've outlined into a clear and straightforward prompt. For example, "Show me my total sales from my BigCommerce shop data for last month broken out by day."
Prompt Library
We have curated a collection of high-value prompts segmented to cater towards various use cases, from analyzing website metrics to enhancing channel performance and uncovering customer insights. Explore the Prompt Library directly within Moby.
Chat with Your Data
Once you ask a question, Moby will query the data warehouse and generate a plain-language response as well as a dynamic widget reflecting the data you were looking for. For more complex questions, Moby may run multiple queries before providing a final answer.
Ask Follow-Up Questions
You can ask Moby follow-up questions about the widget, or request to include additional metrics in a revised widget.
Edit the Data Visualization
Want to see the data reported in another way? Click on Moby's widget and select Edit Section to open Moby's powerful visualization editor. When you are satisfied, click Save.
Review Data Sources
Curious what went into Moby's answer? Click into the widget to review the data sources and other specifications relevant to the widget. Review the SQL Moby wrote to query the data warehouse, and explore related resources and Template Dashboards that may be helpful.
Review Moby's Reply
After receiving Moby's reply, review the response to ensure it meets your expectations. If necessary, refine your prompt to improve accuracy and relevance.
Add Data Filters
Depending on the type of data included in your query, you may be able to add filters to the widget. Click the ☰ button to review available data filters.
Saving Your Results
Once you are satisfied with the data, save the widget to one of your dashboards so you can easily access it later.
Tips for Success
Keep it simple: Focus on one query at a time to avoid overwhelming yourself and to ensure data accuracy.
Be patient: Crafting effective prompts is a skill that improves over time. Learn from each attempt to refine your approach.
Be conversational: Think of your interactions with Moby as a conversation. Instead of just telling Moby to do something for you, It’s important to start your chat by providing context.
Use examples: Refer to provided examples as a starting point and adjust them as needed to fit your specific requirements.
Key Phrases for Prompting Moby
Moby does its' best to delivering the data you are looking for. Using specific key phrases can help Moby more fully understand your request and deliver accurately. Here are some examples of key phrases you can use to prompt Moby more efficiently.
Key Phrase | Use Case | Example |
Give Me / Show Me | Request specific data, information, or examples. | "Give me my Meta ROAS and CPA by campaign for the last 30 days." |
Forecast | Predict future trends, sales, or any other metric. | "Forecast my total revenue for the next 6 Months. Use the last 30 months of data." |
Web Search | Access information that is not stored in local databases but can be found online. | "Search the web for the latest studies on consumer behavior in online shopping." |
Help Center | Get detailed explanations or help understanding how the Triple Whale product works. This code word will search Triple Whale’s Knowledge Base. | "Help center: explain how NC ROAS is calculated." |
Using Code | Perform calculations, generate graphs, or conduct analysis that requires a script in Python. | "Using code, what is 120% of my April 2023 revenue?" |
Revise / Modify Prompt | Request changes or corrections in the data, queries, or scripts provided.
| "Revise the SQL query to include data from the last 12 months instead of 6." |
Analyze / Analysis | Dive deeper into your data to gain plain-language insights. | "Analyze the above data and share key insights to guide my decision-making." |
Retrieve / Pull Data | Pull specific data from a database or a dataset. | "Retrieve all $100+ orders from yesterday." |
Compare / Comparison | Compare data sets, metrics, or performance across different parameters. | "Compare the performance of our two best-selling products over the past year." |