Recent Discussions
SnapGPT Beginner's Guide
What is SnapGPT? SnapGPT is a generative AI solution in early release and currently available only to users who have been invited to SnapLabs. Built right into the SnapLogic web interface (screenshot below), you can now prompt SnapGPT for a wide variety of help creating Pipelines, configuring Snaps, for suggestions about which Snap to use, and so much more. How can I get started with SnapGPT? In this section we cover a few examples that should be repeatable as a way to send your first few prompts to SnapGPT and observe the outcome. After that you can explore our SnapGPT Prompt Catalog, which contains even more prompts to copy/paste into SnapGPT as you explore. One caveat here is that as a generative AI solution that is always learning, it is possible that outcomes will change over time. When SnapGPT creates a Pipeline for you it will be a bit like importing a Pipeline in the sense that it will have a wizard to help select accounts and finalize the Pipeline. Log in at https://snapgpt.labs.snaplogic.com If SnapGPT is not shown by default, press the SnapGPT button in the upper-right corner of the SnapLogic web interface to make it visible; to make it always visible, click your name in the upper-right corner > User Settings > Opt-in Features > Check the box for “Open SnapGPT by Default”: A new box will appear on the right-hand side of the SnapLogic web interface for you to start typing to SnapGPT: Examples: See SnapGPT in Action Now let’s talk about getting your feet wet, hands dirty, or whatever saying floats your boat. Below are several examples you can use to start exploring SnapGPT and they should be precise enough to yield consistent results. Example 1: Create a pipeline that pulls Salesforce Opportunities Our first example is one that will generate a short but complete Pipeline for us. With any generative AI, SnapGPT included, it is important to remember that the more specific you are with the prompt the more accurate a response you will receive, or in this example, the more accurate a Pipeline we will receive. Prompt: “Create a Pipeline using Salesforce Read to fetch my Opportunities, Filter out any opportunities outside of the last fiscal quarter, then write them to Snowflake.” Here is a screenshot of the short Pipeline created by SnapGPT that closely resembles the prompt we provided: Inside the Filter Snap we can see that SnapGPT created an expression for us to filter the $CloseDate file for us: Example 2: Ask help for identifying which Snap to use At some point we were all new to using SnapLogic and we learned it from CSM-led training, trial-and-error, reviewing existing pipelines, etc. What we did not have was an always-on AI assistant ready to answer our questions (we still love you Iris and wouldn’t be here without you!). This example helps show us how SnapGPT can be prompted with natural language to let us know exactly what Snap we need. Prompts: “What snap can I use to remove records from my pipeline based on a given condition?” “Which snap acts like a case statement or switch to allow me to move records down different pathways based on a condition?” Example 3: Ask for help to learn when to use one Snap over a different Snap Another example of using SnapGPT more for educational purposes or documentation skimming would be to ask it when you might want to use one Snap instead of another. Prompt: “When would I need to use the Salesforce SOQL snap instead of the Salesforce Read snap?” Example 4: Generate sample data We can also use SnapGPT to generate sample data, for those times when we need to get started on a business process and show some results but maybe we don’t yet have access to the source system. Prompt: “Create a single-snap pipeline with a JSON Generator that has 10 example Salesforce Lead records” Example 5: Fetch exchange data from third-party API It is also possible to use SnapGPT to pull data from a third-party site such as exchange data. Prompt: “Fetch exchange rate data from the European Central Bank and save it to a JSON file” What should I be aware of when using SnapGPT? As with any early access release of software, especially generative AI that is always learning, there are some key points to keep in mind as you explore SnapGPT and share feedback with the SnapLogic team (including any previously mentioned and/or typical disclaimers about using ChatGPT or SnapGPT): SnapGPT may generate Pipelines with unnecessary Snaps (like kids overpacking to visit grandma’s house!) SnapGPT depends on ChatGPT availability, so there are times when you might see a response like this: What if I have questions? Our goal is to provide several ways to interact with our team, which we’ve broken out below. Community: Using the SnapLogic Community’s locked SnapLabs Category, which is the same category you should be reading this content from (please do not post on the public forums yet since this is a limited release at this time). Office hours: Roger Sramkoski, one of our Sr. Technical Marketing Managers, will be setting up office hours once or twice a week. These will be purely optional and will be minimal agendas so we can focus on open conversations. Email: You can also contact Roger Sramkoski directly at rsramkoski@snaplogic.comGartner - 10 Best Practices for Scaling Generative AI
I recently came back from Gartner's Data and Analytics Summit in Orlando, Floria. As expected, GenAI was a big area of focus and interest. One of the sessions that I attended was "10 best practices for scaling Generative AI." The session highlighted the rapid adoption of generative AI, with 45% of organizations piloting and 10% already in production as of September 2023. While the benefits like workforce productivity, multi-domain applications, and competitive differentiation are evident, there are also significant risks around data loss, hallucinations, black box nature, copyright issues, and potential misuse. Through 2025, Gartner predicts at least 30% of generative AI projects will be abandoned after proof-of-concept due to issues like poor data quality, inadequate risk controls, escalating costs, or unclear business value. To successfully scale generative AI, the session outlined 10 best practices: Continuously prioritize use cases aligned to the organization's AI ambition and measure business value. Create a decision framework for build vs. buy, evaluating model training, security, integration, and pricing. Pilot use cases with an eye towards future scalability needs around data, privacy, security etc. Design a composable platform architecture to improve flexibility and avoid vendor lock-in. Put responsible AI principles at the forefront across fairness, ethics, privacy, compliance etc. Evaluate risk mitigation tools. Invest in data and AI literacy programs across functions and leadership. Instill robust data engineering practices like knowledge graphs and vector embeddings. Enable seamless human-AI collaboration with human-in-the-loop and communities of practice. Apply FinOps practices to monitor, audit and optimize generative AI costs. Adopt an agile, product-centric approach with continuous updates based on user feedback. The session stressed balancing individual and organizational needs while making responsible AI the cornerstone for scaling generative AI capabilities. Hope you found these useful. What are you thoughts on best practices for scaling GenAI?
How to read file as input using SnapGPT from mention path in prompt.
Hi , I am using SnapGPT to read the file uploaded in the path "Project /snaplogictrial/projects/My Folder/xyz.csv" in the Sandbox environment. However, SnapGPT is unable to read the file from the mentioned path. Is this functionality already available or is there any other way that I can read the file via SnapGPT prompt ? Below is the prompt I am using. Generate a pipeline to fetch "Global-Superstore.csv" file from path" Project /snaplogictrial/projects/My Folder", then filter it by removing all records except "India" as Country column, then load in the file writer. Thanks. NihitSnapGPT Prompt Catalog
Introduction While exploring SnapGPT our customers and internal teams are constantly discovering noteworthy prompts, so we are going to start collecting and sharing these here. Unlike the Beginner’s Guide which includes the prompt and result, we will just focus on the prompt itself in this post and let the results be part of your own exploration! What if I have a prompt to share? We would love to hear from you, so please share it with us by replying to this post or creating your own post in the SnapLabs community category! Ask for help Let’s start simple by sharing a few prompts to demonstrate how SnapGPT can help. How do I build a pipeline? When and how should I use the Salesforce SOQL snap? How can one pipeline call another pipeline? Can pipelines use recursion? How is an Ultra pipeline different from a regular pipeline? Create a pipeline Extract opportunity object records from Salesforce and add them to Snowflake Create a Pipeline using Salesforce Read to fetch my Opportunities, Filter out any opportunities outside of the last fiscal quarter, then write them to Snowflake Extract opportunity object records from Salesforce closed before “2022-10-01” and add them to Snowflake Create a pipeline that fetches my SnapLogic Activity Logs from the SnapLogic API Generate Sample Data For those moments when you just need to see how Create a single-Snap pipeline with a JSON Generator that has 10 example Salesforce Lead records Create a pipeline with a JSON Generator that contains 10 sample records with First Name, Last Name, and Email Create a SOQL query For these examples you need an existing pipeline with a SOQL Snap in it, then you can ask SnapGPT one of these prompts. Select records from Salesforce opportunity object closedWon in Q1 2023 Improving SnapGPT prompts for more accurate results Here is a collection of ways to enhance prompts for clarity or to accomplish a certain goal. When asking SnapGPT to create a pipeline to sync accounts between two systems, say Salesforce and NetSuite, consider adding something like “…with Salesforce as the source of truth” or “Treat Salesforce as the source of truth.”
SnapGPT Example: CSV Filter and Write
I used the following to prompt to successfully generate a pipeline that reads data from a csv file, filtered the data and wrote the data to a new file. Read a csv file, then map Registered, Last Name, Email and % complete, then filter records where Registered is equal to or greater than 2023-05-15, and % complete is equal to or less than 40, then write records to csv file Resulting pipeline: I did need to modify the Mapper Snap and provide a file name but the filter expression was a success.Prompt Deep Dive: Exporting audit logs
Overview Many SnapLogic customers are required by various industry regulations to retain audit logs for long periods of time. If you are a SnapLogic org administrator, you have either already built a pipeline to export your SnapLogic Activity Logs or are looking to build one. In one of our recent Office Hours sessions, a customer asked if SnapGPT could help create a pipeline to address this so we are going to take a few minutes to go through this example in a way that would produce a valid pipeline. Walkthrough Here is our SnapGPT prompt (screenshot below): “Create a pipeline that fetches my SnapLogic Activity Log and writes it to S3” SnapGPT comes back with a pipeline preview, which looks like a good starting point: After pressing “Import on new tab” we’re able to start the pipeline import process which includes having a chance to rename the pipeline and choose where you want to save it. Now we’ll open the REST Get snap to add our authentication and verify the URL. NOTE: If your REST Get snap does not include the URL, you can ask SnapGPT for the URL or copy it from here: https://{pod_path}/api/1/rest/public/activities/{org} . The placeholder {pod_path} is the beginning of the URL in your address bar for SnapLogic, so snapgpt.labs.snaplogic.com for SnapGPT in SnapLabs, or elastic.snaplogic.com for other environments. You may need to use the Elastic pod and a different org than SnapLabs if you want to validate and/or run this pipeline. I have used ‘elastic.snaplogic.com’ as my pod_path and ‘ConnectFasterInc’ for my {org} as seen in the screenshot below. If you do intent to run this from SnapLabs you will also want to check the “Trust all certificates” box. I’ve also set a query parameter ‘limit’ to a value of ‘500’. SnapGPT may add some additional expressions in the Mapper, so what you see below is a minimal change we can make to load raw entries and drop header and status information from the audit log file. Wrap up Your final step here would be to configure the S3 File Writer, or if you need to send the audit log to a different location you could reconfigure the Mapper and send to wherever you need the files to go. Video coming soon! Sometimes a video is worth a bunch of words and screenshots, so once we finalize the video we’ll post it here!SnapLogic Data Science Resources
This category is for all things related to SnapLogic Data Science and it’s machine learning capabilities. If you are participating in the SnapLogic Free Trial, see the SnapLogic Trial category. Here are some resources to get you started: Machine Learning Showcase In the Machine Learning Showcase, you will find various machine learning applications that were developed and deployed entirely in SnapLogic Data Science, an extension of SnapLogic’s Intelligent Integration Platform. Customer Churn Prediction Natural Language Processing The Decision Tree Image Recognition (Inception-v3) (This site will request access to your computer’s camera.) Handwritten Digit Recognition Diabetes Progression Prediction Iris Flower Classification ML API Tester Loan Repayment Prediction Product Documentation Documentation of the Snap Pack can be found at SnapLogic Data Science (Machine Learning) SnapLogic Website Information about the Machine Learning Snap Packs can also be found on our website: ML Data Preparation Snap Pack ML Core Snap Pack ML Analytics Pipeline Patterns If you are in the SnapLogic Free Trial, you will find a set of Patterns under the Patterns tab in the SnapLogic Designer. Patterns are pre-built, reusable integration pipelines that can be configured through a step-by-step wizard. These patterns match the use cases described in the documentation and Machine Learning Showcase. Non-trial users can download the same pipelines from the documentation. Videos Data collection and preparation Model building and validation
