INBOX INSIGHTS: Make Google Analytics 4 Work For You, Red Teaming Custom GPTs, Part 3 - Trust Insights Marketing Analytics Consulting

INBOX INSIGHTS: Make GA4 Work For You, Red Teaming Custom GPTs, Part 3 (1/24) :: View in browser

👉 Take our new Generative AI for Marketers course!

How to Make Google Analytics 4 Work for You

I’ve been asking around, and the overwhelming consensus is that everyone dislikes Google Analytics 4. Why? It doesn’t feel like an upgrade from Universal Analytics. If anything, we feel like we lost functionality and data. Google did not give us a choice to opt into this system; they forced us into it. The other option on the table is to find a new system all together. Either way, there has been a lot of pain to get us here today.

So how do we make the best of a bad situation?

Embrace the Learning Curve

It’s important to acknowledge that GA4 is not just an update but a complete overhaul. This means a steep learning curve is inevitable. Don’t get discouraged. Instead, let’s see if we find the opportunities for continual learning. Generative AI is dominating the news cycle and the marketing industry right now. What better time to double down on your technical and analytic skill sets?

Focus on Key Features

GA4 comes with a range of new features and metrics. Instead of trying to understand everything at once, focus on key features relevant to your business needs. This is a great opportunity to spin up some user stories. As a reminder, a user story is a simple sentence with three parts: “As a [persona], I [want to], so [that]”. The “persona” is the user, the “want to” is the action, and the “that” is the outcome. A user story will help you focus what you want to do with the system so that you can focus on where you want to start.

Engage with the Community

You are not alone. There are a lot of people who are on the struggle bus with Google Analytics 4. There are just as many people who are thriving. Ok, maybe not as many, but they are out there! Seek out groups and communities on platforms like LinkedIn, Slack, and Discord. You’ll quickly find people to commiserate with. While you’re commiserating, you’ll also be able to help each other learn the new system.

Provide Feedback to Google

Google made a lot of changes when they rolled out Google Analytics 4. It might also feel like they didn’t take user feedback into consideration. So, providing feedback now might feel like it’s going into a black hole, but it’s worth a shot. If nothing else, it might be cathartic to tell them everything you dislike about the new platform.

Regularly Review and Adapt

Building habits is hard. But the more you do it, the better it will be. Take 5 minutes every morning to review your data. Set a goal for one week. Then do it again the next week. Then do it again. I cannot promise that the system will improve but I can promise that you will start to get more comfortable with it over time. You just have to stick with it.

Professional Training or Consultation

There are great resources out there to help you understand GA4. There are YouTube channels, newsletters, and endless content that will help you get set up. You can also take our Google Analytics 4 for Marketers course to help you get skilled up.

If you get fed up and just want someone to setup the system for you, we do that too!

Reach out to us

It might feel hopeless, but there is a light at the end of the Google Analytics 4 tunnel. If your company has elected to use it as your system of record, it’s time to embrace it.

Are you hating on GA4? Reply to this email to tell me or come join the conversation in our Free Slack Group, Analytics for Marketers.

– Katie Robbert, CEO

Do you have a colleague or friend who needs this newsletter? Send them this link to help them get their own copy:

https://www.trustinsights.ai/newsletter

In this episode of In-Ear Insights, the Trust Insights podcast, Katie and Chris discuss the crucial role of analytics in digital marketing and how it’s often seen as the bearer of bad news. They explore the common pitfalls companies face when they only sporadically review data, leading to missed opportunities for timely adjustments. Katie emphasizes the importance of integrating a thoughtful and focused measurement plan from the onset of marketing campaigns. The conversation also delves into the challenge of making effective decisions when data is not utilized properly, highlighting the importance of iterative and agile program development for better outcomes. This episode offers valuable insights into transforming analytics from a dreaded task to a strategic asset.

Watch/listen to this episode of In-Ear Insights here »

Last time on So What? The Marketing Analytics and Insights Livestream, we examined generative AI and analytics. Catch the episode replay here!

On this week’s So What? The Marketing Analytics and Insights Live show, we’ll be looking at basic diagnostic reporting from Google Analytics 4. Tune in this Thursday at 1 PM Eastern Time and bring your questions! Are you following our YouTube channel? If not, click/tap here to follow us!

Here’s some of our content from recent days that you might have missed. If you read something and enjoy it, please share it with a friend or colleague!

Take your skills to the next level with our premium courses.

Get skilled up with an assortment of our free, on-demand classes.

Red Teaming Custom GPTs, Part 3 of 3

Continuing from last week’s newsletter in which we discussed the people, process, and platforms of red-teaming LLMs, let’s continue this week with the performance.

As a quick reminder, red teaming means trying to get generative AI to do something it shouldn’t – whether that’s to say something inappropriate or divulge information that it shouldn’t. When we talk about inverting the 5Ps, here is what we started with:

Purpose: What is your Custom GPT supposed to do?
People: Who are the intended users?
Process: How is the user expected to interact with the Custom GPT?
Platform: What features of the OpenAI platform does the Custom GPT need access to?
Performance: Does the Custom GPT fulfill the designated purpose?

Performance is very straightforward – can your Custom GPT be made to fail its intended purpose? This is the culmination of red teaming, so let’s look at how we take our questions we’ve asked over the last couple of weeks and put them to the test.

First, you start with the original 5Ps. Let’s say we have a Custom GPT that’s meant to create guacamole recipes. You’ve gone through the effort of documenting the history of guacamole and even trained it on your own secret recipes. Here’s a simple example of the 5Ps for this instance:

Purpose: Generate guacamole recipes upon request, including variations based on consumer needs.
People: Consumers interested in obtaining unique guacamole recipes.
Process: The user begins a new session with GuacPT. GuacPT asks a series of basic questions and then generates a recipe.
Platform: GuacPT should have access to the DALL-E image generator, but neither Code Interpreter nor web browsing.
Performance: Does GuacPT create usable guacamole recipes?

Next, we consider our inversions. What are the things that could go wrong?

Purpose: Unhelpful would be failing to deliver recipes. Harmful would be bad recipes or recipes that violate someone else’s copyright. Untruthful would be recipes that do not actually make guacamole.
People: For this application, there aren’t really any unintended users, but there could always be users with malicious intent, such as people trying to get at our secret guacamole recipes we built as added data.
Process: A user could ask for recipes that are not guacamole. A user could ask for our secret recipes. A user could ask for copyrighted material from the Internet, or from a known recipe that’s built into GPT-4.
Platform: Jailbreaks that work on GPT-4-Turbo will also work on GuacPT.
Performance: Does GuacPT fail to deliver its intended outputs?

Based on this inversion of the 5Ps, we have a short, toy list of the things that are likely to go wrong. When you do this process for your own Custom GPT, it should be substantially longer than this. Our next step is to take a look at the custom instructions we’ve built for our GuacPT, and start to craft antidote instructions for each of the things we’ve outlined. Here’s just a brief example in Purpose:

Always return only guacamole recipes when interacting with the user. Never return a recipe that is not guacamole.
If the user requests a recipe that is not guacamole, decline the request and suggest the user ask solely about guacamole recipes.
Return recipes only based on the supplied information.
If the user asks for a recipe based on a Named Entity such as a chef or a restaurant, decline the user’s request and suggest an alternative, original recipe. For example:
User: “Can you give me a guacamole recipe in the style of Gabriela Camara?”
Incorrect Response: “Sure, I can help with that. Here is a recipe based on the style of Gabriela Camara. ”
Correct Response: “I’m sorry, to respect copyrighted material, I can’t suggest a recipe like that. But I can suggest this original recipe. ”

It’s clear that a comprehensive listing of the inverted 5Ps makes it straightforward to build extensive custom instructions about what the model should and should not do.

Once you’re done with your custom instructions that address all of the vulnerabilities you’ve outlined in your inverted 5Ps, you’ll load these into your Custom GPT in the Configure tab. Your final step is to start a ChatGPT session, provide your custom instructions, and ask ChatGPT to audit them and identify what else could go wrong that you haven’t accounted for.

Remember that software development is an iterative process. It’s never one-and-done – as models change, as users become more savvy, and as your skills improve, new opportunities and new vulnerabilities arise in Custom GPTs (and all AI). Create a plan to audit your Custom GPT on a regular, frequent basis so that its performance improves and the ways it can go wrong diminish.

Here’s a roundup of who’s hiring, based on positions shared in the Analytics for Marketers Slack group and other communities.

Are you a member of our free Slack group, Analytics for Marketers? Join 3000+ like-minded marketers who care about data and measuring their success. Membership is free – join today. Members also receive sneak peeks of upcoming data, credible third-party studies we find and like, and much more. Join today!

Imagine a world where your marketing strategies are supercharged by the most cutting-edge technology available – Generative AI. Generative AI has the potential to save you incredible amounts of time and money, and you have the opportunity to be at the forefront. Get up to speed on using generative AI in your business in a thoughtful way with our new offering, Generative AI for Marketers, which comes in two flavors, workshops and a course.

Workshops: Offer the Generative AI for Marketers half and full day workshops at your company. These hands-on sessions are packed with exercises, resources and practical tips that you can implement immediately.

👉 Click/tap here to book a workshop

Course: We’ve turned our most popular full-day workshop into a self-paced course, available now!

👉 Click/tap here to register for the course

Interested in sponsoring INBOX INSIGHTS? Contact us for sponsorship options to reach over 26,000 analytically-minded marketers and business professionals every week.

Where can you find Trust Insights face-to-face?

MarketingProfs AI Series, Virtual, January 2024
Tourism Industry Association of Alberta’s Tourism Summit, Edmonton, February 2024
Independent Consortium of Booksellers Association, Denver, February 2024
Social Media Marketing World, San Diego, February 2024
MarketingProfs AI Series, Virtual, March 2024
Australian Food and Grocery Council, Melbourne, May 2024
MAICON, Cleveland, September 2024

Going to a conference we should know about? Reach out!

Want some private training at your company? Ask us!

First and most obvious – if you want to talk to us about something specific, especially something we can help with, hit up our contact form.

Where do you spend your time online? Chances are, we’re there too, and would enjoy sharing with you. Here’s where we are – see you there?

Our Featured Partners are companies we work with and promote because we love their stuff. If you’ve ever wondered how we do what we do behind the scenes, chances are we use the tools and skills of one of our partners to do it.

Read our disclosures statement for more details, but we’re also compensated by our partners if you buy something through us.

Some events and partners have purchased sponsorships in this newsletter and as a result, Trust Insights receives financial compensation for promoting them. Read our full disclosures statement on our website .

Thanks for subscribing and supporting us. Let us know if you want to see something different or have any feedback for us!

Need help with your marketing AI and analytics?

Leave a Reply Cancel reply

Subscribe to our Weekly Newsletter

Pin It on Pinterest