Introduction

In today’s digital landscape, generative artificial intelligence (AI) has become a vital tool for marketers to create personalized content and optimize ad targeting with predictive analytics. With the ability to analyze vast amounts of data, AI can predict trends and public sentiment, leading to more effective marketing strategies and increased business results.

Vidmob’s AI Journey

Vidmob, a creative data company, has partnered with the AWS Generative AI Innovation Center (GenAIIC) to unlock the power of generative AI and drive business results through creative data analysis. By leveraging Amazon Bedrock and Anthropic’s Claude model, Vidmob aims to empower customers to directly query and analyze their creative performance data through a chat interface.

Use Case Overview

Vidmob aims to revolutionize its analytics landscape with generative AI. The central goal is to empower customers to directly query and analyze their creative performance data through a chat interface. Over the past 8 years, Vidmob has amassed a wealth of data that provides deep insights into the value of creatives in ad campaigns and strategies for enhancing performance.

Solution Overview

The AWS team worked with Vidmob to build a serverless architecture for handling incoming questions from customers. They used the following services in the solution:

• Amazon Bedrock
• DynamoDB
• Lambda functions
• Streamlit application

Workflow Details

The workflow consists of the following steps:

1. User navigates to Vidmob and asks a creative-related query
2. DynamoDB stores the query and session ID, which is then passed to a Lambda function as a DynamoDB event notification
3. The Lambda function calls Amazon Bedrock, obtains an output from the user query, and sends it back to the Streamlit application for the user to view
4. The Lambda function updates the status after it receives the completed output from Amazon Bedrock

Dataset

The dataset includes a set of ad-related data corresponding to a specific client. Specifically, Vidmob analyzes the client ad campaigns and extracts information related to the ads using various machine learning (ML) models and AWS services.

Results

The results of this engagement demonstrate the power of generative AI in unlocking valuable insights for customers in reduced time. The LLM-generated outputs had high accuracy, relevancy, and clarity, with the ability to answer user queries and provide insights on client information.

Conclusion

In this post, we shared how the AWS GenAIIC team used Anthropic’s Claude on Amazon Bedrock to extract and summarize insights from Vidmob’s performance data using zero-shot prompt engineering. The success of this engagement allows Vidmob to create more valuable insights for customers in reduced time, enabling a more scalable solution.

Frequently Asked Questions

Q1: What is the main objective of Vidmob’s AI journey?

The main objective of Vidmob’s AI journey is to build a differentiated dataset to maximize the potential of its AI-driven solutions and stay at the forefront of the creative data landscape.

Q2: How does Vidmob’s use case leverage generative AI?

Vidmob’s use case leverages generative AI to empower customers to directly query and analyze their creative performance data through a chat interface, allowing for faster and more accurate insights.

Q3: What are the key services used in Vidmob’s solution?

The key services used in Vidmob’s solution include Amazon Bedrock, DynamoDB, Lambda functions, and Streamlit application.

Q4: What is the main challenge in achieving insights with large language models?

One of the main challenges in achieving insights with large language models is limited volume of data they can analyze to generate insights without hallucination.

Q5: How does Vidmob expect the use of generative AI to impact its business results?

Vidmob expects the use of generative AI to reduce the time it takes to generate insights for creative campaigns from hours to minutes, enabling a more scalable solution.