clickforce is a leading company in digital advertising services in Taiwan, specializing in data-driven advertising and conversion (D4A – advertising and data to action). With a mission to provide industry-leading, trend-aligned and innovative marketing solutions, CLICKFORCE helps brands, agencies and media partners make better advertising decisions.
However, as the advertising industry continues to rapidly evolve, traditional analytics methods and typical AI outputs are no longer sufficient to provide actionable insights. To remain competitive, CLICKFORCE turned to AWS to build Lumos, a next-generation AI-powered marketing analytics solution powered by Amazon Bedrock, Amazon SageMaker AI, Amazon OpenSearch, and AWS Glue.
In this post, we demonstrate how CLICKFORCE used AWS services to build Lumos and transform advertising industry analysis from weeks of manual work to an automated, one-hour process.
digital advertising challenges
Before adopting Amazon Bedrock, CLICKFORCE faced several obstacles in building actionable intelligence for digital advertising. Large language models (LLMs) generate general recommendations rather than actionable industry-specific intelligence. Without an understanding of the advertising environment, these models did not have the industry context needed to align their recommendations with actual industry realities.
Another significant challenge was the absence of integrated internal datasets, which weakened the credibility of the outputs and increased the risk of hallucinations or false insights. At the same time, marketing teams relied on disconnected tools and technology, like vibe coding, without standardized architecture or workflows, making processes difficult to maintain and scale.
Preparing a comprehensive industry analysis report was also a time-consuming process, typically requiring two to six weeks. The timeline resulted from several labor-intensive phases: one to three days to define objectives and determine the research plan, one to four weeks to gather and validate data from various sources, one to two weeks to conduct statistical analyzes and create charts, one to two to extract strategic insights, and finally three to seven days to draft and finalize the report. Each phase often requires back-and-forth coordination between teams, causing timelines to move forward. As a result, marketing strategies were often delayed and based more on intuition than timely, data-backed insights.
solution overview
To address these challenges, CLICKFORCE was created lumosAn integrated AI-powered industry analytics service using AWS services.
The solution is designed around Amazon Bedrock agents for contextual reasoning and Amazon SageMaker AI to fine-tune text-to-SQL accuracy. CLICKFORCE chose Amazon Bedrock because it provides managed access to the Foundation model without the need to build or maintain infrastructure, while also offering agents that can orchestrate multi-step tasks and integrate with enterprise data sources through the knowledge base. This allowed the team to gain insight into real, verifiable data, reduce hallucinations, and quickly experiment with different models, while also reducing operational overhead and accelerating time-to-market.
The first step was to build an integrated AI agent using Amazon Bedrock. End-users interact with a chatbot interface that runs on Amazon ECS, developed Streamlight And is fronted by an application load balancer. When a user submits a query, it is routed to an AWS Lambda function that invokes the Amazon Bedrock Agent. The agent pulls relevant information from the Amazon Bedrock Knowledge Base, which is built from source documents – such as campaign reports, product descriptions, and industry analysis files – hosted in Amazon S3. These documents are automatically converted into vector embeddings and indexed in the Amazon OpenSearch service. By grounding model responses in this curated document set, CLICKFORCE ensured that the output was made relevant, reduced hallucinations, and aligned with real-world advertising data.
Subsequently, CLICKFORCE made the workflow more action-oriented by using text-to-SQL requests. When queries require data retrieval, the Bedrock Agent generates a JSON schema through the Agent Action API Schema. These were passed to Lambda executor functions, which translated the requests into text-to-SQL queries. By continuously updating the SQL database from CSV files in Amazon S3 through the AWS Glue crawler, analysts were able to run precise queries on campaign performance, audience behavior, and competitive benchmarks.
Ultimately, the company improved accuracy by incorporating Amazon SageMaker mlflow In the development workflow. Initially, CLICKFORCE relied on Foundation models for text-to-SQL translation, but found them to be inflexible and often inaccurate. Using SageMaker, the team processed the data, evaluated different approaches, and tuned the overall text-to-SQL pipeline. Once validated, the optimized pipeline was deployed via AWS Lambda functions and integrated back into the agent, ensuring that improvements flowed directly into the Lumos application. With MLflow providing experiment tracking and evaluation, the cycle of data processing, pipeline tuning, and deployment was streamlined, allowing Lumos to achieve higher precision in query generation and deliver automated, data-driven marketing reports.
Result
The impact of adopting Amazon Bedrock Agents and SageMaker AI has been transformational for CLICKFORCE. Industry analysis that previously required two to six weeks can now be completed in less than an hour, dramatically speeding up the decision-making process. The company also reduced its reliance on third-party industry research reports, resulting in a 47 percent reduction in operating costs.
In addition to time and cost savings, the Lumos system has increased scalability across all roles within the marketing environment. Brand owners, agencies, analysts, marketers and media partners can now generate insights independently without waiting for centralized analyst teams. This autonomy has brought greater agility to all operations. Furthermore, by grounding the output in both internal datasets and industry-specific context, Lumos significantly reduced the risk of hallucinations and ensured that insights more closely aligned with industry realities.
Users can generate industry analysis reports through natural language conversations and iteratively refine the content as the conversation continues.
These visual reports, generated through the Lumos system powered by Amazon Bedrock Agents and SageMaker AI, demonstrate the platform’s ability to generate comprehensive market intelligence within minutes. Charts depict brand sales distribution, retail and e-commerce performance, and demonstrate how AI-powered analytics automates data aggregation, visualization and insight generation with high precision and efficiency.
conclusion
CLICKFORCE’s Lumos System represents a breakthrough in the way digital marketing decisions are made. By combining Amazon Bedrock Agents, Amazon SageMaker AI, Amazon OpenSearch Service, and AWS Glue, CLICKFORCE transformed their industry analytics workflow from a slow, manual process to a fast, automated, and reliable system. In this post, we showed how CLICKFORCE used these AWS services to create Lumos and transform advertising industry analysis from weeks of manual work to an automated, one-hour process.
About the authors
ray wang Is a Senior Solutions Architect at AWS. With 12+ years of experience in backend and consulting, Ray is dedicated to building modern solutions in the cloud, especially in NoSQL, big data, machine learning, and generative AI. As a hungry player, he passed all 12 AWS certifications to increase the breadth and depth of his technical knowledge. He likes to read and watch sci-fi movies in his spare time.
Shanna Chang Solution Architect at AWS. She focuses on observability in modern architectures and cloud-native monitoring solutions. Before joining AWS, she was a software engineer.
