## Transforming Customer Experience with AI

Our Executive Function series features perspectives from leaders driving transformation through AI.

**[CRED](https://cred.club/)** is an India-based members-only club that rewards creditworthy individuals for their timely credit card bill payments by providing them with exclusive offers and access to premium experiences. Since 2018, CRED has built its brand on delivering **seamless, secure, and beautifully designed digital products** for India's most affluent consumers. Today, over **15 million members** use CRED each month. As the company scales, maintaining this level of quality has required new approaches to product development, service, and internal collaboration.

We sat down with Swamy Seetharaman of CRED to understand how the company is working with **OpenAI** to create premium, concierge-like experiences at scale.

## Building for Excellence from Day One

"When we started, we were building for India's most affluent households—a user base that expects **trust, transparency, security, reliability, and exceptional design**. These principles have guided us from day one.

But as we grew—more products, more teams, more data—it became harder to maintain context and move quickly without compromising quality. The question we ask is, how do we make every single member in every function be **10X**? For us, **AI has become a huge unlock** in that journey. It lets us move fast *and* stay right, without sacrificing our core principles."

> "The question we ask is, how do we make every single member in every function be 10X? For us, AI has become a huge unlock in that journey."
> Swamy Seetharaman, CRED

## Introducing Cleo: The AI Conversational Companion

We wanted to move from transactional responses to **empathetic conversations**, which led us to build ***Cleo***, our AI conversational companion powered by **OpenAI models**, including GPT‑4.0, GPT‑5, o3.

Cleo handles three common query types:

- **Informational**: *"What is CRED Cash?"*
- **Contextual**: *"Am I eligible for CRED Cash?"*
- **Transactional**: *"Can I refund to my wallet or original payment method?"*

Cleo diagnoses the issue, classifies the intent, maps it to the right SOP, and frames a **contextual, accurate response**.

## Empowering Teams with Internal AI Tools

We also built two internal tools: ***Thea*** and ***Stark***. Thea is used for support agents, **summarizing multi-format conversations** (text, voice, Hinglish) and suggesting next steps. Stark is designed for operations teams, helping them **create or update SOPs in minutes instead of days**.

## Measurable Results and Impact

Broadly, we've had a **14 percentage point improvement in our CSAT scores**. In the three months since launch, Cleo has reached a **98% resolution accuracy rate**, with **18% more multi-intent conversations** being resolved successfully. **Average handling times have decreased** across all three tools, and **session drop-offs have fallen by 31%**. These are early results, but incredibly encouraging. Together with Cleo, Thea, and Stark—tailored for customers, agents, and operations with the help of AI—we're moving closer to our goal of creating a **true concierge experience** built on trust, reliability, security, and exceptional design.

> "With the help of AI—we're moving closer to our goal of creating a true concierge experience built on trust, reliability, security, and exceptional design."
> Swamy Seetharaman, CRED

## Overcoming Skepticism and Driving Adoption

As with any new technology, there was initial skepticism. But once teams saw results through our internal evaluation framework (which also uses OpenAI models), **confidence grew quickly**.

The biggest surprise has been how fast people adapt once they experience real unlocks. They see that they can be **exponentially more effective and efficient with AI**.

## Future Directions and Scaling Impact

Next, we're expanding ***Cleo*** across all business lines. We're also building tools that detect **"data dead-ends"**—cases where user queries can't be answered—and feed them back into our knowledge base to improve our SOPs in real time.

Our broader goal is for every team member, across every function like engineering, QA, infra, compliance to become **10x more efficient**.

As the ecosystem evolves, success will depend on how fast and how right we can act, identifying the right insights from noise and making **accurate decisions at speed**.

Every company must identify what's most important whether it's efficiency, effectiveness, or both, and then **leverage AI in alignment with their values**.

For us, incorporating OpenAI's technology has been a true unlock across two of our values: compounding and being fast and right. The early results are encouraging, and we're focused on **amplifying and scaling that impact**.

A conversation with Swamy Seetharaman of CRED. 

How CRED's AI Revolution is Creating 10X More Efficient Customer Service Teams

![PIKE-RAG Technology](https://www.microsoft.com/en-us/research/wp-content/uploads/2025/10/PIKERAG-BlogHeroFeature-1400x788-1.jpg)

As a world leader in connected LED lighting products, systems, and services, **Signify** (formerly Philips Lighting) serves not only everyday consumers but also a large number of professional users who have stringent requirements for technical specifications and engineering compatibility. Faced with thousands of product models, complex component parameters, and technical documentation spanning multiple versions, delivering **accurate, professional answers efficiently** has become a core challenge for Signify's knowledge management system.

To address this challenge, Signify collaborated with **Microsoft Research Asia** on a proof-of-concept using **PIKE-RAG technology**, integrating it into their upgraded knowledge management system built on Microsoft Azure. The result: a **12% improvement in answer accuracy**.

## Challenges of Applying RAG in Lighting

In an era where AI is rapidly transforming how enterprises manage information, Signify recognized the strategic importance of precise and efficient knowledge systems. It adopted large AI models and retrieval-augmented generation (RAG) techniques to better support its wide range of customer inquiries.

Yet applying RAG to lighting scenarios involving professional users presented unique challenges. Product data spanned multimodal documents, unstructured tables, and complex product parameters, demanding continuous customization that slowed development and limited scalability. Despite improvements through keyword tuning, system optimization, and refined prompts, Signify sought more advanced approaches to further raise accuracy and reliability.

Seeking to unlock greater value from its knowledge management system, Signify began exploring more suitable technical solutions that are better aligned with their professional use cases. Upon learning that PIKE-RAG had been successfully applied in domains like healthcare and law, significantly improving information accuracy, Signify worked with Microsoft Research Asia on a PoC of PIKE-RAG on Microsoft Azure.

## How PIKE-RAG Addressed Signify's Pain Points

Compared to traditional RAG, **PIKE-RAG efficiently retrieves textual information** and also understands multimodal content like charts and tables. Its built-in domain adaptation module quickly learns reasoning patterns aligned with specific domains to generate responses that are consistent with engineering contexts. These differentiated advantages stem from PIKE-RAG's unique approach to understanding and processing professional knowledge. In Signify's use case, this manifests in three key areas:

### Multimodal Document Parsing and Learning of Industry-Specific Reasoning Patterns

Signify's product documentation includes diverse formats, such as nonstandard tables (e.g., comparison charts of voltage ranges under different currents) and circuit diagrams (e.g., driver power limits). Traditional systems often fail to process this information effectively—either ignoring it or extracting disorganized text fragments.

PIKE-RAG integrates Microsoft Research Asia's Document Intelligence technology with Microsoft Azure OpenAI models to accurately identify table structures and parse key parameters in circuit diagrams. For example, when a customer service agent queries, "What is the output voltage of a specific driver model at 0.15A current," the system automatically locates the curve chart in the document and infers a range of 40–54V based on the current interval—an area where traditional systems frequently err, due to their inability to "read" diagrams.

### End-to-End Knowledge Loop, Eliminating Reliance on Erroneous Data Sources

Enterprise knowledge systems often integrate data from multiple sources, which can lead to discrepancies, especially when database updates are not fully synchronized. PIKE-RAG captures diverse information sources and establishes citation relationships, supporting complex reasoning tasks that rely on multi-source data.

In other words, PIKE-RAG can directly use original documents as data sources, efficiently parsing and understanding product manuals and PDF charts. By extracting key information from these text- and graphic-rich documents, PIKE-RAG enables more efficient and trustworthy knowledge retrieval.

### Dynamic Task Decomposition and Multi-Hop Reasoning for Precise Answers to Complex Questions

Traditional RAG systems typically follow a "one question, one answer" model and struggle with multi-step reasoning. In Signify's lighting domain, customer inquiries often involve multi-level associations. PIKE-RAG dynamically decomposes user questions into executable subtasks and solves them through multi-hop reasoning. For example, when asked, "List all bases compatible with the G8 series lamps," if no document directly provides the answer, PIKE-RAG's reasoning proceeds as follows:

Step 1: The system identifies implicit knowledge. One document notes that the G7 and G8 series have identical dimensions and that all bases compatible with the G7 series are also compatible with the G8 series.

Step 2: Based on this, the system retrieves the base list for the G7 series.

Step 3: Since the list uses abbreviations, the system searches for a table that maps abbreviations to full names and generates a complete list of G8-compatible bases.

Through this automated multi-hop reasoning, the system delivers accurate and complete answers.

![PIKE-RAG Framework](https://www.microsoft.com/en-us/research/wp-content/uploads/2025/10/PIKERAG_figure-1-new.png)

*Figure 1: PIKE-RAG orchestrates and integrates heterogeneous information in multi-source and multimodal environments.*

Testing showed that the PIKE-RAG-powered knowledge management platform provided a significant advantage. It achieved a **12% improvement in performance** compared with the original system.

These results were achieved without any question-specific customization, only algorithmic optimization, demonstrating precise knowledge matching and generation. As the system continues to learn and integrate Signify's proprietary knowledge, accuracy is expected to improve further.

"In the PoC for our product specification insight tool, PIKE-RAG helped us significantly improve the original system's performance. This will enhance overall customer satisfaction. We're currently evaluating PIKE-RAG's application path from multiple angles, including technical implementation, cost control, and future adaptability, and we look forward to deepening our collaboration with Microsoft Research Asia to drive further innovation," said Haitao Liu, head of Signify Research China.

"It's also worth noting that the researchers at Microsoft Research Asia demonstrated strong industry knowledge and rigorous scientific methodology. They proactively studied and analyzed the issues, tracing and clarifying the root causes of our issues to make PIKE-RAG better suited to Signify's real-world needs."

## Beyond Lighting: Generalization Across Industries

In Signify's successful test, PIKE-RAG demonstrated strong generalization capabilities in complex industrial scenarios, enabling rapid cross-domain adaptation. Its three core strengths are:

- **Support for self-evolution and continuous learning**: PIKE-RAG continuously analyzes error cases in interaction logs and uses evolutionary algorithms to automatically optimize knowledge extraction strategies, such as trying different table parsing methods or adjusting multimodal content weights. Validated strategies are then solidified for future Q&A, allowing the system to adapt to new knowledge types without manual intervention.

- **Modular architecture driven by capability needs**: PIKE-RAG flexibly combines modules for document parsing, knowledge extraction, storage, retrieval, organization, knowledge-centered reasoning, and task decomposition. It dynamically adjusts focus areas based on scenario needs (e.g., fact retrieval, multi-hop reasoning, innovative generation) and flexibly builds RAG methods that adapt to real-world applications, efficiently handling various complex tasks.

- **Strong adaptation to domain-specific reasoning patterns**: With dynamic updates through the Domain Tips feature, enterprises can add domain-specific logic (e.g., "the maximum output voltage of an LED driver should be the maximum of the operating range, not the spec sheet's max output") in real time, enabling the system to process information according to professional engineering standards and follow industry conventions.

![PIKE-RAG Overview](https://www.microsoft.com/en-us/research/wp-content/uploads/2025/10/PIKERAG_figure-2.png)

*Figure 2: Overview of the PIKE-RAG framework*

PIKE-RAG's generalization capabilities have been validated not only in Signify's knowledge management platform but also in pilot applications across industries like manufacturing, mining, and pharmaceuticals—significantly improving Q&A system accuracy.

"A leader in lighting, Signify presents a complex industrial knowledge system with a highly challenging real-world scenario for PIKE-RAG. Through this collaboration, we validated that PIKE-RAG's general approach can greatly improve the accuracy of professional knowledge Q&A and accelerate scenario customization. Our researchers also gained valuable experience in handling domain-specific data," explained Jiang Bian, partner research manager at Microsoft Research Asia.

"Our goal isn't to build a universal chatbot but to create a professional assistant that aligns with domain-specific logic and performs rigorous knowledge reasoning. That's the true driving force behind intelligent transformation in industrial knowledge management."

A collaboration between Signify and Microsoft Research shows how PIKE-RAG improves enterprise knowledge systems, delivering a 12% increase in accuracy and faster, more reliable answers:

Today Customer Services Articles Digested