Gen AI interface enhances API productivity and UX

Transportation & Logistics

Gen AI interface enhances API productivity and UX

Integrating Generative AI technology and developer portal reduces logistics provider’s API onboarding to 1-2 days.

Client
Leading logistics services provider
Goal
Improve API functionality and developer team’s productivity and user experience
Tools and Technologies
Business Challenge

A leading logistics provider offers an API Developer Portal as a central hub for managing APIs, enabling collaboration, documentation, and integration efforts, but faces limitations, including:

  • Challenges to comprehend schemas, necessitating continued reliance on developers
  • No means to individually search for API operations on the API Developer Portal
  • Difficulties keeping track of changes in newly-released API versions
  • Potential week-long delays as business analysts or product owners must engage developers to check if existing APIs can support new website functionalities
Solution

Integrating Gen AI technology with API, we provided a user-friendly chat interface for business users. Features include:

  • Conversational interface for API interaction, eliminating the need for technical expertise to interact directly with APIs
  • Search mechanism for API operations, query parameters, and request attributes
  • Version comparison and tailored response generation
  • Backend API execution according to user query needs

 

Outcomes
  • Business users are now empowered with a chat-based interface for querying API details
  • Users can seamlessly explore APIs, streamlining collaboration with the API team and reducing onboarding time to one or two days, ultimately enhancing the customer experience for all stakeholders.
  • Developer productivity improved with the AI-powered tools in the API Developer Portal
  • Functionality is enhanced from the version comparison, individual API operation search, and tailored responses
Contact

Our experts can help you find the right solutions to meet your needs.

Get in touch
Explore the world with Iris. Follow us on social media today.

Gen AI summarization solution aids lending app users

Banking

Gen AI summarization solution aids lending app users

Conversational agent built with Gen AI eases commercial lenders’ access to information, use of complex applications, and integration of new users.

Client
Commercial banking unit of a large Canadian bank
Goal
Help lenders access information for complex lending applications on more timely basis and simplify onboarding of new users
Tools and Technologies
PyPDF2, Meta
Business Challenge

As a part of the credit adjudication process for a transaction, commercial bankers use an application to create summaries, memos and rating alerts as needed, which are instrumental for ongoing Capital at Risk (CaR) monitoring, Risk Profiling, Risk Adjusted Return on Capital (RAROC) computations, etc.

There is a significant amount of complexity involved in understanding this application due to the diversity in types of borrowers / loans, nature of collaterals, etc., e.g., How to create a transaction report for my deal? How to update an existing deal?

All of this information is spread across multiple user guides and FAQ documents that may run into hundreds of pages.

Solution
  • Ringfenced a knowledge base comprised of the user guides of various functionalities (e.g., facility creation, borrower information, etc.)
  • Built a custom-developed, React-based front-end for the conversational assistant to interact with the users
  • Parsed, formatted and extracted text chunks from these documents using libraries such as PDF Miner, PyPDF2
  • Created vector embeddings using sentence transformer embedding model (all-MiniLM-L6-v2) and stored as indices in the Facebook AI Similarity Search (FAISS) vector database
  • Broke down the user query into vector embeddings, searched against the vector database and leveraged local LLM (Llama-2-7B-chat) to generate summarized responses based on the context passed to it by the similarity search
Outcomes

Our custom solution was a conversational agent built using Generative AI, which summarizes relevant information from multiple documents.

It significantly:

  • Improved existing users’ ability to access relevant information on a timely basis
  • Simplified the migration of bankers and integrations of lending applications resulting from merger or acquisition
Contact

Our experts can help you find the right solutions to meet your needs.

Get in touch
Explore the world with Iris. Follow us on social media today.

Conversational assistant boosts AML product assurance

Banking

Conversational assistant boosts AML product assurance

Gen AI-powered responses improve the turnaround time to provide technical support for recurring issues, resulting in a highly efficient product assurance process.

Client
A large global bank
Goal
Improve turnaround time to provide technical support for the application support and global product assurance teams
Tools and Technologies
React, Sentence–Bidirectional Encoder Representations from Transformers (S-BERT), Facebook AI Similarity Search (FAISS), and Llama-2-7B-chat
Business Challenge

The application support and global product assurance teams of a large global bank faced numerous challenges in delivering efficient and timely technical support as they had to manually identify solutions to recurring problems within the Known Error Database (KEDB), comprised of documents in various formats. With the high volume of support requests and limited availability of teams across multiple time zones, a large backlog of unresolved issues developed, leading to higher support costs.

Solution

Our team developed a conversational assistant using Gen AI by:

  • Building an interactive customized React-based front-end
  • Ringfencing a corpus of problems and solutions documented in the KEDB
  • Parsing, formatting and extracting text chunks from source documents and creating vector embeddings using Sentence–Bidirectional Encoder Representations from Transformers (S-BERT)
  • Storing these in a Facebook AI Similarity Search (FAISS) vector database
  • Leveraging a local Large Language Model (Llama-2-7B-chat) to generate summarized responses
Outcomes

The responses generated using Llama-2-7B LLM were impressive and significantly reduced overall effort. Future enhancements to the assistant would involve:

  • Creating support tickets based on information collected from users
  • Categorizing tickets based on the nature of the problem
  • Automating repetitive tasks such as access requests / data volume enquiries / dashboard updates
  • Auto-triaging support requests by asking users a series of questions to determine the severity and urgency of the problem

Gen AI For Software Engineers

Contact

Our experts can help you find the right solutions to meet your needs.

Get in touch
Explore the world with Iris. Follow us on social media today.

AI-powered summarization boosts compliance workflow

Insurance

AI-powered summarization boosts compliance workflow

Gen AI-enabled conversational assistant substantially simplifies access to underwriting policies and procedures across multiple, complex documents.

Client
A leading specialty property and casualty insurer
Goal
Improve underwriters’ ability to review policy submissions by providing easier access to information stored across multiple, voluminous documents.
Tools and Technologies
Azure OpenAI Service, React, Azure Cognitive Services, Llama-2-7B-chat, OpenAI GPT 3.5-Turbo, text-embedding-ada-002 and all-MiniLM-L6-v2
Business Challenge

The underwriters working with a leading specialty property and casualty insurer have to refer to multiple documents and handbooks, each running into several hundreds of pages, to understand the relevant policies and procedures, key to the underwriting process. Significant effort was required to continually refer to these documents for each policy submission.

Solution

A Gen-AI enabled conversational assistant for summarizing information was developed by:

  • Building a React-based customized interactive front end
  • Ringfencing a knowledge corpus of specific documents (e.g., an insurance handbook, loss adjustment and business indicator manuals, etc.)
  • Leveraging OpenAI embeddings and LLMs through Azure OpenAI Service along with Azure Cognitive Services for search and summarization with citations
  • Developing a similar interface in the Iris-Azure environment with a local LLM (Llama-2-7B-chat) and embedding model (all-MiniLM-L6-v2) to compare responses
Outcomes

Underwriters significantly streamlined the activities needed to ensure that policy constructs align with applicable policies and procedures and for potential compliance issues in complex cases.

The linguistic search and summarization capabilities of the OpenAI GPT 3.5-Turbo LLM (170 bn parameters) were found to be impressive. Notably, the local LLM (Llama-2-7B-chat), with much fewer parameters (7 bn), also produced acceptable results for this use case.

Gen AI For Software Engineers

Contact

Our experts can help you find the right solutions to meet your needs.

Get in touch
Explore the world with Iris. Follow us on social media today.

Automated financial analysis reduces manual effort

Commercial & Corporate Banking

Automated financial analysis reduces manual effort

Analysts in a large North American bank's commercial lending and credit risk operations can source intelligent information across multiple documents.

Client
Commerical lending and credit risk units of large North American bank
Goal
Automated retrieval of information from multiple financial statements enabling data-driven insights and decision-making
Tools and Technologies
OpenAI API (GPT-3.5 Turbo), LlamaIndex, LangChain, PDF Reader
Business Challenge

A leading North American bank had large commercial lending and credit risk units. Analysts in those units typically refer to numerous sections in a financial statement, including balance sheets, cash flows, and income statements, supplemented by footnotes and leadership commentaries, to extract decision-making insights. Switching between multiple pages of different documents took a lot of work, making the analysis extra difficult.

Solution

Many tasks were automated using Gen AI tools. Our steps:

  • Ingest multiple URLs of financial statements
  • Convert these to text using the PDF Reader library
  • Build vector indices using LlamaIndex
  • Create text segments and corresponding vector embeddings using OpenAI’s API for storage in a multimodal vector database e.g., Deep Lake
  • Compose graphs of keyword indices for vector stores to combine data across documents
  • Break down complex queries into multiple searchable parts using LlamaIndex’s DecomposeQueryTransform library
Outcomes

The solution delivered impressive results in financial analysis, notably reducing manual efforts when multiple documents were involved. Since the approach is still largely linguistic in nature, considerable Prompt engineering may be required to generate accurate responses. Response limitations due to the lack of semantic awareness in Large Language Models (LLMs) may stir considerations about the usage of qualifying information in queries.

Gen AI For Software Engineers

Contact

Our experts can help you find the right solutions to meet your needs.

Get in touch
Explore the world with Iris. Follow us on social media today.

Next generation chatbot eases data access

Brokerage, Wealth & Asset Mgmt

Next generation chatbot eases data access

Gen AI tools help users of retail brokerage trading platform obtain information related to specific needs and complex queries.

Client
Large U.S.-based Brokerage and Wealth Management Firm
Goal
Enable a large number of users to readily access summarized information contained in voluminous documents.
Tools and Technologies
Google Dialogflow ES, Pinecone, Llamaindex, OpenAI API (GPT-3.5 Turbo)
Business Challenge

A large U.S.-based brokerage and wealth management client has a large number of users for its retail trading platform that offers sophisticated trading capabilities. Although extensive information was documented in hundreds of pages of product and process manuals, it was difficult for users to access and understand information related to their specific needs (e.g., How is margin calculated? or What are Rolling Strategies? or Explain Beta Weighting).

Solution

Our Gen AI solution encompassed:

  • Building a user-friendly interactive chatbot using Dialogflow in Google Cloud
  • Ringfencing a knowledge corpus comprising specific documents to be searched against and summarized (e.g., 200-page product manual, website FAQ content)
  • Using a vector database to store vectors from the corpus and extract relevant context for user queries
  • Interfacing the vector database with OpenAI API to analyze vector-matched contexts and generate summarized responses
Outcomes

The OpenAI GPT-3.5 turbo LLM (170 bn parameters) delivered impressive linguistic search and summarization capabilities in dealing with information requests. Prompt engineering and training are crucial to secure those outcomes.

In the case of a rich domain such as a trading platform, users may expect additional capabilities, such as:

  • API integration, to support requests requiring retrieval of account/user specific information, and
  • Augmentation of linguistic approaches with semantics to deliver enhanced capabilities.

Gen AI For Software Engineers

Contact

Our experts can help you find the right solutions to meet your needs.

Get in touch
Explore the world with Iris. Follow us on social media today.
Copyright © 2024 Iris Software, Inc. All rights reserved