test test case studies
test test case studies
test test case studies
Executive Summary To solve a complex client requirement for an insurance quote, RUNNINGHILL embarked on a 6-month project, beginning with a 2-month deep-dive to build a foundational agentic workflow. Mastering the LangGraph SDK, our team successfully built a stateful, reliable proof-of-concept that is now being expanded for production. This initial phase, using a JSON-based “collection …
Read more “LangGraph Case Study: RUNNINGHILL Builds Stateful AI Agent for Insurance Quote Workflow”
Executive Summary To solve the critical industry challenge of scaling AI systems, a RUNNINGHILL developer dedicated 3-4 weeks to a strategic R&D project. The initiative involved building a proof-of-concept for the new Agent-to-Agent (A2A) protocol. The result was a successful multi-agent system where agents built on different frameworks (Google ADK and CrewAI) collaborated seamlessly to …
Read more “Building a Scalable, Multi-Agent AI System with the A2A Protocol”
Executive Summary To solve internal challenges around AI data privacy and limited context windows, RUNNINGHILL championed a developer-led R&D initiative. The project produced a production-ready AI agent, “Project Raggedy Rag,” that runs 100% locally, ingests entire codebases for full context, and automates error analysis and ticket creation. This zero-cost POC, built with open-source tools in …
Read more “From R&D to RAG: Automating Error Analysis with On-Prem AI”
About the Client A Top-Tier South African Insurer, the client is one of the country’s largest and best providers of financial services, offering a broad portfolio including personal lines, business insurance, and value-added products. Their ongoing strategic goal is to move away from expensive, skill-limited legacy systems to a modern, agile tech stack that enables …
Read more “Insurance System Overhaul for Stability & Efficiency”
About the Client A leading South African insurance and financial services provider, the client is a diversified group that offers a wide range of products including commercial, personal, and life insurance. Known for its innovative approach to the market, the company sought to modernise its core technology stack to maintain its competitive edge and improve …
Transforming the eternal question of ‘What will we eat?’ into a delightful discovery with CulinaryCognition—where your pantry meets our technology to create meals that inspire. Challenges: AI Model Training Challenges: Our journey began with the challenge of training AI models due to limited infrastructure. Initially, we leveraged Google Colab’s Nvidia T4 GPUs for their tensor …
Our collaborative endeavour aimed to streamline school finances with efficient fee collection, ensure engaged learning with AI-driven blended education, support educators with robust professional development tools, and monitor school performance with real-time insights—all in one accessible, offline-ready Student Information System (SIS) solution. Challenges: Implementation: Results: These strategic efforts have transformed the tutoring bot solution, fostering …
In the ever-changing realm of technology, businesses often find themselves missing skills and having to go through hiring processes to fill gaps. Introducing Runninghill’s newest creation: The Swiss-army-developer—everything you need in one convenient package. Challenges: Implementation: We are developing a cutting-edge application that leverages the latest technologies to create an immersive and intelligent user experience. …
Transforming complexity into clarity: How Runninghill’s strategic overhaul of a lead management system propelled one of South Africa’s largest insurance companies from operational chaos to peak performance in production. Challenges: Implementation: Results: Through these strategic interventions, Runninghill not only rescued a faltering project but also laid a strong foundation for ongoing enhancements and growth. The …