Fully Automated Agentic AI Programming Frameworks
Research focused on automated agentic AI programming frameworks that enable AI systems to generate, test, and optimize code using Gen AI, LLMs, and orchestration tooling like LangChain, LLM Agents, and the MCP Protocol.
Research Focus: Ongoing research in methodologies and advancements for autonomous AI systems, with published work available in our research portfolio.
Benchmarking: Continuous benchmarking to validate the performance, robustness, and efficiency of agentic AI programming frameworks for real-world applications.
Context-Based Document Management Systems
Development of context-based document management systems that process and manage unstructured data repositories. These systems utilize RAG, Vector Databases, and data governance capabilities (Microsoft Purview) for information retrieval, insight extraction, and compliance.
Vision for AI Products
This foundational research informs the design and development of AI products built on secure and responsible AI principles for industrial and enterprise applications.
Events & Speaking Engagements
Smart Water Utilities 2025 Conference
Speaker: Zahir Alward, Precocity Research Limited
Date: March 2025
Location: Melbourne, Australia
Speaking engagement at the Smart Water Utilities 2025 conference covering advanced topics in AI, data architecture, and smart water infrastructure solutions.
View EventCyma's Learning Lunch Webinar
Speaker: Zahir Alward, Precocity Research Limited
Date: June 13, 2024
Webinar presentation covering enterprise technology solutions and industry insights.
View Event6th Annual New Zealand Government Data Summit
Speaker: Zahir Alward, Precocity Research Limited
Date: May 7-9, 2024
Speaking engagement at the 6th Annual New Zealand Government Data Summit, presenting on data architecture and government technology solutions.
View EventPublished Research
Benchmarking Small LLM Retrieval Augmented Generation
Author: Zahir Alward, Precocity Research Limited
Published: June 13, 2025 on LinkedIn
A comprehensive analysis of small language model performance in retrieval-augmented generation scenarios, providing benchmarks and insights for practical AI implementation in enterprise environments.
Read Paper