An innovative engineering portal powered by artificial intelligence has revolutionized the way a major oil and gas firm's software engineering team manages information, streamlining operations and enhancing productivity. Previously, engineers faced challenges due to dispersed documentation across platforms like ADO Repo, Confluence, and SharePoint, resulting in time-consuming searches and bottlenecks.
RiverSafe's introduction of this AI-driven solution marks a significant improvement in the engineering workflow, characterized by quicker access to technical data and increased efficiency.
Overcoming Documentation Fragmentation
RiverSafe's intervention aimed at addressing these issues has significantly improved the engineering team’s ability
The corporation's engineering department struggled with scattered documentation, which not only delayed access to crucial information but also hindered project progress. The traditional reliance on individual expertise created a dependency culture that led to frequent meetings and inefficiencies.
RiverSafe's intervention aimed at addressing these issues has significantly improved the engineering team’s ability to perform tasks by minimizing time spent searching for misplaced documentation.
AI-Enabled Knowledge Discovery
The engineering portal incorporates natural language processing (NLP) and a closed-domain RAG model to facilitate an intuitive ChatGPT-style interaction, allowing engineers to obtain answers swiftly through natural language queries.
This enhancement significantly reduces the time spent locating information and includes features such as diagrams, graphs, and videos, as well as automation capabilities for task execution, such as tool onboarding. The solution integrates information from various repositories, creating a cohesive search experience.
Ensuring Precision and Relevance
RiverSafe has introduced near-real-time monitoring of vital model metrics to ensure the accuracy
RiverSafe has introduced near-real-time monitoring of vital model metrics to ensure the accuracy and relevance of responses. This is crucial in maintaining the portal's effectiveness and providing real-time value to its users.
By addressing potential pitfalls such as response degradation common in AI systems, innovative solutions have been crafted to enhance user interaction outcomes.
Positive Organizational Impact
The impact of the AI-driven portal on the organization has been substantial, with engineers now saving between 45 minutes and ten days when seeking technical solutions.
The implementation has led to saving 68,000 engineering hours annually, translating to over £4 million in cost savings during its first year. The portal also provides high-fidelity responses, linking to pertinent documentation and media to support task execution.
Improved Document Quality and Automation
Data collected on document usage ensures that outdated items are updated, maintaining a high-quality
Data collected on document usage ensures that outdated items are updated, maintaining a high-quality knowledge base.
Engineers can seamlessly perform tasks within the platform, such as new tool onboarding, enhancing workflow efficiency by eliminating the need to toggle between systems.
User Feedback and Continuous Optimization
The portal's ongoing user feedback collection aids in its evolution as a valuable tool for the organization.
In collaboration with NeuroLogik, efforts to deepen insights across codebases continue, allowing engineers to readily access and utilize existing code fragments efficiently, thus fostering a streamlined software development environment.
The client, a pioneering oil and gas corporation, faced significant challenges in knowledge management. The software engineering function struggled with locating the right documentation across multiple platforms such as ADO Repo, Confluence, SharePoint, and others.
This fragmented system created delays and inefficiencies, with engineers spending valuable time searching for answers rather than focusing on delivery. Slow Access to Technical Information The sheer volume of documentation, continuously growing, compounded the problem.
Onboarding tools for cloud services
Onboarding tools for cloud services was also cumbersome, often dependent on a “hero culture” where finding the right person for help was the norm. This led to frequent meetings, wasted time, and a negative engineering experience, significantly slowing down workflows.
RiverSafe was brought in to improve the engineer experience and increase velocity by enabling engineers to complete tasks more efficiently, reduce reliance on individual knowledge holders, and minimize time spent searching for outdated or misplaced documentation.
The solution
AI-enabled knowledge discovery
They introduced an engineering portal powered by AI and natural language processing (NLP). Using a closed-domain RAG model, this portal introduced a ChatGPT-style interface where engineers could engage in natural language conversations to query documentation and receive consolidated answers, dramatically reducing the time spent locating information.
The portal’s capabilities include rich content support such as diagrams, graphs, videos, and even in-platform automation for tasks like tool onboarding, further streamlining processes. The platform draws from multiple high-quality content repositories, creating a unified search experience across ADO Repo, Confluence, Internal document management systems, SharePoint, and more.
Crucially, they implemented near-real-time monitoring for key model metrics, ensuring that each user’s question and answer interactions delivers unparalleled accuracy and relevance. This guarantees that the portal continuously provides genuine value through its responses. Recognizing the challenges posed by response degradation and hallucinations in AI-driven systems, they have developed a set of innovative solutions designed to optimize each interaction’s impact.
The outcome
Eliminating wasted time and accelerating software delivery
The portal has transformed the way engineers work, saving significant time and boosting efficiency across the board.
One engineer commented, “I’ve been here for 15 years, and this is the best product for software delivery in our organization. Previously, it could take me 2 weeks just to find out how to build a cloud environment. Now I get the answer straight away.”
Key outcomes
- Time and Cost Savings: Engineers now save between 45 minutes and 10 days when searching for technical solutions. The portal has saved the organization 68,000 engineering hours annually, equating to over £4 million in cost savings within the first year.
- Improved Document Quality: The platform collects and analyses data on the usefulness and quality of documents. This feedback loop ensures that outdated or low-quality documents are flagged for improvement, keeping the knowledge base relevant and focused on high-value content.
- High-Fidelity Responses: Engineers receive immediate, detailed responses with links to relevant documentation, images, videos, and graphs. This reduces reliance on outdated information and significantly improves the quality of software delivery.
- Onboarding and Automation: Engineers can complete tasks directly within the platform, such as onboarding new tools, without needing to switch between systems, further streamlining workflows.
User feedback and performance data
The portal continues to gather user feedback and performance data, ensuring that it remains an invaluable tool for the organization, consistently improving the engineer experience and accelerating software delivery. The organization has also engaged NeuroLogik to build on these successes.
NeuroLogik specialises in providing deep insights into entire codebases, ensuring that engineers can easily locate and reuse existing code across the organization, further enhancing efficiency and reducing duplication of effort.
