The National Social Security Fund (NSSF) of Uganda, a quasi-government agency mandated under the NSSF Act, Cap 222 to provide social security services to private-sector employees, has deployed an AI-enabled digital customer assistant named 'Sanyu' to automate front-line member interactions across its digital channels. The NSSF is the largest pension fund in the East African Community, managing assets exceeding USh15.5 trillion (approximately USD 4.4 billion as of June 2021), and serves a substantial member base of private-sector employees and employers across Uganda. The Fund is regulated by the Uganda Retirement Benefits Regulatory Authority, with the Minister of Finance, Planning and Economic Development responsible for policy oversight.
Sanyu was first deployed in October 2020 as part of NSSF's broader digital transformation strategy, which has moved over 94 percent of member transactions and interactions to digital channels, leaving only 6 percent handled through walk-in service centres. The chatbot was developed and integrated using Avaya OneCloud CCaaS (Contact Centre as a Service) technology, with Sybyl reported as the systems integrator in trade press. Sanyu is an AI-enabled chatbot that simulates human conversation and addresses routine member requests through text-based chat and self-service capabilities. It is integrated across multiple customer-facing interfaces including the NSSF web portal, mobile app, mobile browser, and social messaging platforms. Initial deployment covered Twitter Direct Messages, Facebook Messenger, and the corporate website. By financial year 2022/23, NSSF had extended Sanyu to its WhatsApp channel, reflecting the messaging platform's widespread adoption in Uganda.
The chatbot enables members to perform several key self-service functions: employer registration, member registration, tracking the status of benefit processing, checking provisional balances, requesting member statements, and accessing answers to frequently asked questions. When Sanyu cannot fulfil a customer request, the system seamlessly routes the query to the best available human agent, ensuring that complex or non-routine matters receive appropriate attention from trained staff. This escalation mechanism represents a human-on-the-loop (HOTL) oversight model, where automated replies handle routine queries while human agents remain available for cases requiring judgment or intervention.
The deployment of Sanyu was driven by operational pressures documented by NSSF Managing Director Richard Byarugaba, who stated that customer service personnel were spending approximately three-quarters of their working day on easily-answered routine queries such as statement requests, registration, and FAQs. The Fund was also struggling to maintain consistent service quality across its various digital platforms as the volume of inbound requests grew. By automating these routine interactions, NSSF aimed to free front-end employees to focus on more complex tasks, including providing psychological and financial wellness support to members during the COVID-19 pandemic. The pandemic context was particularly significant: lockdowns and social distancing measures reduced physical branch visits and sharply increased demand on NSSF's call centres and online platforms, making the chatbot deployment operationally critical.
Quantified outcomes from the deployment have been reported across two NSSF Integrated Reports. The FY2020/21 Integrated Report stated that 240,194 customer interaction transactions had been registered via the chatbot since deployment, and that up to 75 percent of routine agent interactions were being handed off to the chatbot. The earlier Intelligent CIO Africa report from March 2022 cited nearly 164,000 customer transactions and interactions through Sanyu as of that reporting period. A January 2022 Aptantech report described the same deployment and specified the employer registration and member statement workflows available through the chatbot. NSSF has stated that the solution contributes to improvement in its Net Promoter Score (NPS) and first contact resolution rates, and that contact centre agents have been able to refocus their time on more complex requests requiring direct intervention. The Fund tracks a comprehensive range of service quality indicators including Customer Satisfaction Index, NPS, Mystery Shopper Survey Score, Service Quality Score, Customer Effort Score, service levels and efficiency, first call resolution, customer complaints and resolution turnaround time, and the ratio of e-channel to walk-in interactions.
The specific NLP or large language model components underlying Sanyu's conversational capabilities have not been disclosed in any primary source. NSSF's own materials describe Sanyu as an 'Artificial Intelligent-powered chatbot that simulates human conversation,' but do not specify the model architecture, training data, or whether the system relies on scripted decision trees, retrieval-based NLP, or generative AI components. The Avaya OneCloud CCaaS platform provides the contact centre infrastructure, but the precise AI pipeline remains unverified. Similarly, details regarding the hosting location, data residency arrangements, and specific data protection controls applied to member data processed through Sanyu have not been located in any primary source reviewed.