UGA-003

NSSF Uganda 'Sanyu' AI-Enabled WhatsApp Chatbot for Member Self-Service

Download PDF
Uganda Sub-Saharan Africa Low income Full Production Deployment Confirmed

National Social Security Fund (NSSF) Uganda

At a Glance

What it does Perception and extraction from unstructured inputs — User communication and interaction
Who runs it National Social Security Fund (NSSF) Uganda
Programme National Social Security Fund (NSSF) Uganda
Confidence Confirmed
Deployment Status Full Production Deployment
Key Risks Market, sovereignty and industry structure risks
Key Outcomes 240,194 customer interaction transactions via chatbot reported in NSSF FY2020/21 Integrated Report.
Source Quality 4 sources — News article / media, Report (government / official)

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.

Classifications follow the DCI AI Hub Taxonomy. Hover over field labels for definitions.

Social Protection Functions

Implementation/delivery chain
Outreach/communications/sensitisation primaryCase management Management of contributions and withdrawals Registration
SP Pillar (Primary) The social protection branch: social assistance, social insurance, or labour market programmes. Social insurance
Programme Name National Social Security Fund (NSSF) Uganda
Programme Type The type of social protection programme, classified under social assistance, social insurance, or labour market programmes. View in glossary Old age, survivors and disability pensions
System Level Where in the social protection system the AI is applied: policy level, programme design, or implementation/delivery chain. View in glossary Implementation/delivery chain
Automation Subtype For operational automation cases: (a) document processing and generative staff assistance, or (b) workload and resource forecasting. (a) Document processing and generative staff assistance
Programme Description Uganda's NSSF is a provident fund established in 1985 covering all private-sector employees. Participation is compulsory for both employers and employees. The Fund collects, safekeeps, responsibly invests, and distributes retirement savings. Following the NSSF (Amendment) Act 2022, the Fund is expanding coverage to the informal sector.
Implementation Type How the AI output is produced: Classical ML, Deep learning, Foundation model, or Hybrid. Affects validation, compute requirements, and governance profile. View in glossary Classical ML
Lifecycle Stage Current stage in the AI lifecycle, from problem identification through to monitoring, maintenance and decommissioning. View in glossary Monitoring, Maintenance and Decommissioning
Model Provenance Origin of the AI model: developed in-house, adapted from open-source, commercial/proprietary, or accessed via third-party API. View in glossary Commercial/proprietary
Compute Environment Where the AI system runs: on-premise, government cloud, commercial cloud, or edge/device. View in glossary Not documented
Sovereignty Quadrant Classification of data and compute sovereignty: I (Sovereign), II (Federated/Hybrid), III (Cloud with safeguards), or IV (Shared Innovation Zone). View in glossary Not assessed
Data Residency Where the data used by the AI system is stored: domestic, regional, or international. View in glossary Not documented
Cross-Border Transfer Whether data crosses national borders, and if so, whether documented safeguards are in place. View in glossary Not documented
Is Agentic Whether the system autonomously plans and executes multi-step workflows, selecting tools and chaining actions with limited human intervention. View in glossary Partial
Agentic Pipeline Description of the chained workflow steps in the agentic pipeline. Sanyu handles inbound member queries autonomously through text-based chat, performing self-service tasks (registration, balance checks, benefits tracking, FAQs). When unable to fulfil a request, it autonomously routes the query to the best available human agent.
Agentic Autonomy Degree of autonomy: fully autonomous, semi-autonomous (human checkpoints), or supervised (human approval at each step). Semi-autonomous
Override Points Where in the pipeline human review or override is triggered. Human agent escalation for unresolved queries; queries seamlessly routed to best available agent when chatbot cannot fulfil request.
Decision Criticality The rights impact of the decision the AI supports. High criticality requires HITL oversight; moderate requires HOTL; low may operate HOOTL. View in glossary Low
Human Oversight Type Level of human involvement: Human-in-the-Loop (active review), Human-on-the-Loop (monitoring), or Human-out-of-the-Loop (periodic audit). View in glossary HOTL
Development Process Whether the AI system was developed fully in-house, through a mix of in-house and third-party, or fully by an external provider. View in glossary Fully third-party developed
Highest Risk Category The most significant structural risk source identified: data, model, operational, governance, or market/sovereignty risks. View in glossary Market, sovereignty and industry structure risks
Risk Assessment Status Whether a formal risk assessment, informal assessment, or independent audit has been conducted for this system. Not assessed

Impact Dimensions

Autonomy, human dignity and due process
  • Human oversight protocol
CategorySensitivityCross-System LinkageAvailabilityKey Constraints
Beneficiary registries and MISPersonalLinks data across multiple systemsCurrently available and usedChatbot retrieves member balance and benefits status data from NSSF backend systems; linkage details not disclosed.
Unstructured and text-based contentPersonalSingle source (no linkage)Currently available and usedMember text queries and basic identifiers implied by chatbot functions (registration, balance checks, benefits tracking); specific data fields processed by Sanyu not enumerated in primary sources.

Aptantech (2022) 'NSSF Uganda unveils Sanyu digital assistant to boost customer service', 27 January. Available at: https://aptantech.com/2022/01/27/nssf-uganda-unveils-sanyu-digital-assistant-to-boost-customer-service/ (Accessed: 27 March 2026).

View source News article / media

Intelligent CIO Africa (2022). Uganda National Social Security Fund Transforms Customer Experience with AI-Based Chatbot Powered by Avaya. Dubai: Lynchpin Media. Available at: https://www.intelligentcio.com/africa/2022/03/14/uganda-national-social-security-fund-transforms-customer-experience-with-ai-based-chatbot-powered-by-avaya/ (Accessed 31 Oct 2025).

View source News article / media

National Social Security Fund (2021). The 'Sanyu' Chatbot (Our Members) - NSSF Integrated Report 2020/21. Kampala: NSSF Uganda. Available at: https://amm-report-2021.azurewebsites.net/our-members.php (Accessed 31 Oct 2025).

View source Report (government / official)

National Social Security Fund (2023). WhatsApp Chatbot (Our Members) - NSSF Integrated Digital Report 2023. Kampala: NSSF Uganda. Available at: https://amm-ir-2023.azurewebsites.net/our-members.html (Accessed 31 Oct 2025).

View source Report (government / official)
Deployment Status How far the system has progressed into real-world operational use, from concept/exploration through to scaled and institutionalised. View in glossary Full Production Deployment
Year Initiated The year the AI system was first initiated or development began. 2020
Scale / Coverage The scale and geographic or population coverage of the deployment. National coverage across all NSSF digital channels (web portal, mobile app, WhatsApp, Twitter DM, Facebook Messenger); 240,194 interactions reported by FY2020/21
Funding Source The source(s) of funding for the AI system development and deployment. NSSF operational budget (not specified in sources)
Technical Partners External technology vendors, academic partners, or development partners involved. Avaya (OneCloud CCaaS platform); Sybyl (systems integrator, reported in trade press only)
Outcomes / Results 240,194 customer interaction transactions via chatbot reported in NSSF FY2020/21 Integrated Report. Up to 75% of routine agent interactions handed off to chatbot. Nearly 164,000 transactions reported in earlier Intelligent CIO Africa coverage (March 2022). NSSF reports the solution contributes to improved NPS and first contact resolution rates. 94% of member transactions and interactions moved to digital channels overall.

How to Cite

DCI AI Hub (2026). 'NSSF Uganda 'Sanyu' AI-Enabled WhatsApp Chatbot for Member Self-Service', AI Hub AI Tracker, case UGA-003. Digital Convergence Initiative. Available at: https://socialprotectionai.org/use-case/UGA-003 [Accessed: 1 April 2026].

Change History

Updated 1 Apr 2026, 08:11
by system (system)
Updated 31 Mar 2026, 06:35
by system (system)
Created 30 Mar 2026, 08:41
by v2-import (import)