Skip to main content
AI Hub
Home Browse Cases Countries Sources Explore Taxonomy About Submit
Sign In
DCI AI Hub — AI Tracker socialprotectionai.org/use-case/AZE-001
AZE-001 Exported 1 April 2026

Social Bot / iDost — AI-Enabled Chatbot and Call Center System for Social Protection Services

Country Azerbaijan
Deployment Status Operational Deployment (Limited Rollout)
Confidence Likely
Implementing Agency DOST Agency (Agency for Sustainable and Operational Social Security); DOST Digital Innovations Center; Ministry of Labour and Social Protection of Population (MLSPP); State Social Protection Fund; Social Services Agency; State Employment Agency

Overview

Azerbaijan's Ministry of Labour and Social Protection of Population (MLSPP), through the DOST Agency (Agency for Sustainable and Operational Social Security) and the DOST Digital Innovations Center, operates an AI-enabled chatbot and call center system that provides automated citizen inquiry handling across multiple social protection service channels. The system has two main components: the 142 Call Center, which serves as a unified platform consolidating the call centers of all MLSPP subordinate bodies into a single contact number, and the Social Bot / iDost digital assistant, which provides AI-driven conversational support via the e-Social web portal and social media channels.

The 142 Call Center, operating from the premises of Baku DOST Center No. 4, has the capacity to receive up to 5,000 calls per day across the country. Over five years of operation, it has handled approximately 4.17 million citizen appeals. The center transitioned from a multichannel customer support format to an omnichannel model, integrating previously separate communication channels — telephone, social media, and web-based inquiries — into a single communication system. In the first half of 2024, the system processed 812,589 applications, with approximately 7,100 daily calls. The Social Bot component handles approximately 69.8 per cent of social media appeals automatically, with unresolved queries escalated to human operators.

On 6 January 2026, the MLSPP launched the iDost digital assistant on the e-Social portal (e-sosial.az). iDost uses natural language processing to allow citizens to access electronic services by typing natural language requests rather than navigating through the site menu. For example, citizens can type queries such as 'I want to check my pension' or 'I need to obtain an electronic certificate', and the AI assistant directs them to the appropriate service within seconds. iDost covers inquiries related to pension provision, social payments, disability services, electronic certificates, and other social welfare programmes. The assistant includes an interactive feedback mechanism allowing users to rate responses with star ratings, designed to continuously refine AI accuracy.

The DOST Digital Innovations Center, established on 17 December 2021 by decision No. 4 of the DOST Agency's Supervisory Board, serves as the unified management body for information and communication issues across the MLSPP and its subordinate bodies. It integrates data from over 80 state and private institutions and draws on 17 comprehensive social registries through a centralized electronic information system (CEIS) that automates information creation, storage, and retrieval. The center has established a dedicated Artificial Intelligence Application Division responsible for developing and deploying AI solutions including the chatbot systems. A local vendor was procured for the 'Chatbot (Social Bot) platform' through tender processes conducted in 2022-2023.

The system serves a population of approximately 10.2 million citizens. Since 2022, the DOST Digital Innovations Center has facilitated services reaching more than 9.2 million people. The center has digitised 91.5 per cent of the MLSPP's 160 services, with 56 per cent of services operating via a proactive mechanism that automatically identifies eligible citizens without requiring applications. The broader digital ecosystem executes approximately 25,000 daily assignments. In 2024 alone, over 250,889 individuals received proactive social payments, with the most commonly assigned being the lump sum birth benefit.

The chatbot and call center system handles inquiries spanning multiple social protection domains: pensions, disability benefits, rehabilitation services, employment services, labour compliance, and use of e-services. Template responses are continuously updated, and a human operator backup is maintained for queries the bot cannot address. Long-term call data accumulated since 2014 (millions of interactions) is used to refine the knowledge base. The DOST Agency's roadmap for 2025-2027 includes further integrating AI technologies into the social protection system to enhance data-driven decisions and predictive analytics for more targeted service delivery.

Classification

AI Capabilities

Perception and extraction from unstructured inputs (primary)Classification

Use Cases

User communication and interaction (primary)Operational and process automation

Social Protection Functions

Implementation/delivery chain: Outreach/communications/sensitisation (primary)Implementation/delivery chain: Provision of payments/services
SP Pillar (Primary)Social insurance
SP Pillar (Secondary)Social assistance

Programme Details

Programme Name142 Call Center and Social Bot / iDost Digital Assistant
Programme TypeOther
System LevelImplementation/delivery chain
Automation Subtype(a) Document processing and generative staff assistance

Unified multi-channel citizen inquiry and information service operated by DOST Agency covering all MLSPP social protection programmes. Handles inquiries about pensions, disability benefits, social payments, employment services, rehabilitation, labour compliance, and e-service usage. Capacity of up to 5,000 calls per day; 4.17 million appeals handled over five years of operation.

Implementation Details

Implementation TypeClassical ML
Lifecycle StageIntegration and Deployment
Model ProvenanceCommercial/proprietary
Compute EnvironmentNot documented
Sovereignty QuadrantNot assessed
Data ResidencyNot documented
Cross-Border TransferNot documented

Agentic AI

Is AgenticPartial
PipelineSocial Bot autonomously handles ~69.8% of social media appeals with template-based responses; unresolved queries are escalated to human operators via the 142 Call Center. iDost autonomously directs users to appropriate e-services based on natural language input.
AutonomySemi-autonomous
Override PointsHuman operators handle queries the bot cannot address; clear escalation pathway from automated response to 142 Call Center staff; user feedback mechanism (star ratings) for continuous refinement.

Risk & Oversight

Decision CriticalityLow
Human OversightHITL
Development ProcessMix of in-house and third-party
Highest Risk CategoryOperational and system integration risks
Risk Assessment StatusNot assessed

Risk Dimensions

Data-related risks

Data quality failure

Governance and institutional oversight risks

Weak documentation or auditability

Market, sovereignty and industry structure risks

Opaque supply chainVendor lock-in

Model-related risks

Hallucination or misinformationReliability or generalisation failure

Operational and system integration risks

Inadequate real-world validationMonitoring gap

Impact Dimensions

Equality, non-discrimination, fairness and inclusion

Systematic exclusion from benefits or services

Privacy and data security

Loss of individual control over personal data

Systemic and societal

Deepened digital divide

Safeguards

Data minimisation controlsHuman oversight protocol

Deployment & Outcomes

Deployment StatusOperational Deployment (Limited Rollout)
Year Initiated2022
Scale / CoverageNational coverage across Azerbaijan (population ~10.2 million). 9.2 million people served since 2022. Up to 5,000 calls per day; ~7,100 daily calls; 812,589 applications in H1 2024.
Funding SourceGovernment of Azerbaijan (MLSPP budget)
Technical PartnersDOST Digital Innovations Center (Artificial Intelligence Application Division); local vendor for Chatbot (Social Bot) platform (procured via tender 2022-2023); 142 Call Center platform

Outcomes / Results

812,589 applications processed in H1 2024. Approximately 7,100 daily calls handled. ~69.8% of social media appeals handled automatically by the bot. 9.2 million people served since 2022. 91.5% of MLSPP's 160 services digitised. 56% of services operate via proactive mechanism. Over 250,889 individuals received proactive social payments in 2024. 4.17 million citizen appeals handled over five years.

Challenges

Specific AI architecture and analytics plans are still to be fully documented. The local vendor for the Social Bot platform has not been publicly identified. Detailed technical specifications of the NLP models and training data are not publicly available. The transition from template-based responses to more sophisticated AI-driven analytics for call data is still in progress.

Sources

  1. SRC-004-AZE-001 Azernews (2025) 'DOST Digital Innovation Center celebrates 3 years of driving social service transformation', azernews.az.
    https://www.azernews.az/business/235249.html
  2. SRC-003-AZE-001 DOST Agency (n.d.) 'All the call centers of the MLSPP are gathered under a single platform', dost.gov.az.
    https://dost.gov.az/en/news/544
  3. SRC-002-AZE-001 InterweaveGov (2025) 'An interview with Orkhan Salahov, Deputy Director of Azerbaijan's DOST Digital Innovations Centre', Substack.
    https://interweavegov.substack.com/p/an-interview-with-orkhan-salahov
  4. SRC-001-AZE-001 Ministry of Labour and Social Protection of Population (2026) 'AI-based "iDost" Digital Assistant Launched on the e-Social Platform', sosial.gov.az, 6 January 2026.
    https://sosial.gov.az/en/media/news/ai-based-idost-digital-assistant-launched-on-the-e-social-platform-8871
  5. SRC-005-AZE-001 MLSPP (n.d.) 'DOST Digital Innovation Center', sosial.gov.az.
    https://sosial.gov.az/en/ministry/dost-digital-innovation-center
  6. SRC-006-AZE-001 Zero Project (n.d.) 'e-government', zeroproject.org.
    https://zeroproject.org/view/project/668f2e5b-3e7d-4819-8ac2-91ed2f9a9f1b

How to Cite

DCI AI Hub (2026). 'Social Bot / iDost — AI-Enabled Chatbot and Call Center System for Social Protection Services', AI Hub AI Tracker, case AZE-001. Digital Convergence Initiative. Available at: https://socialprotectionai.org/use-case/AZE-001

Back to case page
AI Hub

Digital Convergence Initiative - AI Hub

Responsible, ethical use of AI in social protection

MarketImpact Platform developed by MarketImpact Digital Solutions
Co-funded by European Union and German Cooperation. Coordinated by GIZ, ILO, The World Bank, Expertise France, and FIAP.