AZE-001

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

Download PDF
Azerbaijan Europe & Central Asia Upper middle income Operational Deployment (Limited Rollout) Likely

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

At a Glance

What it does Perception and extraction from unstructured inputs — User communication and interaction
Who runs it 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
Programme 142 Call Center and Social Bot / iDost Digital Assistant
Confidence Likely
Deployment Status Operational Deployment (Limited Rollout)
Key Risks Operational and system integration risks
Key Outcomes 812,589 applications processed in H1 2024.
Source Quality 6 sources — News article / media, Government website / press release, Interview / consultation, +1 more

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.

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

Social Protection Functions

Implementation/delivery chain
Outreach/communications/sensitisation primaryProvision of payments/services
SP Pillar (Primary) The social protection branch: social assistance, social insurance, or labour market programmes. Social insurance
SP Pillar (Secondary) The social protection branch: social assistance, social insurance, or labour market programmes. Social assistance
Programme Name 142 Call Center and Social Bot / iDost Digital Assistant
Programme Type The type of social protection programme, classified under social assistance, social insurance, or labour market programmes. View in glossary Other
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 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 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 Integration and Deployment
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. Social 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.
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 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.
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 HITL
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 Mix of in-house and third-party
Highest Risk Category The most significant structural risk source identified: data, model, operational, governance, or market/sovereignty risks. View in glossary Operational and system integration risks
Risk Assessment Status Whether a formal risk assessment, informal assessment, or independent audit has been conducted for this system. Not assessed

Risk Dimensions

Data-related risks
Governance and institutional oversight risks
Market, sovereignty and industry structure risks
Operational and system integration risks

Impact Dimensions

Equality, non-discrimination, fairness and inclusion
Systemic and societal
  • Data minimisation controls
  • Human oversight protocol
CategorySensitivityCross-System LinkageAvailabilityKey Constraints
Beneficiary registries and MISSensitiveLinks data across multiple systemsCurrently available and usedCEIS (Centralized Electronic Information System) integrates data across MLSPP subordinate bodies including State Social Protection Fund, Social Services Agency, State Employment Agency. Used to provide contextual information for citizen inquiries.
Unstructured and text-based contentPersonalLinks data across multiple systemsCurrently available and usedCall recordings since 2014 (millions of interactions), social media inquiries, citizen queries on pensions, disability, rehabilitation, employment, labour compliance and e-services. Data drawn from 80+ state and private institutions and 17 social registries via CEIS platform.

Azernews (2025) 'DOST Digital Innovation Center celebrates 3 years of driving social service transformation', azernews.az.

View source News article / media

DOST Agency (n.d.) 'All the call centers of the MLSPP are gathered under a single platform', dost.gov.az.

View source Government website / press release

InterweaveGov (2025) 'An interview with Orkhan Salahov, Deputy Director of Azerbaijan's DOST Digital Innovations Centre', Substack.

View source Interview / consultation

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.

View source Government website / press release

MLSPP (n.d.) 'DOST Digital Innovation Center', sosial.gov.az.

View source Government website / press release

Zero Project (n.d.) 'e-government', zeroproject.org.

View source Report (multilateral / development partner)
Deployment Status How far the system has progressed into real-world operational use, from concept/exploration through to scaled and institutionalised. View in glossary Operational Deployment (Limited Rollout)
Year Initiated The year the AI system was first initiated or development began. 2022
Scale / Coverage The scale and geographic or population coverage of the deployment. National 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 Source The source(s) of funding for the AI system development and deployment. Government of Azerbaijan (MLSPP budget)
Technical Partners External technology vendors, academic partners, or development partners involved. DOST 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.

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 [Accessed: 1 April 2026].

Change History

Updated 1 Apr 2026, 08:11
by system (system)
Created 30 Mar 2026, 08:38
by v2-import (import)