IND-004

CPGRAMS AI-Assisted Complaint Triage and Routing with IGMS 2.0 Analytics

Download PDF
India South Asia Lower middle income Scaled & Institutionalised Confirmed

Department of Administrative Reforms and Public Grievances (DARPG), Ministry of Personnel, Public Grievances and Pensions; National Informatics Centre (NIC) as hosting and development partner.

At a Glance

What it does Classification — Operational and process automation
Who runs it Department of Administrative Reforms and Public Grievances (DARPG), Ministry of Personnel, Public Grievances and Pensions; National Informatics Centre (NIC) as hosting and development partner.
Programme Centralised Public Grievance Redress and Monitoring System (CPGRAMS)
Confidence Confirmed
Deployment Status Scaled & Institutionalised
Key Risks Governance and institutional oversight risks
Key Outcomes Average disposal time reduced from 32 days (2021) to 18 days (2023) to 12 days (2024), approximately 63% reduction over three years.
Source Quality 7 sources — Government website / press release, Report (multilateral / development partner)

The Centralised Public Grievance Redress and Monitoring System (CPGRAMS) is the Government of India's primary digital platform for citizens to lodge, track, and monitor grievances against central ministries, departments, state governments, and other public authorities. Operated by the Department of Administrative Reforms and Public Grievances (DARPG) under the Ministry of Personnel, Public Grievances and Pensions, and hosted and developed by the National Informatics Centre (NIC), the system has been progressively enhanced with artificial intelligence and machine learning capabilities since 2021. CPGRAMS currently interlinks 91 central ministries and departments and 36 states and union territories, with over 74,000 registered government users processing approximately 20 lakh (2 million) grievances annually. Between 2020 and 2024, the system handled over 11.2 million grievances in total, making it one of the largest public grievance redressal platforms globally. The system received international recognition as a advanced grievance redressal system at the Commonwealth conference in London in April 2024.

The AI and machine learning integration within CPGRAMS operates through two interconnected components. The first is CPGRAMS version 7.0, which introduced auto-routing functionality to direct grievances automatically to field-level offices at the last mile, using a questionnaire-guided registration process with dropdown menu-based filing. The second is the Intelligent Grievance Management System (IGMS), developed through a formal memorandum of understanding signed between DARPG and the Indian Institute of Technology Kanpur (IIT Kanpur) on 14 December 2021. The IGMS was developed by a team at IIT Kanpur's Centre for Data and Information Sciences (CDIS), led by Professor Shalabh from the Department of Mathematics and Statistics (also Dean of Academic Affairs) and Professor Nisheeth Srivastava from the Department of Computer Science and Engineering, along with student researchers. The upgraded version, IGMS 2.0, was launched on 29 September 2023 by Dr Jitendra Singh, Union Minister of State (Independent Charge) for Science and Technology.

The IGMS performs four core AI-driven functions within the CPGRAMS ecosystem. First, it provides automated spam detection, identifying and filtering spam, bulk, and repetitive grievances in real time. Second, it conducts semantic content analysis using natural language processing to extract the gist of grievances by analysing their text contents and PDF attachments, effectively performing automated topic identification without requiring manual review. Third, it performs issue clustering to identify recurring complaint patterns across departments and policy areas, enabling root cause identification. Fourth, it provides spatiotemporal filtering capabilities that allow officials to track policy and implementation-level issues by location and time period. The IGMS dashboard provides instant tabular analysis of grievances filed and disposed, with state-wise, district-wise, and ministry-wise breakdowns. It also generates automated draft letters for selected schemes and ministries to expedite the grievance redressal process.

The system also includes urgent grievance flagging capabilities. Grievances of an urgent nature are mapped on the CPGRAMS platform with system specifications and flagged to all Nodal Officers and Grievance Redressal Officers (GROs). This AI-driven urgent flagging is part of the ten-step CPGRAMS reform programme that also includes the universalisation of CPGRAMS 7.0 for auto-routing of grievances to the last mile. In addition, DARPG has issued a procurement notice to further modernise the platform with enhanced AI capabilities, including improved natural language processing to understand informal multilingual complaints across India's 22 scheduled languages plus English, voice AI for citizens with limited literacy, and predictive analytics to detect systemic issues and anticipate complaint surges.

The regulatory framework governing CPGRAMS operations was strengthened through a comprehensive Office Memorandum issued by DARPG on 23 August 2024, which reduced the maximum advised resolution time from 30 days to 21 days for original grievances, with a 3-day target for urgent or priority cases. Appeals against disposed grievances must be handled within 30 days by designated Appellate Authorities at the Additional or Joint Secretary rank. The OM mandates that grievances cannot be closed by stating that the matter does not pertain to the receiving ministry or department; instead, efforts must be made to transfer the grievance to the correct authority. An appeal mechanism was operationalised on 21 January 2021, enabling citizens to escalate unsatisfied grievances through designated Nodal Appellate Authorities.

The human oversight model follows a human-in-the-loop paradigm. GROs review and act on AI-assisted triage recommendations, with appeals and escalations handled by officials according to the guidelines established in the August 2024 Office Memorandum. The AI system classifies, prioritises, and routes grievances, but substantive decisions on grievance resolution remain with human officials. Auto-escalation timelines ensure that unresolved grievances are automatically flagged for higher-level review. Performance monitoring is conducted through the Grievance Redressal Assessment Index (GRAI), which provides monthly rankings of ministries and departments across efficiency, feedback, domain, and organisational commitment dimensions. Analytics dashboards are accessible at treedashboard.in and dashboard-pmopg.nic.in. The 2023 GRAI assessment showed that 85 of 89 ministries and departments achieved enhanced resolution rates compared to the previous year.

In terms of measurable impact, the average disposal time for central ministries and departments decreased from 32 days in 2021 to 18 days in 2023, representing a reduction of approximately 44 percent. By 2024, the average resolution time had further decreased to 12 days, with over 24 lakh grievances received and a 98 percent resolution rate achieved. The system is available through the CPGRAMS web portal, native mobile apps on Android and iOS, the My Grievance application, and integration with the UMANG (Unified Mobile Application for New-age Governance) platform. Citizens can also lodge grievances via WhatsApp and feedback call centres.

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

Social Protection Functions

Implementation/delivery chain
Accountability mechanisms primaryMonitoring and evaluation
SP Pillar (Primary) The social protection branch: social assistance, social insurance, or labour market programmes. Social assistance
Programme Name Centralised Public Grievance Redress and Monitoring System (CPGRAMS)
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 National online platform for citizens to lodge, track, and monitor public grievances against central ministries, departments, state governments, and public authorities, operated by DARPG and hosted by NIC. Processes approximately 20 lakh grievances annually, interlinking 91 central ministries/departments and 36 states/UTs.
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 Adapted from open-source
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
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 Moderate
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 Governance and institutional oversight risks
Risk Assessment Status Whether a formal risk assessment, informal assessment, or independent audit has been conducted for this system. Informal assessment

Risk Dimensions

Governance and institutional oversight risks

Impact Dimensions

Equality, non-discrimination, fairness and inclusion
  • Grievance mechanism
  • Human oversight protocol
CategorySensitivityCross-System LinkageAvailabilityKey Constraints
Beneficiary registries and MISPersonalLinks data across multiple systemsCurrently available and usedCPGRAMS operational data on grievance filing, routing, disposal, and appeal across 91 central ministries/departments and 36 states/UTs; used for GRAI performance monitoring and IGMS analytics dashboards
Unstructured and text-based contentPersonalSingle source (no linkage)Currently available and usedCitizen-submitted grievance text and PDF attachments in 22+ languages; semantic gist extraction and topic clustering performed by IGMS NLP models

DARPG (2024) 'Comprehensive guidelines for handling the Public Grievances - Revised/Reiterated vide DARPG OM dated 23.08.2024', as reported by StaffNews, September 2024. Available at: https://www.staffnews.in/2024/09/comprehensive-guidelines-for-handling-the-public-grievances.html (Accessed: 23 March 2026).

View source Government website / press release

DARPG (2025) 'Public Grievances', Department of Administrative Reforms and Public Grievances website. New Delhi: Government of India. Available at: https://darpg.gov.in/public-grievances (Accessed: 23 March 2026).

View source Government website / press release

Indian Institute of Technology Kanpur (2023) 'Dr. Jitendra Singh launches Intelligent Grievance Monitoring System (IGMS) 2.0 implemented by IIT Kanpur team', News, 3 October. Kanpur: IIT Kanpur. Available at: https://iitk.ac.in/intelligent-grievance-monitoring-system-igms (Accessed: 23 March 2026).

View source Government website / press release

IIT Kanpur Centre for Data and Information Sciences (2023) 'IGMS 2.0, Developed by CDIS, Launched by Union Minister', CDIS Blog. Kanpur: IIT Kanpur. Available at: https://iitk.ac.in/cdis/blog/igms2/ (Accessed: 23 March 2026).

View source Government website / press release

Press Information Bureau (2023) 'Dr Jitendra Singh launches the Intelligent Grievance Monitoring System (IGMS) 2.0 Public Grievance portal and Automated Analysis in Tree Dashboard portal of DARPG', Press Release PRID 1962142, 29 September. New Delhi: Government of India. Available at: https://www.pib.gov.in/PressReleaseIframePage.aspx?PRID=1962142 (Accessed: 23 March 2026).

View source Government website / press release

Press Information Bureau (2024) 'Year End Review - Department of Administrative Reforms and Public Grievances - 2024', Press Release PRID 2088575. New Delhi: Government of India. Available at: https://www.pib.gov.in/PressReleasePage.aspx?PRID=2088575 (Accessed: 23 March 2026).

View source Government website / press release

World Bank (2025) 'CIVIC: Amplifying citizens' voice through AI-powered grievance redress systems', Governance Blog, June 2025. Washington, DC: World Bank Group. Available at: https://blogs.worldbank.org/en/governance/civic--amplifying-citizens--voice-through-ai-powered-grievance-r (Accessed: 23 March 2026).

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 Scaled & Institutionalised
Year Initiated The year the AI system was first initiated or development began. 2021
Scale / Coverage The scale and geographic or population coverage of the deployment. National — 91 central ministries/departments, 36 states/UTs, 74,000+ registered users, ~20 lakh grievances annually, 11.2 million grievances processed 2020-2024
Funding Source The source(s) of funding for the AI system development and deployment. Government of India (DARPG/NIC budgets); MoU-based collaboration with IIT Kanpur for IGMS development
Technical Partners External technology vendors, academic partners, or development partners involved. IIT Kanpur Centre for Data and Information Sciences (CDIS) — developed IGMS/IGMS 2.0 under MoU signed 14 December 2021; Professor Shalabh (Mathematics & Statistics) and Professor Nisheeth Srivastava (Computer Science & Engineering) led the development team.
Outcomes / Results Average disposal time reduced from 32 days (2021) to 18 days (2023) to 12 days (2024), approximately 63% reduction over three years. 98% resolution rate in 2024 with over 24 lakh grievances received. 85 of 89 ministries/departments achieved enhanced resolution rates in 2023 GRAI assessment. Maximum advised resolution time reduced from 30 to 21 days per DARPG OM dated 23 August 2024. System recognised at Commonwealth conference (London, April 2024) as state-of-the-art grievance redressal system.

How to Cite

DCI AI Hub (2026). 'CPGRAMS AI-Assisted Complaint Triage and Routing with IGMS 2.0 Analytics', AI Hub AI Tracker, case IND-004. Digital Convergence Initiative. Available at: https://socialprotectionai.org/use-case/IND-004 [Accessed: 1 April 2026].

Change History

Created 30 Mar 2026, 08:40
by v2-import (import)