DoT and ITU Organise AI for Good Build-a-thon 5.0 to Develop Policy-Compliant AI Solutions for 5G

Ø  Dr. Bilel Jamoussi, Deputy Director and Chief, Study Groups and Policy Department, Telecommunication Standardization Bureau, ITU inaugurates the Build-a-thon 5.0 in the august presence of senior DoT leadership and distinguished experts

Ø  Build-a-thon 5.0 focuses on building Agentic AI solutions complied with Indian policies in the domain of telecommunications

·         The Department of Telecommunications (DoT) and the International Telecommunication Union (ITU) jointly organised AI for Good Build-a-thon 5.0 at India Mobile Congress 2026 at Yashobhoomi, New Delhi.

·         The event, themed “Creating Innovative Agents in 5G,” focused on developing Agentic AI solutions for telecommunications that comply with Indian policies and international standards.

·         More than 25 teams registered for the programme, and five online mentoring sessions provided over 10 hours of expert guidance, resulting in 16 AI prototype submissions.

·         The prototypes covered multi-agent network analysis, telecom policy compliance, traffic management, cybersecurity, automated network troubleshooting and regulatory gap identification.

·         First prize: Team Netaxis, RVCE Bangalore, for its AI-based 5G quality-of-service orchestration and adaptive security solution.

·         Second prize: Team SNR, for its knowledge-grounded retrieval and multi-agent arbitration solution.

·         Third prize: Team Agentnet, for its multi-agent framework for automated private 5G network troubleshooting.

·         Special women’s prizes were awarded to Team Orbitflow (SNU Chennai) and Team Handshake Protocol. The judges’ prize went to Team Nethealers for its autonomous self-healing 5G network solution.

·         The initiative highlighted India’s potential to advance AI-driven telecommunications, secure 5G networks and responsible innovation aligned with Indian laws and global standards.

 

[ABS News Service/15.10.2026]

The Department of Telecommunications (DoT), Ministry of Communications, Government of India, in collaboration with the International Telecommunication Union (ITU), organised the Artificial Intelligence (AI) for Good Build-a-thon 5.0, a hands-on capacity-building event that brought together teams from across the country to develop Agentic AI solutions for the telecommunications sector on the last day of India Mobile Congress (IMC) 2026 at Yashobhoomi, New Delhi.

The event, themed “Creating innovative agents in 5G”, was inaugurated by Dr. Bilel Jamoussi, Deputy Director and Chief, Study Groups and Policy Department, Telecommunication Standardization Bureau, ITU, in the august presence of senior DoT leadership and distinguished representatives from academia, industry, international organisations and the technology ecosystem.

Addressing the gathering, Dr. Jamoussi underscored the importance of Agentic AI solutions that are contextualized to the country, compliant with international standards and governed by local policies. He stressed that, to fully realize the benefits of integrating AI into workflows, policy gaps must be identified through real AI solutions and then addressed in regulation.

Strong leadership from Shri Prabhat Dikshit, DDG(Satellite) and Shri Bishnu Dubey, Director (AS-II), DoT along with support from C-DoT and the organizing teams was critical for the success of this event. The judges panel also included Shri Amit Shrivastava, DDG(MT), TEC, Dr. Brajesh Mishra, Executive Director, C-DoT and Shri Prachish Khanna, DDG(Media), DoT.

From Kick-off to Prototypes

The Build-a-thon 5.0 opened in early July with more than 25 registered teams, each with an average of four members. During the preparation phase, ITU and DoT experts held five online mentoring sessions covering the Build-a-thon problem statements, the ITU-T Y.3172 standardized machine learning pipeline, the ITU AI Readiness 2.0 report (a global benchmark for AI Ready use cases) and open-source data sources.

More than 10 hours of mentoring resulted in 16 well-designed AI prototype submissions. The entries featured a range of agent types, including knowledge-base agents that solve domain-specific problems, policy and legal adviser agents that play an institutional role within the solution, and coordinator agents that orchestrate multiple agents.

Standout Solutions

Several submissions distinguished themselves:

·         Multi-agent network analysis with policy mapping: One solution combines a country-specific 5G/telecom knowledge base with multi-agent AI analysis, progressive network-error scenarios, policy and standards mapping, gap identification, human supervision and auditable evidence.

·         Unified traffic and security controller: Another proposes an AI agent-based controller that manages traffic priority and security together, based on three inputs: service intent, available network resources and data sensitivity.

·         Law inside the control loop: A third embeds regulation directly into network operations. Three optimizer agents (Spectrum, Energy and Slicing) propose actions, while a Regulator agent with veto power checks each against ten rules grounded in Indian telecom law, citing the official text. A Policy & Legal Adviser answers questions drawn from 16 official documents, and a gap analyzer reports where Indian law is silent.

Judges noted the energy and dedication of the participating teams, and lively discussions took place between judges and teams during the interaction session. Presentations clearly set out each use case’s problem statement and its mapping against policy, standards and global benchmarks, and were accompanied by live demonstrations showing concrete evidence, including error scenarios and policy gaps.

The engaging session wrapped up with an exciting prize distribution by ITU and DoT dignitaries.

The 1st prize went to Team Netaxis, RVCE Bangalore, for “Context Aware Agentic Orchestration of QoS and Adaptive Security in Resource Constrained 5G”.

The 2nd prize was presented to Team SNR, for “knowledge-grounded retrieval, deterministic constraint validation and multi-agent arbitration”.

The 3rd prize went to team Agentnet for “TeleAgent: Collaborative Multi Agent Framework Using a Fine Tuned Small Language model for Automated Private 5G Network Troubleshooting”.

A special women’s prize was awarded to team Orbitflow (SNU Chennai) & team Handshake protocol for “Predictive Traffic-aware Beam Hopping for LEO Non-Terrestrial Networks” and “Law-aware AI agents for 5G emergency response”.

Lastly, the judges’ prize was presented to team Nethealers for “Autonomous Self-Healing 5G Radio Access Network Agent with Foundation-Model Diagnosis and Digital-Twin Pre-Validation”.

Build-a-thon 5.0 demonstrates India’s strong potential to lead in AI solutions for the telecommunications domain and in the policy design that governs them.