Home / AGORA-AI
Private Sector
Stage 1, Stage 2

AGORA-AI

DOTSOFT
‹ Back to Open Call Winners
AGORA-AI is an evidence-grounded decision-support and what-if assistant for municipalities, built as a containerised AI layer on DOTSOFT's NOON-IoT smart-city platform. It combines a knowledge graph, hybrid similarity search, scenario modelling and retrieval-augmented generation to recommend ranked urban interventions with projected impact ranges, uncertainty and traceable sources. Stage 2 will replace non-EU model dependencies with European AIoD services, validate grounding and retrieval quality, support six EU languages, launch the product on the AIoD Marketplace and prepare a cross-border Stage 3 deployment with OPSIS in Romania.

Background

Municipalities and city-service operators must make costly, difficult-to-reverse decisions on mobility, energy, water and waste, often without in-house data-science expertise. Existing dashboards show what is happening but not which intervention is likely to work, while evidence from comparable cities is fragmented across studies and operational systems. Generic AI assistants lack access to live city data, contextual similarity and verifiable sources, making their recommendations unsuitable for accountable public decisions. This leads to slow, intuition-based choices, uncertain impact and avoidable spending.

Proposed solution

AGORA-AI is an evidence-grounded recommendation and what-if assistant for municipalities and city-service operators, delivered as a containerised AI layer on DOTSOFT’s NOON-IoT smart-city platform. A user describes an urban challenge in natural language, such as traffic congestion or excessive energy consumption. AGORA-AI searches a knowledge graph linking urban problems, interventions, city contexts and measured outcomes from peer-reviewed evidence and operational city data. Its hybrid similarity engine identifies genuinely comparable cases, while the scenario engine estimates likely impact ranges and explicitly communicates uncertainty. A European LLM, constrained through retrieval-augmented generation, produces ranked recommendations with traceable sources. The system does not make autonomous decisions: the administrator retains full authority. Built on NGSI-LD, FIWARE and open APIs, AGORA-AI is portable, interoperable and suitable for accountable public-sector use.

Objectives

  • Replace non-EU LLM and embedding dependencies with European AIoD model services.
  • Establish repeatable grounding and retrieval-quality evaluation using CoverRAGBench.
  • Validate multilingual operation across six EU languages.
  • Launch AGORA-AI and its subscription model on the Marketplace and Business Navigator.
  • Beta-test the selected AIoD components and provide structured technical feedback.
  • Formalise OPSIS as the Stage 3 AI Adopter and prepare the cross-border Romanian deployment.

DOTSOFT

Greece
Thessaloniki-based DOTSOFT S.A. specializes in smart-city solutions, digital transformation, and AI applications for public and private sectors. Combining AI/ML, knowledge graphs, and FIWARE interoperability, its flagship NOON-IoT platform powers evidence-based urban management across 30+ municipalities while driving active European R&D initiatives.
Stay informed on AI opportunities
Get updates on new solutions, market trends, and adoption strategies delivered to your inbox.
The DeployAI project has received funding from the Digital Europe Programme (DIGITAL) under grant agreement №. 101146490 - DIGITAL-2022-CLOUD-AI-B-03
Stay informed on AI opportunities
Get updates on new solutions, market trends, and adoption strategies delivered to your inbox.
The DeployAI project has received funding from the Digital Europe Programme (DIGITAL) under grant agreement №. 101146490 - DIGITAL-2022-CLOUD-AI-B-03