Human–Computer Interaction
[Open soon]
Work description
The aim of the grant is to investigate, develop and validate an architecture of conversational agents, with orchestration mechanisms and guardrails, for natural language interaction with the DFence system. The work will focus on the design of specialised agents to answer producers’ questions, explain KPIs and grazing plans, simulate and propose changes to plans, and validate the safety of interactions. Mechanisms for control, explainability, traceability, authorisation and the prevention of inappropriate responses or actions will be studied, with a view to ensuring human-AI interaction that is safe, transparent and aligned with objectives of animal welfare, agro-environmental sustainability and decision support. Specifically, the main activities to be carried out by the grant holder are: • To study conversational agent architectures applied to decision support systems, with a focus on human-AI interaction, explainability, security and safety measures. • To define use cases for natural language interaction within the DFence context, including data querying, explanation of KPIs, explanation of grazing plans, simulation of changes and generation of recommendations. • Design a multi-agent architecture for interaction with the Decision Support System, including specialised agents for intention interpretation, context retrieval, explanation, plan modification and validation. • Develop guardrail mechanisms to ensure that the agent’s responses and proposals comply with restrictions regarding safety, animal welfare, agro-environmental sustainability, user permissions and traceability. • Create a functional prototype of a conversational agent that is integrated, or integrable, with DFence’s data and modules. • Evaluate the prototype using realistic scenarios, measuring response quality, perceived usefulness, clarity of explanations, detection rate of unsafe requests, robustness against ambiguous requests, and ability to support farmers’ decisions.
Academic Qualifications
- A degree in computer engineering, information systems or a related field;
Minimum profile required
- A bachelor's degree with an average grade of over 12.
Preference factors
- Fluency in Portuguese. - Experience in computer vision techniques, specifically in self-service approaches focused on technology adoption issues. - Preference will be given to candidates with a master’s degree; candidates with a bachelor’s degree will only be considered if no master’s degree holders apply, or if those who do apply do not have the required background and/or the experience mentioned above.
Application Period
Since 14 May 2026 to 27 May 2026
[Open soon]
Centre
Industrial & Systems Engineering and Management