Speaker

Marjia Siddik

Marjia Siddik

Co-Founder & CEO at Safentic

Dublin, Ireland

Actions

Marjia Siddik is the co-founder and CEO of Safentic, a runtime enforcement layer for multi-agent systems. She is a published AI safety researcher with experience in national and international AI policy initiatives, and is the youngest Microsoft MVP in the field of Trustworthy AI. Her work has been recognised through over 15 academic and industry scholarships.

Area of Expertise

  • Information & Communications Technology

Topics

  • Artificial Intelligence
  • Democratized Artificial Intelligence
  • Ethical AI
  • Ethics in AI
  • AI Ethics

Runtime Safety for Autonomous Agents with Azure AI

As AI agents gain autonomy and access to tools, traditional prompt and output filters no longer provide sufficient safeguards. Many risks emerge between an agent’s decision and its execution, especially in multi-agent systems where behaviour becomes harder to predict.

This talk introduces a Python-based runtime enforcement layer for LLM agents that works with Azure OpenAI, LangChain, and Microsoft AutoGen. The system enables real-time policy checks, logging, and blocking of unsafe tool calls, without modifying the agent’s core logic. It can be deployed via Azure Functions for lightweight runtime control and integrates with the Model Context Protocol (MCP) for traceability.

I will cover:

Where runtime risks emerge in agent behaviour

How to intercept and enforce policy at runtime

Python-based enforcement examples using Azure AI

What MCP enables for multi-agent oversight and debugging

Lessons from early deployments and open safety questions

This session is designed for developers and engineers building autonomous or multi-agent systems who aim to enhance runtime safety and operational visibility.

Keeping AI Agents in Check: Runtime Safety for Autonomous Systems

As AI agents gain autonomy and start interacting in complex ways, traditional input and output filters fall short. Many risks arise between the time an agent decides on an action and when it executes that action. This is especially true in multi-agent systems, where coordination becomes increasingly difficult to predict.

This talk introduces a Python-based runtime safety layer for LLM agents built with frameworks like LangChain and Microsoft AutoGen. The layer enables real-time monitoring, policy checks, and intervention without modifying the agent’s core logic.

The system also supports interoperability through the Model Context Protocol (MCP), which tracks agent decisions across tools and execution steps.

I will cover:

1. How multi-agent systems introduce new risks

2. What runtime enforcement enables beyond static filtering

3. Examples of real-time oversight using Python-based tools

4. How MCP supports debugging and traceability

5. Key lessons and open challenges in agent safety

This session is designed for developers, engineers, and researchers working with AI agents who want to build more reliable and aligned systems.

Addressing Algorithmic Bias: Fostering Fair and Inclusive Healthcare

The integration of AI algorithms into healthcare has revolutionized patient care, with the potential to improve diagnosis, treatment, and overall health outcomes. However, this transformative technology also introduces the risk of algorithmic bias, which can have detrimental consequences for patients and perpetuate existing health disparities.

What will be discussed:

- The dangers of algorithmic bias in healthcare, i.e. how bias can infiltrate AI algorithms and lead to unfair treatment of marginalized groups.

- How bias can arise from data collection to algorithm implementation, and how it can distort healthcare decisions and lead to disparities in care for diverse patients.

- Illustrate real-world implications of algorithmic bias in healthcare.

What the audience will learn:

- The significance of algorithmic bias in healthcare and its potential to harm patients.

- The dangers of biased AI algorithms, including misdiagnosis, delayed treatment, and poorer health outcomes for marginalized groups.

- The various ways in which bias can arise in healthcare algorithms, from data imbalances to flawed evaluation metrics.

Key Takeaways:

- Develop a comprehensive understanding of algorithmic bias in healthcare.

- Identify the potential sources of bias in AI algorithms.

- Become an advocate for responsible AI development and contribute to a healthier, more equitable future for all.

Addressing Algorithmic Bias: Fostering Fair and Inclusive Healthcare

The integration of AI into healthcare holds both promise and peril. While AI algorithms can improve diagnosis and treatment, they also risk perpetuating existing health disparities if biases aren't addressed.

This talk will explore:

The dangers of algorithmic bias, include misdiagnosis, delayed treatment, and poorer health outcomes for marginalized groups.

How bias can creep in at every stage of AI development, from flawed data to the metrics used for evaluation.

Real-world examples demonstrate the urgent need for change.

A potential solution: Althical, a platform that puts physicians at the center of AI development to create bias-reducing and explainable solutions.

DevFest Ireland 2025 Sessionize Event Upcoming

December 2025 Portlaoise, Ireland

Global Azure & AI Community Day User group Sessionize Event

October 2025 Dublin, Ireland

Impact the Future (IWD- 2024) Sessionize Event

April 2024 Dublin, Ireland

Women Techmakers Belfast 2024 Sessionize Event

March 2024 Belfast, United Kingdom

Marjia Siddik

Co-Founder & CEO at Safentic

Dublin, Ireland

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top