Building Autonomous Software Systems with AI Agents and Telemetry
Details
Join our session to explore how AI agents are enabling software systems that can detect, diagnose, and fix their own bugs autonomously. This event features two technical talks that demonstrate how combining telemetry data with agentic AI creates self-healing applications that resolve issues before they impact users.
Boris Paskalev from LogicStar will demonstrate how AI agents can automatically detect production bugs, reproduce them, and generate validated pull requests with fixes, thereby removing human bottlenecks from the debugging cycle. Lazar Kanelov will demonstrate how high-quality telemetry data powers AI-driven incident response, creating adaptive feedback loops where agents interpret system signals, identify root causes, and apply automated remediation.
Whether you're an engineering leader exploring autonomous systems or building with AI agents, this session will give you practical insights into the architecture and techniques behind self-healing software that fixes itself in production.
Autonomous Bug Fixing Through AI Agents That Detect, Reproduce, and Repair by Boris Paskalev
What if your software could fix its own bugs—before anyone even notices them? In this session, LogicStar co-founder Boris Paskalev shares how self-healing applications are becoming a reality—fixing bugs automatically, before they reach production or immediately after an issue is detected/reported.
LogicStar combines classical computer science, deep tech research from the pioneers of “AI for Code”, and Agentic AI to detect, reproduce, and fix real production issues with validated, test-backed pull requests. This session is for engineering leaders, PMs, and AI builders ready to rethink the boundaries of autonomy in software delivery.
About Speaker
Boris Paskalev is the co-founder and CEO of LogicStar, a company pioneering self-healing software that fixes itself. Previously, he co-founded DeepCode, acquired by Snyk, where he led the first commercial application of AI for code, scaling bug detection to millions of developers. His work focuses on removing human bottlenecks in software development through automation, deep tech, and applied AI.
Creating self-healing software systems via effective usage of telemetry data and AI agents by Lazar Kanelov
Modern software systems operate in complex, dynamic environments where failures are inevitable. Traditional monitoring and manual incident response are no longer sufficient to ensure resilience or customer satisfaction. This talk explores how to design and implement self-healing software systems by combining telemetry data with an AI-driven agentic approach.
We’ll start by examining how high-quality telemetry forms the foundation for detecting anomalies and predicting failures. Next, we’ll show how modern GenAI (LLMs) can transform this telemetry into actionable insights for AI agents that interpret data, pinpoint root causes, and apply automated fixes. Through a practical, real-world example, you’ll see how telemetry and AI work together to create adaptive feedback loops that continuously improve system reliability, while freeing engineers from repetitive operational tasks.
About Speaker
Lazar Kanelov is an engineering leader with deep expertise across the technical stack, from embedded systems and control theory to distributed enterprise architecture. As a researcher, technical lead, and software architect turned engineering manager, he builds high-performing teams and scalable engineering organisations. His work focuses on translating R&D innovation into systems that deliver measurable impact at scale.
Participation
This event will be streamed live on YouTube. Once registered, you’ll receive a link and calendar invite with YouTube Live details. You can view the live stream, participate in chat, or join Q&A. You will be able to access the event recording on our YouTube channel.
Social & Community