Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
LangChain Multi-Agent IT Automation
Explore a LangChain-based multi-agent architecture that integrates tools and graph knowledge retrieval to automate complex IT support and DevOps tasks, with live code demonstration.
This presentation showcases the power of AI-driven multi-agent systems to tackle complex IT challenges with minimal human intervention. From first-line support to intricate DevOps issues, our system integrates specialized tools, advanced context management, and graph-based knowledge retrieval to handle tasks traditionally requiring hours of manual effort. Dive into the architecture and strategies that make these systems transformative for IT operations, enabling faster, smarter, and more efficient problem-solving.
- LangChainThe open-source framework for building and deploying reliable, data-aware Large Language Model (LLM) applications.LangChain is the essential framework for engineering LLM-powered applications: it simplifies connecting models (like GPT-4 or Claude) to external data, computation, and APIs. The platform provides a modular set of components—Chains, Agents, Tools, and Memory—allowing developers to quickly build complex workflows like Retrieval-Augmented Generation (RAG) pipelines and sophisticated conversational agents. Its Python and JavaScript libraries, combined with LangChain Expression Language (LCEL), offer a standardized interface for rapid prototyping and moving applications to production with confidence.
- Knowledge GraphsA Knowledge Graph is a structured, semantic network: it connects real-world entities (nodes) with defined relationships (edges) to provide context and meaning for intelligent systems.Knowledge Graphs (KGs) are semantic networks that model data as a collection of subject-predicate-object triples, using nodes for entities (e.g., a person, a product) and labeled edges for their relationships (e.g., 'works at,' 'is a customer of'). This graph-based structure, often built on standards like RDF, enables machines to understand context and meaning, moving beyond simple keyword matching to entity-based reasoning. Major implementations include Google's Knowledge Graph, which contains billions of facts, and enterprise KGs used for complex data integration, fraud detection, and grounding Generative AI (GraphRAG) for more accurate, explainable results.
- Multi-Agent SystemsAutonomous AI teams (agents) that collaborate, coordinate, or compete to solve complex, large-scale problems; think distributed intelligence for maximum resilience and efficiency.Multi-Agent Systems (MAS) are computational architectures comprising multiple autonomous, interacting agents (software, LLMs, or robots) that distribute tasks to achieve a collective goal. This decentralized model is critical for tackling challenges too complex for a single AI: for example, a self-driving system uses separate agents for obstacle detection, mapping, and real-time decision-making. The core advantage is superior resilience and scalability; if one agent fails, the system maintains operations. MAS is actively deployed across logistics, finance, and healthcare, leveraging parallel execution to enhance decision-making and streamline complex workflows like supply chain negotiation.
- DevOpsDevOps is the cultural and professional movement that unifies software development (Dev) and IT operations (Ops) through automation, enabling rapid, continuous delivery.DevOps is a cultural shift: it breaks down traditional silos between Dev and Ops teams, fostering shared ownership and empathy across the entire application lifecycle. The core mechanism is automation, specifically through Continuous Integration and Continuous Delivery (CI/CD) pipelines. Teams leverage tools like Git for version control, Jenkins or GitLab for CI/CD orchestration, and containerization technologies (Docker, Kubernetes) for consistent environments. This integrated approach dramatically increases deployment frequency and velocity, reducing the Mean Time To Recover (MTTR) from outages and delivering higher-quality features to customers faster.
- IT OperationsIT Operations (ITOps) is the core function ensuring 99.99% uptime: it manages the entire IT infrastructure (servers, networks, cloud) to guarantee service delivery and business continuity, often leveraging AIOps for proactive incident management.IT Operations is the engine room of the digital enterprise, responsible for the day-to-day management of all critical technology infrastructure, from on-premise data centers to multi-cloud environments (AWS, Azure). Our mandate is simple: maintain maximum availability and performance. This involves rigorous system monitoring, incident response (targeting a 5-minute Mean Time to Resolution), security management, and capacity planning to handle peak loads. We implement the ITIL framework for process standardization, using ITSM platforms like Jira Service Management to manage tickets, changes, and assets. The shift to AIOps is key: we automate event correlation and triage to move from reactive firefighting to proactive problem resolution, securing the business's core digital services.
Related projects
Teachable AI Agents in Software Development
Poland
Learn how to build AI agents that continuously adapt to development workflows, using practical techniques and best practices…
Embedding agents into workflows – where do we start?
Poland
Learn practical steps to embed AI agents into existing workflows, focusing on automating reactive tasks and creating reliable,…
Agent Laboratory: Agentic AI Researcher
Prague
The session demonstrates an end‑to‑end autonomous workflow using specialized LLM agents to conduct literature reviews, design plans, run…
AI Agents working together on a Machine Learning Task
Milan
Watch three AI agents collaborate: a data engineer cleans raw data, a tech lead orchestrates, and a data…
Agents: Thinking Fast and Slow
Bengaluru
Learn how agents dynamically retrieve and structure context, use iterative and ontology‑guided reasoning, and orchestrate complex SaaS workflows…
Secure authentication for agent-to-agent interactions
Poland
Learn practical security protocols and authentication methods for safe, reliable communication between autonomous AI agents in distributed systems,…