Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Engineering AI Agents that Don’t Break

Avatar for Bilge Yücel Bilge Yücel
August 28, 2025
6

Engineering AI Agents that Don’t Break

Event link: https://luma.com/ftrqjbaa

AI agents are having a moment, but most of them are little more than fragile prototypes that break under pressure. Together, we’ll explore why agentic systems fail in practice, and how to fix that with real engineering principles. In this talk, you’ll learn how to build agents that are modular, observable, and ready for production. If you’re tired of LLM demos that don’t deliver, this talk is your blueprint for building agents that work.

Avatar for Bilge Yücel

Bilge Yücel

August 28, 2025
Tweet

Transcript

  1. Bilge Yucel Hello 👋 • Developer Relations Engineer at deepset

    • Istanbul → Berlin in/bilge-yucel @bilgeyucl
  2. Our Context Company Solving Custom AI challenges since 2018. HQ

    in Berlin and NYC. Backed by: Leading open source framework & commercial platforms for custom enterprise-grade AI Products Used by 70 Thought leaders
  3. What is an AI agent? An AI agent is an

    LLM-based system that autonomously pursues a goal by interacting with its environment using tools. Human LLM Call Environment Action Feedback Stop
  4. “Agent involves a lot more work than expected and 90%

    of it is pure engineering. Nothing really to do with LLM, but it is how to blend LLM into an agentic workflow that makes senseˮ - a Haystack community member
  5. Failure Reason 1 Too Much Trust, Too Little Design ❌

    No fallback plans ❌ Brittle prompts ❌ Too many tools ❌ No observability ❌ No guardrails
  6. Failure Reason 2 Wrong Use Case • You have complex,

    multi-step problems requiring diverse actions • Tasks involve multiple tools / sources • Goals are clear but the optimal path to achieve them isn't predetermined • When interactions can follow predictable patterns (e.g. Q&A • Tasks can be decomposed into clear steps • Stability, robustness and efficiency are prioritized over automation potential Agents for Reasoning, Pipelines for Defined Flow
  7. AI Workflows & Agents Designing for the right level of

    agentic behavior is a strategic choice Operational Risk Autonomy AI Agent Deterministic AI Workflow Variables, outputs, com plexity • You can decide how much “powerˮ to give • Balance of Performance vs. Speed vs. Costs • 🔐 Modularity
  8. • Open-source AI orchestration framework by deepset • Provides the

    tools that Python developers need to build real world, agentic AI systems with visibility and control • Building blocks: Components & Pipelines
  9. Haystack Agents User Request Agent LLM (e.g. OpenAI, Anthropic, Gemini)

    System Prompt Python Functions External APIs Haystack Components MCP Servers Generated Answer
  10. Practical Tips For Building Agents • Find the optimal level

    of autonomy. Have the control over your system. • Minimize tools. Each new tool adds failure risk. • Split agents. Donʼt make one agent do everything. Use planners, coders, fixers if needed. • Build ‘fatʼ tools. Encapsulate logic, retries, and fallback paths into the tool logic. • Build guardrails. Validate inputs, actions and outputs. • Log everything. Add tracing to every step, tool, and output. • Human-in-the-loop. Let people oversee and guide agents.
  11. Unbreakable AI Agents with Haystack Build a Tool-Calling Agent AI

    Guardrails: Content Moderation and Safety with Open Language Models Creating a Multi-Agent System with Haystack Trace and Evaluate RAG with Arize Phoenix DevOps Support Agent with Human in the Loop Build a GitHub Issue Resolver Agent Build a GitHub PR Creator Agent Building AI Agents with Haystack