Skip to main content

Creating a GitHub Issue Resolver AI Agent with Haystack

Bilge Yücel, a Developer Relations Engineer at deepset, demonstrates how to create an AI agent using the Haystack framework.
Jun 12, 2025
Code along with us onCode Along

AI agents are increasingly being used to automate repetitive tasks in software and data workflows, from triaging bugs to generating documentation. With frameworks like Haystack, engineers can build domain-specific agents that integrate seamlessly into their existing tools—boosting productivity and reducing manual overhead. For those looking to put AI to work in real development environments, this session offers a practical, hands-on starting point.

In this code-along interview webinar, Bilge Yücel, a Developer Relations Engineer at deepset, demonstrates how to create an AI agent using the Haystack framework. You’ll explore how to build a simple AI agent designed to automatically resolve GitHub issues, walk through a real-world case study, and learn how similar agents can be applied to streamline both software development and data science workflows. This session is ideal for AI and software engineers eager to bring intelligent automation into their daily work.

Key Takeaways:

  • Learn how to get started with the Haystack framework for building AI agents.
  • Discover how AI agents can be applied to automate GitHub issue resolution.
  • Understand how to integrate AI agents into broader software and data workflows.

Session Resources (including slides)

Topics
Related

Tutorial

Haystack AI Tutorial: Building Agentic Workflows

Learn how to use Haystack's dataclasses, components, document store, generator, retriever, pipeline, tools, and agents to build an agentic workflow that will help you invoke multiple tools based on user queries.
Abid Ali Awan's photo

Abid Ali Awan

8 min

Replit Agent: from idea to app

Tutorial

Replit Agent: A Guide With Practical Examples

Learn how to set up Replit Agent and discover how to use it through an example walkthrough and 10 real-world use cases.
Dr Ana Rojo-Echeburúa's photo

Dr Ana Rojo-Echeburúa

10 min

code-along

Building a Deep Research AI Multi-Agent with LlamaIndex

Laurie Voss, VP of Developer Relations at LlamaIndex, guides you through building a deep research AI multi-agent using LlamaIndex.
Laurie Voss's photo

Laurie Voss

code-along

Building NLP Applications with Hugging Face

Perform a variety of NLP tasks from sentiment analysis to clustering with Hugging Face, and build a bot that generates marketing copy for a fashion retailer.
Jacob Marquez's photo

Jacob Marquez

code-along

Using Open Source AI Models with Hugging Face

Deep dive into open source AI, explore the Hugging Face ecosystem, and build an automated image captioning system.
Alara Dirik's photo

Alara Dirik

code-along

Working with APIs in Python

Chris Ramakers, Developer Platform and Design System Engineering Manager at DataCamp, guides you through the process of building a simple bot using Python.
Chris Ramakers's photo

Chris Ramakers

See MoreSee More