Max Agency

← Max Agency23 Apr · 48 min

How Listen is building a system of AI Agents & subagents for specialized tasks | Florian Juengermann, CTO

How Listen is building a system of AI Agents & subagents for specialized tasks | Florian Juengermann, CTO23 Apr48 min

<p>Florian Juengermann is the co-founder and CTO of Listen, an AI startup that turns qualitative research across hundreds of interviews, surveys, and focus groups into structured, traceable insights. Listen&#39;s agents analyze responses at scale, and Florian has rearchitected the system multiple times to get there. In this conversation, he walks through the virtual table architecture at the core of their Research Agent, how small models run map-reduce classification across thousands of open-ended responses, and the self-reviewing feedback subagent that catches errors during long async runs.</p><p><br></p><p><strong>We also discuss:</strong></p><ul><li>The three agents inside Listen&#39;s platform</li><li>How Listen rearchitected from a simple RAG bot to a multi-agent system multiple times</li><li>Why the PowerPoint subagent was completely rebuilt using Claude&#39;s code SDK</li><li>Contextual prompt engineering as an alternative to skills</li><li>How Listen keeps report numbers live as new interview responses come in</li><li>When to trigger the long-running agent vs. showing early results</li><li>What Florian looks for when hiring agent engineers</li></ul><p><br></p><p><strong>References:</strong></p><ul><li><a href="https://www.anthropic.com/" target="_blank" rel="ugc noopener noreferrer">Anthropic</a></li><li><a href="https://chatgpt.com/" target="_blank" rel="ugc noopener noreferrer">ChatGPT</a></li><li><a href="https://claude.ai/" target="_blank" rel="ugc noopener noreferrer">Claude</a></li><li><a href="https://docs.anthropic.com/en/docs/claude-code/sdk" target="_blank" rel="ugc noopener noreferrer">Claude Code SDK</a></li><li><a href="https://e2b.dev/" target="_blank" rel="ugc noopener noreferrer">E2B</a></li><li><a href="https://listenlabs.ai/features/emotional-intelligence" target="_blank" rel="ugc noopener noreferrer">Emotional Intelligence</a></li><li><a href="https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/" target="_blank" rel="ugc noopener noreferrer">GPT Mini</a></li><li><a href="https://www.anthropic.com/claude/haiku" target="_blank" rel="ugc noopener noreferrer">Haiku</a></li><li><a href="https://listenlabs.ai/" target="_blank" rel="ugc noopener noreferrer">Listen</a></li><li><a href="https://openai.com/" target="_blank" rel="ugc noopener noreferrer">OpenAI</a></li><li><a href="https://pandas.pydata.org/" target="_blank" rel="ugc noopener noreferrer">Pandas</a></li><li><a href="https://www.postgresql.org/" target="_blank" rel="ugc noopener noreferrer">Postgres</a></li><li><a href="https://www.python.org/" target="_blank" rel="ugc noopener noreferrer">Python</a></li><li><a href="https://listenlabs.ai/features/research-agent" target="_blank" rel="ugc noopener noreferrer">Research Agent</a></li><li><a href="https://render.com/" target="_blank" rel="ugc noopener noreferrer">Render</a></li><li><a href="https://zoom.us/" target="_blank" rel="ugc noopener noreferrer">Zoom</a></li></ul><p><br></p><p><strong>Where to find Florian:</strong></p><ul><li><a href="https://www.linkedin.com/in/juengermann/" target="_blank" rel="ugc noopener noreferrer">LinkedIn</a></li><li><a href="https://x.com/florian_jue" target="_blank" rel="ugc noopener noreferrer">Twitter/X</a></li></ul><p><br></p><p><strong>Where to find Harrison:</strong></p><ul><li><a href="https://www.linkedin.com/in/harrison-chase-961287118/" target="_blank" rel="ugc noopener noreferrer">LinkedIn</a></li><li><a href="https://x.com/hwchase17" target="_blank" rel="ugc noopener noreferrer">Twitter/X</a></li></ul><p><br></p><p><strong>Where to find LangChain:</strong></p><ul><li><a href="http://langchain.com" target="_blank" rel="ugc noopener noreferrer">Website</a></li><li><a href="https://docs.langchain.com/" target="_blank" rel="ugc noopener noreferrer">Docs</a></li><p><br></p></ul><p>Send feedback or questions to maxagency@langchain.dev</p><p><br></p><p><strong>Timestamps</strong></p><p>(00:00) Introduction</p><p>(01:25) The three agents i