How Listen builds AI Agents that review their own work | Florian Juengermann, CTO

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'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.

We also discuss:
• The three agents inside Listen's platform
• How Listen rearchitected from a simple RAG bot to a multi-agent system multiple times
• Why the PowerPoint subagent was completely rebuilt using Claude's code SDK
• Contextual prompt engineering as an alternative to skills
• How Listen keeps report numbers live as new interview responses come in
• When to trigger the long-running agent vs. showing early results
• What Florian looks for when hiring agent engineers

References:
• Anthropic: https://www.anthropic.com/
• ChatGPT: https://chatgpt.com/
• Claude: https://claude.ai/
• Claude Code SDK: https://docs.anthropic.com/en/docs/claude-code/sdk
• E2B: https://e2b.dev/
• Emotional Intelligence: https://listenlabs.ai/features/emotional-intelligence
• GPT Mini: https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/
• Haiku: https://www.anthropic.com/claude/haiku
• Listen: https://listenlabs.ai/
• OpenAI: https://openai.com/
• Pandas: https://pandas.pydata.org/
• Postgres: https://www.postgresql.org/
• Python: https://www.python.org/
• Research Agent: https://listenlabs.ai/features/research-agent
• Render: https://render.com/
• Zoom: https://zoom.us/

Where to find Florian:
• LinkedIn: https://www.linkedin.com/in/juengermann/
• Twitter/X: https://x.com/florian_jue

Where to find Harrison:
• LinkedIn: https://www.linkedin.com/in/harrison-chase-961287118/
• Twitter/X: https://x.com/hwchase17

Where to find LangChain:
• Website: http://langchain.com
• Docs: https://docs.langchain.com/

Send feedback or questions to maxagency@langchain.dev

Timestamps:
00:00 Introduction
01:25 The three agents inside Listen's platform
03:15 Live chat vs. long async runs, and how Listen tunes for each
05:33 Under the hood of the Research Agent
06:37 Listen's virtual table architecture
07:34 How small models classify thousands of open-ended responses
10:05 Running code in a sandbox: how E2B fits in
11:52 Why Listen rebuilt the PowerPoint subagent from scratch
14:11 Contextual prompt engineering instead of skills
16:32 The feedback subagent that reviews its own reports
18:14 How Listen runs evals in production
19:47 Unexpected ways users push the agent to its limits
21:42 How many times Listen has rearchitected, and why
24:59 Trace observability: depth over breadth
26:10 Lessons from running Claude Code SDK inside E2B
27:42 Memory: what's solved and what isn't
29:10 The Composer agent UX: co-editing a document with AI
35:50 How Listen keeps report numbers live as new responses come in
43:47 What Listen looks for when hiring agent engineers