Just Now Possible Building AI Coworkers: How Neople Is Making Agents Work Where You Work
14 snips
Oct 16, 2025 In this chat, Seyna Diop, Chief Product Officer at Neople, and Job Nijenhuis, CTO and co-founder, dive deep into the world of AI digital coworkers. They talk about Neople's innovative approach to building personified AI agents tailored for customer service. Seyna shares fascinating use cases, from handling repetitive tickets to invoicing help. Job discusses the evolution of their technology, moving from simple suggestions to complex automations. They highlight the importance of customer feedback in ensuring quality and building trust with their AI solutions.
AI Snips
Chapters
Transcript
Episode notes
Start With Suggestions, Then Automate
- Start with suggestions to agents before full automation to regain reliability with improving models.
- Use suggestion telemetry to learn where automation is safe and where guardrails are required.
Code Plus Agentic LLMs
- Neople evolved from single-prompt LLM usage to modular agentic workflows with fixed guardrails.
- They blend deterministic code for data gathering with agentic LLM steps where flexible reasoning is needed.
Separate Data Gathering From LLM Reasoning
- Use deterministic code to gather ticket context and LLM agents only for retrieval and answer composition.
- Always run automated LLM evaluations before sending customer-facing replies to prevent hallucinations.