Meet Rachel: the AI agent that phoned 3,000 pubs to price a pint

2026-03-20 · Source: Tech.eu - Tech.eu · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Intermediate, medium

Summary

AI engineer Matt Cortland developed "Rachel," a voice agent, to call over 3,000 pubs across Ireland during Paddy's weekend 2026 to collect current Guinness pint prices. This initiative, named the "Guinndex," addresses a 14-year data gap since Ireland's Central Statistics Office stopped tracking pint prices. Rachel, designed with a friendly Northern Irish accent using ElevenLabs and Twilio, successfully gathered over 1,000 verified prices, costing approximately €200. The project revealed a national average price of €5.95, with Dublin being the most expensive at €6.75 and Laois the cheapest at €5.38. The Guinndex aims to increase price transparency and potentially stabilize pint costs, now evolving into a crowdsourced platform at guinndex.ai for ongoing data collection.

Key takeaway

For AI engineers developing conversational agents, your focus should be on refining voice, accent, and personality to enhance believability and interaction efficiency. Prioritize concise scripts to minimize call duration and reduce suspicion, as demonstrated by Rachel's success in gathering over 1,000 data points. This approach can significantly improve data collection efficacy in real-world scenarios, even for nuanced tasks like price discovery.

Key insights

AI voice agents can efficiently collect real-world data, even in complex human interactions, to fill critical information gaps.

Principles

• Voice agent believability is critical for data collection.
• Iterative script refinement improves interaction efficiency.

Method

An AI voice agent, built with ElevenLabs and Twilio, called pubs using Google Maps API numbers. Claude AI extracted prices from call transcripts, creating a live, crowdsourced dataset.

In practice

• Use ElevenLabs for realistic voice agent synthesis.
• Integrate Twilio for scalable telephony operations.
• Employ Google Maps API for business contact data.

Topics

• AI Voice Agents
• Conversational AI
• Data Collection
• Market Analysis
• Crowdsourcing

Best for: Machine Learning Engineer, NLP Engineer, AI Engineer, Data Scientist, Entrepreneur

Related on AIssential

• Why Emotion Matters More Than Sound — Building production-grade voice AI agents requires overcoming significant application-layer challenges beyond basic LLM integration.
• Top 5 Benefits of AI Call Analysis — your workplace could be missing out — AI call analysis transforms phone conversations into structured data for comprehensive insights and operational improvements.
• Introducing voice finder — a new tool to quickly find the right voice for your app from over 600+ voices — Voice finder simplifies selecting appropriate voices for AI agents by centralizing search and filtering across diverse TTS models.
• Deep: How ElevenLabs built an AI User Research Voice Agent — AI voice agents can rapidly scale qualitative user research and significantly boost product activation and engagement.
• Grok Voice Think Fast 1.0: Build Voice AI Agents That Actually Think — Grok Voice Think Fast 1.0 integrates speech recognition, reasoning, and response into a single feedback loop for real-time, full-duplex voice AI.
• Issue #120 - Turn-based voice AI agents — Voice agents fall into turn-based (sequential) or streaming (overlapping) architectures, each with distinct trade-offs.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Tech.eu - Tech.eu.