Voice-Enabled Affordability Stress-Test Agent
Design an autonomous 'Market Advisor' agent using the OpenAI Agents SDK that performs affordability stress tests for different metros. The agent will analyze Zillow Observed Rent Index (ZORI), Zillow Home Value Index (ZHVI), and Redfin market temperature data (like inventory and price drops). You will integrate ElevenLabs to provide a high-quality, conversational voice interface that allows users to ask questions like 'How much would a 2% interest rate hike impact affordability in Austin?' The agent must identify rental-market anomalies where rent growth exceeds income growth or price drops are spiking unusually. By combining OpenAI's function-calling capabilities with real-world real estate metrics, the agent will simulate 'stress scenarios' (e.g., rising mortgage rates or unemployment) and communicate the impact via natural, synthesized speech. You will focus on building robust tools that fetch CSV data from Zillow and Redfin and calculate the housing cost burden for local residents.
What you are building
The core problem, expected build, and operating context for this challenge.
Design an autonomous 'Market Advisor' agent using the OpenAI Agents SDK that performs affordability stress tests for different metros. The agent will analyze Zillow Observed Rent Index (ZORI), Zillow Home Value Index (ZHVI), and Redfin market temperature data (like inventory and price drops). You will integrate ElevenLabs to provide a high-quality, conversational voice interface that allows users to ask questions like 'How much would a 2% interest rate hike impact affordability in Austin?' The agent must identify rental-market anomalies where rent growth exceeds income growth or price drops are spiking unusually. By combining OpenAI's function-calling capabilities with real-world real estate metrics, the agent will simulate 'stress scenarios' (e.g., rising mortgage rates or unemployment) and communicate the impact via natural, synthesized speech. You will focus on building robust tools that fetch CSV data from Zillow and Redfin and calculate the housing cost burden for local residents.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
ElevenLabs Integration
Verifies that the agent successfully sends text to ElevenLabs and receives an audio response.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Anomaly Detection Precision
Precision of the agent in identifying rental markets with >2 standard deviation growth. • target: 0.9 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Master the OpenAI Agents SDK for defining autonomous agents with specialized tool-calling logic
Implement ElevenLabs 'Conversational AI' or 'Text-to-Speech' endpoints to create an interactive voice UI
Design data pipelines to parse and aggregate large Redfin 'Data Center' CSV files containing inventory and price drop metrics
Apply statistical anomaly detection (e.g., Z-score or Isolation Forest) to Zillow rental data across different geographies
Build a mortgage payment calculator function that the agent can use to simulate affordability scenarios
Optimize agent prompts for 'expert advisor' persona while ensuring data-driven accuracy
How this agent runs
Evaluation is based on the agent's ability to accurately calculate housing cost burdens and the successful integration of the voice interface.
Challenge input
CSV data snippet from Zillow (ZHVI) and a target interest rate
ElevenLabs
AI voice synthesis platform
OpenAI
OpenAI AI model provider
Zed
High-performance code editor
Evaluated output
Float representing the monthly payment
- Verifies that the agent successfully sends text to ElevenLabs and receives an audio response.
- Precision of the agent in identifying rental markets with >2 standard deviation growth. • target: 0.9 • ran...
- Anomaly Detection Precision target: 0.9
- 1 public reference case
- Python execution harness
View technical recipe
Configured tools
- ElevenLabs · Required
- OpenAI · Optional
- Zed · Optional
Evaluation contract
- ElevenLabs Integration · Weight 1
- Anomaly Detection Precision · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.
Run this agent on your dataset and AI stack
Bring your dataset, model providers, and success criteria. We will scope the right managed run for your team.
Scope a managed run[ok] Wrote CHALLENGE.md
[ok] Wrote .versalist.json
[ok] Wrote eval/examples.json
Requires VERSALIST_API_KEY. Works with any MCP-aware editor.
DocsFind another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.