Privacy boundary
Because raw community input stays private, the page uses synthetic sample text to demonstrate the publication path.
Pablo Zavala · AI Safety Evaluation · Research Engineering
Heard.now: Civic-Listening Platform
A civic-listening pilot with Professor Jordan Usdan of Heinz College that stores raw input privately and publishes privacy-checked extracts. The public synthetic sample demonstrates a 7/7 verification path while keeping community messages private.
Claim precision
- What the evidence demonstrates
- Synthetic public sample with 7/7 privacy and integrity checks
- Capability and evidence frontier
- Public visuals use synthetic text so community messages stay private.
Role: Product and systems builder with Professor Jordan Usdan.
How to Inspect This Work
System pattern
The prototype separates private intake from public extracts, with verification checks before publication.
Scope
This is early-stage civic technology work with private materials, so the public artifact is intentionally a synthetic report card.
Case Study
Problem
Civic-listening tools can expose raw community input or publish summaries that lack a trustworthy audit trail.
Setup
Heard.now separates the private input store from public extracts, so publication can pass privacy and integrity checks.
Method
The prototype uses an auditable intake path, privacy checks, and verification checks before surfacing themes.
Result
The synthetic sample run shows privacy-preserving extracts and 7/7 verification checks while keeping raw messages private.
Verification scope
Public visuals use synthetic text because real community messages remain private.
Evidence
The displayed report card is generated from a synthetic sample run of the local Heard workflow.
Key Outcomes
- Separates raw input storage from public extracts
- Uses synthetic public examples that keep community messages private
- Shows a 7/7 verification check path in the sample run
Methods
- Privacy-preserving publication
- Auditability
- Synthetic test data
- Civic listening