What this system does with twenty seconds of honesty
SiteVoice turns short, anonymous entries from the people doing the work into the risk picture their leaders are required to see — in the language regulators already use.
How an entry becomes intelligence
Someone says something. Green for a suggestion, red for an issue. Typed or spoken — speech is transcribed on this system's own server and the audio is deleted immediately. No login, no name, no device details.
The analysis engine reads it. A trained reading model extracts what the entry is about (the aspects: equipment, workload, management, pay, environment and so on) and how it was felt — the emotional reading, including intensity, understatement (mild wording over serious content is detected and flagged) and whether the content is escalation-grade.
The reading becomes recognised risk signals. Feelings and aspects compose into signals that match the structures workplace regulators already publish: the Australian model Code of Practice for psychosocial hazards, the UK HSE Management Standards, and the ISO 45003 risk areas. Free text goes in; "Low control over work, rising, worst severity 3" comes out — with the framework alignment printed in every report.
People see what they need, when they need it. Danger-to-life content alerts the supervisor immediately. Everything else lands in the daily brief, the board, and the weekly and monthly listening reports — retellings only, never the writer's own wording.
The anonymity model
- No identity exists to leak. Seats are capacity, not people: no accounts, no names, no device fingerprints, no per-person logs.
- Wording never travels. Every entry is retold by the system before anyone reads it, so writing style cannot identify anyone.
- Take-back is real. Each entry can be deleted from the system by the person who sent it — from their own phone, any time, no questions.
- One honest exception: danger-to-life reports alert the supervisor immediately, and the submit screen says so before anything is sent.
What happens to original wording
This is a per-company policy choice, set by the account owner:
- Sealed custodian — originals are kept but sealed: supervisors never see them; a single designated custodian (typically senior HR) can open one for a formal investigation, and every access is recorded. Chosen when investigative evidence matters.
- Zero retention — originals cease to exist the moment analysis completes. The strongest promise; nothing to unseal, ever.
This deployment: …
In this demo, an audit view additionally shows originals beside the analysis so the reading quality can be assessed. Production deployments follow the policy above.
What leaders get
- Immediate alerts with a recommended first move, an escalation stage, and an act-within window.
- A daily brief built to be read in one minute, card by card.
- The board and explore views: where it sits by group, by aspect, by signal — every number opens into its entries.
- Framework report cards per jurisdiction, and printable daily, weekly and monthly listening reports suitable for internal review, client assurance, insurers and audits.
Signal categories are aligned with recognised frameworks (AU model Code of Practice, UK HSE Management Standards, ISO 45003); alignment does not imply approval or certification by any regulator. Demo data consists of real worker and incident texts from public corpora, analysed by the real engine; no fabricated readings appear anywhere in this product.