Group plan · Powered by Claude Opus 4.7

The Compliance Copilot.

Ask "Are we ready for CQC?", "What's missing in Caring?", "Draft me a Duty of Candour letter for incident #42." The Copilot answers from your own evidence stream — never invents — cites every claim back to the source record.

Live example

Grounded answers with bracketed citations.

Every claim the Copilot makes points at a source record: an evidence event [E12], a complaint [C3], an incident [I7], an open risk [R2], a policy [P5]. Click any chip to open the underlying record in the dashboard.

COPILOT EXAMPLE
Draft me a Duty of Candour letter for incident I3.
Dear Mrs Patel,

I am writing to you in respect of your recent appointment on [date] at The Vesey Private Hospital. I am sorry that we did not deliver the standard of care we expect of ourselves on that occasion.

[Continues, drafted from incident I3 summary + Vesey's brand voice. Apology without admitting legal liability. Reference to investigation timeline + CQC contact details.]
Three rules

How we keep AI safe in compliance contexts.

1. Ground every claim

The system prompt instructs the model to refuse questions it can't answer from the supplied context. Never invents. Never guesses. If the answer isn't in your evidence stream + records, the Copilot says so plainly.

2. Cite every source

Every claim references a bracketed source id (E1, C3, I7, R2, P5) that maps back to the underlying record. The UI renders these as chips. Click any chip to open the source — the user verifies before acting.

3. Refuse clinical + legal advice

The system prompt explicitly forbids: clinical decisions, legal advice, regulator-facing statements without human review. For high-stakes outputs (DoC letters, statutory notifications) a human always reviews before send.

The Outstanding Loop · three questions

The three questions that close the loop.

Outstanding services don't just capture — they change. Each governance huddle, the Copilot answers these three. Inadequate services can't.

Q1 · Outstanding Loop

"What did we change?"

Lists every change made last month because of an incident, complaint, or audit finding — with each change cited back to its trigger record. If the list is empty, you're capturing without improving.

Q2 · Outstanding Loop

"Where's the evidence it's working?"

For each change, surfaces the post-change metric: recurrence count, audit pass rate, training completion, complaint trend. Data, not vibes — Outstanding services prove the change embedded.

Q3 · Outstanding Loop

"Does every clinician know?"

Cross-references the change list against training completions + read-receipted policy circulars. If clinicians haven't acknowledged the change, you've changed paperwork, not practice.

What else the Copilot answers

Six more high-leverage questions.

"Are we ready for CQC?"

Returns a readiness score (0-100), per-KLOE evidence density, weak areas, and the top 3 actions that would boost readiness fastest. Sourced from your live evidence stream.

"What's missing in Caring?"

Surfaces the under-evidenced KLOE + tells you specifically what categories of evidence are thin (e.g. "you have 3 complaint outcomes but 0 dignity-in-care training completions this quarter").

"Draft me a Duty of Candour letter"

Generates a Reg 20-compliant notification letter from the incident summary. Apology without admitting legal liability. Plain English. Under 400 words. Reviewed and edited before send.

"Themes in complaints + incidents this quarter"

Pattern-matches across the recent complaints + incidents corpus. Surfaces themes you can lift directly into the next governance committee report.

"Boost Effective evidence next 30 days"

Recommends specific tracker actions that would shift the Effective KLOE — typically completing a paused audit cycle, recording mandatory training catch-ups, or surfacing outcome data.

"Riskiest open risks"

Ranks the open risk register by combined likelihood × impact × age, plus surfaces any risks whose evidence base contradicts their current rating.

Model + privacy

You pick the model. We protect your data.

Default: Claude Opus 4.7

The Anthropic adapter is the platform default. Best-in-class reasoning over compliance corpora. No training on your data per Anthropic's enterprise terms.

Swap to OpenAI / Azure / Ollama

Adapter pattern means one config change. Use Azure OpenAI if your procurement requires Microsoft. Use local Ollama if you need zero third-party data egress. Per-tenant choice.

No third-party training

Our enterprise agreement with Anthropic excludes training on customer data. Per-tenant API key isolation. SAR export covers every Copilot interaction so subjects can request their full history.

Audit trail of every call

Every Copilot call logs to HR_EVENTS with the question, the context counts, and the model+stop-reason. SOC 2 auditors get a complete record on request.

Try the Copilot live.

Group-tier feature. 14-day trial includes the Copilot at full power so you can interrogate your own evidence stream from day one.