Harper logoH.A.R.P.E.R.
Safeguarding

Safety is not a setting. It is the architecture.

Every prompt and every reply passes through the same five-stage pipeline. Nothing reaches a child unscreened. Nothing leaves the system unlogged.

01Live

Pre-screening

Every prompt is classified for intent, sentiment and risk before it reaches a model.

02Live

Policy routing

Blocked categories are refused inline; monitored patterns are tagged for review.

03Live

Agent response

Curriculum-aligned reply generated within the agent's character and reading age.

04Live

Post-screening

The reply is re-checked for safety, tone and accuracy before the child sees it.

05Live

Audit & escalation

Severity-scored, logged, and escalated to a human safeguarding lead when needed.

Visible safeguards

What children and parents can see.

5-stage pipeline

Pre-screen, route, respond, post-screen, escalate.

Childline fallback

Always-on signposting to 0800 1111.

Per-agent redirects

Each character holds the same calm, scripted safe responses.

Hidden safeguards

What runs behind every reply.

Pre/post-screening

Every message is checked before and after generation.

Severity scoring

Signals are scored 1–5 and routed to the right reviewer.

Human-in-the-loop

DSLs see flagged conversations with full context.

Parent alerting

Trusted grown-ups are notified for severity 3 and above.

Categories

Blocked vs monitored.

Hard-blocked

Refused inline. Logged at severity 5.

Self-harm contentSexual contentViolenceHate speechGamblingDrugs

Monitored patterns

Tracked across a session. Escalated when severity rises.

Sentiment dipsFamily conflict cuesBullying mentionsLoneliness signalsRepeated frustration
Embedded rules

The seven non-negotiables every agent holds.

  1. 01Never ask for personal information.
  2. 02Never roleplay as a real person or family member.
  3. 03Never offer medical, legal or crisis advice.
  4. 04Always pivot gently when a child is distressed.
  5. 05Always offer Childline when safeguarding signals appear.
  6. 06Always log the event with severity and reasoning.
  7. 07Always defer to the human safeguarding lead.
Live

See the pipeline in action.

A scripted exchange demonstrating sentiment pivots and safeguarding escalations.

Live safeguarding playground · scripted demo
Access

Role-based by default.

Child

Sees only their own conversations and missions.

Parent

Sees their child's progress, tone and any alerts.

Admin / DSL

Sees the cohort queue, audit trail and exports.