System Transparency Pack (System Card)

1. System Overview

System name: askKira  |  System type: AI-powered professional decision-support assistant for education  |  Deployment context: Schools, Multi-Academy Trusts, education organisations

Primary purpose: askKira supports education professionals by interpreting policy and statutory guidance, supporting planning, reflection and professional judgement, reducing administrative workload, and improving consistency and confidence in decision-making.

Non-purpose (explicit exclusions): askKira does not make autonomous decisions, replace professional judgement, perform automated safeguarding determinations, diagnose pupils or staff, or grade, assess or label individuals.

2. Model & Architecture Summary

Model class: Large Language Model (LLM)–based conversational system with domain-specific constraints.

Model provenance: Built on commercially available foundation models. Models are not trained on customer content.

System architecture (high level): User prompt → safety checks → contextual orchestration → model inference → output filtering → user response. Optional retrieval of organisation-specific, permissioned content where enabled.

Data isolation: Customer data is logically isolated by organisation. No cross-organisation data sharing.

3. Training Data & Knowledge Sources

Foundation models are trained on a mixture of licensed data, data created by human trainers, and publicly available text. Customer prompts, documents and outputs are not used to train models. Data is processed solely to provide the service. Where enabled, askKira can reference internal policies, trust documentation and approved guidance — access is strictly permission-controlled.

4. Intended Users & Use Cases

Intended users: Teachers, school leaders, trust executives, central teams (SEND, safeguarding, HR, governance).

Intended use cases: Policy interpretation and clarification, drafting and sense-checking professional documents, scenario-based reflection and support, staff workload reduction.

Out-of-scope use cases: High-stakes automated decisions, live safeguarding judgements without human oversight, medical, psychological or legal determinations.

5. Guardrails & Safety Controls

All outputs are advisory only. Users are explicitly instructed to verify outputs. Automated detection and filtering for safeguarding-sensitive content, harmful or discriminatory language, and inappropriate sexual or violent content. Conservative defaults when discussing children, vulnerability or risk. Clear prompting to escalate safeguarding concerns through organisational procedures. Rate limiting, abuse prevention, role-based access controls and organisational admin oversight are all in place.

6. Known Limitations

Outputs may be inaccurate, incomplete or outdated. The system may hallucinate plausible but incorrect information. It cannot replace contextual knowledge of a school or pupil, cannot account for all local policies or professional nuance, and is not suitable for sole reliance in safeguarding or disciplinary decisions. Model outputs may reflect biases present in underlying training data — active professional scrutiny is required.

7. Monitoring, Evaluation & Improvement

Automated logging of system performance and safety signals (metadata-level). Monitoring for misuse, abuse or anomalous patterns. Defined escalation pathways for safety concerns, safeguarding issues and data protection incidents. Periodic review of guardrails and prompts, with updates informed by user feedback and incident analysis.

8. Privacy & Data Protection Summary

UK GDPR compliant. Privacy by design and by default. Data minimisation. Encryption in transit and at rest. No model training on customer data. Configurable retention and deletion controls.

9. Accountability & Governance

Human accountability retained by customer organisation. askKira provides technical and safety controls; professional judgement remains with users. Ethical use embedded in product design and onboarding. Alignment to UK Government Data & AI Ethics Framework.

10. Summary for Buyers

askKira is designed as a low-risk, assistive AI system for education, with strong privacy and safety foundations, clear limits on autonomy and decision-making, and conservative safeguards for safeguarding and vulnerable users.