Referral and correspondence processing
Structured extraction from inbound referrals and letters into the receiving system, with a person confirming before the record is created.
Industry
Administrative and operational systems that reduce clinical admin without touching clinical decision-making.
Context
Healthcare has the clearest boundary of any sector we work in: the administrative burden around care is a legitimate target for automation, and clinical decision-making is not. We work firmly on the administrative side — referrals, scheduling, documentation, correspondence, reporting and the movement of information between systems.
That boundary is a design constraint, not a disclaimer. Anything that could be read as clinical advice is out of scope for the systems we build, and where an output informs a clinical process it is presented as source material for a clinician, attributed and unaltered.
Where we would start
Ordered by how quickly the result can be verified. Where output is easy to check, automation carries less risk.
Structured extraction from inbound referrals and letters into the receiving system, with a person confirming before the record is created.
Drafting routine non-clinical correspondence and administrative documentation from existing records, for staff review and sign-off.
Visibility of waiting times, throughput, capacity and backlog on agreed definitions, with drill-through to the underlying records.
Cited answers drawn from current internal policy and standard operating procedures — never from clinical literature, and never offering clinical guidance.
Reliable exchange between administrative systems using standard interfaces, with reconciliation reporting so nothing is silently lost.
Governance
These are the requirements that decide the architecture in this sector. Retrofitting any of them means rebuilding, so they are settled during design.
Related
AI agents, assistants and automated workflows that carry out real work inside your systems, with human approval at the points that matter.
Dashboards, reporting and data foundations that make operational reality visible — and make your organisation ready for AI.
Security engineering, assurance and compliance support — including the controls specific to AI systems.
Cloud architecture, migration and system integration — designed for the cost, resilience and compliance position you actually need.
Structured data extracted from inbound documents, with confidence surfaced and a person confirming before anything is committed.
Read the full write-upIllustrative solution patternA single operational view built on agreed metric definitions, with visible freshness and drill-through to source records.
Read the full write-upIllustrative solution patternReliable data movement between line-of-business systems, with versioned contracts and reconciliation so failures surface.
Read the full write-upTell us which of these pressures you recognise and which you would put first. We will come back with an honest view of whether we are the right people for it.
We reply to every enquiry within one business day.