Patient enquiries and booking admin
Reads incoming enquiries, handles booking changes within your rules and routes everything else to the right team. It never assesses symptoms or clinical urgency.
AI for Healthcare and Life Sciences
AI for healthcare and life sciences, with clinical decisions left to your people
Enquiries, letters, quality records and inspection requests take hours of finding and retyping before anyone qualified looks at them. We build AI into the systems you already run so that work arrives prepared, and a named person approves anything that reaches a patient, a record or a regulator.
.png?height=28&name=Gunnebo%20Logo%20(1).png){kind=small}
.png?height=28&name=Closer%20Still%20Media%20(1).png){kind=small}
.png?height=28&name=Ecommpay%20Logo%20(1).png){kind=small}
.webp?height=28&name=Tussell%20Logo%20(1).webp){kind=small}
-4npmo6jxod.png?height=28&name=iconsolutionsrgb%20(1)-4npmo6jxod.png){kind=small}
Where the time goes today, and what we build instead
SpotDev's AI for healthcare and life sciences builds AI into the systems a provider, manufacturer or research organisation already runs, so administrative and quality work arrives prepared and a named person approves it.
Without SpotDev
Common today
With SpotDev
What we build instead
Without SpotDev
Enquiries sorted by hand
Emails, forms and messages land in one inbox, and someone reads each one to decide where it goes.
With SpotDev
Routed with the context attached
Non-clinical enquiries classified and sent to the right team with the booking or account details attached. Anything clinical goes straight to a clinician.
Without SpotDev
Admin letters typed one by one
Appointment letters, insurer correspondence and billing queries are written from scratch or copied from old ones.
With SpotDev
Drafted in your templates
Routine correspondence drafted from your records and approved templates, for a person to check and send.
Without SpotDev
Quality records started from a blank page
Deviations, change controls and SOP updates are written up by the people who should be investigating them.
With SpotDev
A structured first draft for QA
Drafts assembled from the recorded facts and your templates, with the source record untouched and every change attributed, for your quality team to approve.
Without SpotDev
Inspection requests land on one person
An inspector or client auditor sends a list, and someone spends days finding records and approvals.
With SpotDev
Evidence found and indexed
Requested documents matched to the list and the gaps marked, for a person to check before anything is shared.
What we build for healthcare and life sciences
Each of these takes on administrative or documentation work and leaves clinical, safety and quality decisions with qualified people.
Correspondence and billing admin
Drafts appointment letters, insurer correspondence and invoice queries from your practice system and templates, for your team to check and send.
Quality documents
Drafts deviation reports, change controls and SOP revisions in your templates from the facts recorded, for your quality team to review and approve.
Safety and medical information intake
Reads incoming emails and call notes, flags possible adverse events or product complaints for your safety team, and drafts standard medical information replies from approved wording.
Inspection and audit readiness
Finds and indexes the records an inspector or client auditor asks for and marks what is missing, so requests are answered from evidence.
Enablement for your teams
Your people trained on the workflow: what the system checks, what it cannot see, and when to send something back.
The systems we connect to
- 01
Practice and patient administration
Private practice systems such as Semble, and the booking, billing and correspondence tools around them. What each allows depends on your edition, which we check rather than assume.
- 02
Quality and regulatory systems
Veeva Vault through its published API, and the document control or quality management system your QA team already runs.
- 03
Lab and study data
Electronic lab notebooks such as Benchling, LIMS and study trackers, read without changing the source record unless your quality team agrees otherwise.
- 04
Documents, email and CRM
Microsoft 365, SharePoint, Outlook and Teams, and Salesforce or Dynamics 365 for commercial and partner records.
The rules we build to
Your data protection, clinical safety and quality leads decide what each rule requires of you, and the build gives them the controls and records to act on it.
Health data is special category
UK GDPR gives health data extra protection, so processing it needs an Article 6 lawful basis and an Article 9 condition. Each workflow sees only the data it needs, and we document the processing for your data protection impact assessment.
Administrative by design
MHRA guidance says booking or admin software is unlikely to be a medical device if it only has an administrative function. We write the intended purpose down and keep clinical judgement outside the build.
Human oversight
The CQC's principles say AI should enhance human decision making without replacing it, with outputs continuously monitored. Every output is reviewed by a named person and its accuracy is tracked over time.
GxP data integrity
MHRA guidance expects GxP data to be attributable, legible, contemporaneous, original and accurate, with audit trails. Drafts are attributed, source records are never overwritten, every change is logged, and validation stays with your quality team.
Prepares, never decides
No clinical, safety or quality decision is taken by the system. It prepares the work, and a qualified person decides.
Everything is logged
Every preparation, approval and rejection is recorded, so you can show an inspector or auditor what happened and who decided.
What AI for healthcare and life sciences costs
Three ways in, depending on how far you want to go. Prices exclude VAT, and AI subscriptions and usage are billed to you by the vendor. For a whole department of up to 100 people, AI Rollout starts at £18,000.
AI Starter
£3,500
Your team using AI on their own drafting, summarising and documentation work, set up and trained online over four weeks.
- Up to 15 people, fully remote
- Workspace and usage rules set up for you
- Three live online sessions on real healthcare and life sciences work
- Shared starter tools for correspondence, summaries and document checks
- A review at day 30
Custom Agents
£20,000
One workflow built into your systems and put into controlled use.
- One workflow, such as enquiry routing or deviation report drafting
- Integration with your systems and data sources
- Approval rules written down per action
- Training for the people who use it
- Measured against a baseline
- 60-day post-launch support
AI Accelerator
From £10,000 per month
One department at a time, in a twelve-month programme that moves a team into controlled production each quarter.
- Committed a quarter at a time
- Two production agents per wave
- Baseline, measurement and a monthly review
- Model and platform usage billed separately
Implementation expertise that drives adoption
An in-house engineering team that has delivered more than 300 technology projects. Work with engineers who have built this before.
300+HubSpot implementations, firm-wide
In-house engineering team.
Agents and integrations designed, tested and shipped by our own engineers. Nothing is subcontracted.
OpenAI Select Partner, Certified in the Claude Partner Network
SpotDev is an OpenAI Select Partner and is Certified in the Claude Partner Network, alongside HubSpot Diamond status and Custom Integration and Onboarding accreditations.
Model chosen for the job.
Honest evaluation of the right model for the work. We will say when the answer is the AI you already pay for.
AI with security in mind
- Not trained on by default
- Cyber Essentials Plus
- Built on your infrastructure
- In-house engineers
Common questions
What does it cost?
AI Starter gets a team of up to 15 using AI on their own work for £3,500, set up and trained remotely over four weeks. One workflow built into your systems is a Custom Agents project at £20,000. Running one healthcare or life sciences team as one wave of the AI Accelerator starts at £10,000 per month, committed a quarter at a time. Model and platform usage is billed separately.
Will what you build count as a medical device?
The workflows on this page are administrative. MHRA guidance says software used to book an appointment or request a prescription is unlikely to be a medical device if it only has an administrative function. Software that informs decisions about an individual's care is a different matter with its own regulatory route, and we will say so at the diagnostic if that is what you need.
What does the CQC expect from providers using AI?
The CQC has published principles for providers, including human oversight with outputs continuously monitored, effective governance, and a data protection impact assessment. It also says the absence or presence of AI does not predict a specific rating. We build the oversight and records those principles describe, and you decide how they apply to your service.
Do patients need to know AI is involved?
The CQC's principles say people using services should have appropriate information about their care, including the role of AI in care pathways, with non-digital routes offered if needed. How you tell patients is your decision, and we can build the wording and a non-digital route into the workflow.
Is it safe to use patient or trial data with AI?
Health data is special category data under UK GDPR, and the ICO says you must carry out a data protection impact assessment if you plan to process it on a large scale. On their business plans, Anthropic and OpenAI do not train their models on your content by default. We give each workflow only the data it needs, log every action and put the position for your chosen vendor in writing for your assessment.
We supply the NHS. What about the DSPT, DTAC and clinical safety?
Organisations with access to NHS patient data and systems must use the Data Security and Protection Toolkit, and NHS buyers assess digital health products against DTAC, which covers clinical safety, data protection, technical security, interoperability, and usability and accessibility. Where DCB0129 applies to a health IT system, a Clinical Safety Officer must approve each version of its hazard log. We supply the design, data flows and test evidence those assessments ask for.
We work under GxP. Can AI touch regulated records?
It can prepare them, under controls your quality team sets. MHRA data integrity guidance expects audit trails that record changes without obscuring or overwriting the original record. Drafts are attributed to a person, source records are never overwritten, and validation for intended use is your quality team's decision.
Will it work with the systems we already run?
Usually. SharePoint, Outlook, Salesforce and Dynamics 365 are already in our integration library, and we check what your practice, quality or lab system allows before committing to anything. What each supports depends on your edition.
Are you giving us legal or regulatory advice?
No. We give no legal, regulatory, clinical or compliance advice. We build the controls, logs and approval steps, and your advisers, clinical safety lead and quality team rule on your obligations.
Start with a diagnostic.
A short, fixed-scope assessment of which healthcare and life sciences workflows are worth automating, which are not, and where the approval line has to sit. No obligation.
Related:
SpotDev is an OpenAI Select Partner and a HubSpot Diamond Solutions Partner, and is Certified in the Claude Partner Network. SpotDev is a separate company from OpenAI and from Anthropic, and partner status does not constitute endorsement of SpotDev by OpenAI or by Anthropic. OpenAI and ChatGPT are trademarks of OpenAI. Claude is a trademark of Anthropic, PBC. HubSpot is a trademark of HubSpot, Inc.