Safety and governance

AI is how we build it. It is not what we sell.

Reedley is designed to use language models, alongside deterministic rules, as enabling technology. In the development build the product screen calls no language model: its document findings are pre-written. A model route exists in the code outside the product screen; it has been run once, on 89 synthetic development documents (13 November 2026), through a development harness rather than the intended production provider, and that run is not evidence of accuracy. The demonstrations on this website use pre-written outputs, and Ask Reedley uses a deterministic planner with no language model. Practices care whether the work is right, explained and finished — so we foreground the evidence, the human decision and the limits.

Statements reviewed 14 November 2026. Reedley is in development; nothing here describes a live service.

Where AI assistance is intended to be used

In the current design, AI-assisted components are intended to help with:

  • reading clinical correspondence: classification, extraction of findings and proposed record updates, each with a verbatim citation;
  • Ask Reedley: finding and quoting entries in the record with their sources, and saying when nothing can be found. It does not give clinical advice. This is in development and its accuracy has not been measured. In the current build the question is read by a deterministic planner and answered from structured record retrieval; no language model is consulted.

Many other functions — routing, review policy, lifecycle and verification — are deterministic rules, not AI. Rules are designed to be versioned and owned by a named clinician, with the rule behind every item visible in the product. Today every rule is an unsigned draft with no named owner.

What AI in Reedley must never do

  • Make a clinical decision, diagnose, interpret a result or prescribe.
  • Act without a named person’s decision, or mark work verified.
  • Present an inference as a fact. Every statement carries its kind: record fact, derived, rule, AI inference or uncertainty.
  • Follow instructions contained in a document. Document text is data.
  • Be personified. There are no chat personas or “I” statements in clinical surfaces.

Known limitations and risks

Language models can produce output that is incomplete, incorrect or confidently wrong. They can miss a passage, misread a dose or link a finding to the wrong source. These are hazards, and they are recorded as such.

Extraction accuracy has not been established. One model-in-the-loop run on synthetic development documents was recorded on 13 November 2026, against provisional engineering thresholds that carry no clinical weight; the locked holdout has not been sent to any model, and the demonstration on this website uses pre-written outputs, not a live model. Citations are checked to appear word for word in the source; whether a quoted passage actually supports its finding is for the reviewer to judge.

Human verification and source traceability

Every generated statement links to the passage it came from, quoted verbatim, so the reviewer checks it against the original rather than taking dictation. Confidence is expressed as a checkable reason — “dose stated explicitly on page 2” — never as a percentage. Proposals are accepted, edited or rejected by a named person, and rejections need a reason.

Evaluation principles

  • When the evaluation suite runs, false negatives and false positives are to be measured separately, with dangerous misses reported on their own. The one run so far, on synthetic development documents, reports error classes separately; no accuracy figure is claimed from it.
  • A locked holdout set is kept apart from development and re-locked only with a recorded reason.
  • Results are reported by document type and specialty, not just as an average.
  • Synthetic results are never presented as real-world performance.

Change management and accountability

Any change to a model, prompt or rule that affects clinical behaviour will be versioned, evaluated against the regression and holdout suites, assessed in the hazard log and approved by a Clinical Safety Officer (not yet appointed) before release. Outputs are designed to be snapshotted with the versions that produced them, so that any decision can be reconstructed later; in the development build that history is held in browser memory and is lost on reload. Accountability for the product sits with Reedley; accountability for clinical decisions stays with the clinicians who make them.

Data protection and model training

Reedley does not currently process any real patient data. No model provider has been contracted for clinical use, so we make no claims yet about where production processing would happen or which provider would be used.

Our intended position, to be confirmed in contracts and published before any pilot:

  • patient data will not be used to train models;
  • processing will be limited to what is needed for direct care, under the practice’s instructions as data controller;
  • providers, processing locations and retention will be listed here and in the practice’s data processing agreement.

Whether parts of Reedley are regulated as a medical device has not been assessed. MHRA guidance says intended purpose is judged partly from promotional material, so this website avoids describing clinical claims Reedley does not make. MHRA guidance on software as a medical device.

Next steps

Reviewing Reedley for your organisation?

If you are assessing Reedley for clinical safety, information governance or procurement, we will answer directly and tell you what does not exist yet.

  1. See it work

    A scripted walkthrough of a synthetic clinic letter, from receipt to evidence. Pause or step through it at any point.

    Take the 90-second tour
  2. Share it

    Ten short sections for partners, PCN leads and digital staff, written to be forwarded without a conversation first.

    Read the evaluation pack
  3. Talk to us

    Registering interest takes about a minute. A conversation is with Salim Miah, founder (MPharm, independent prescriber).

Questions buyers ask

What will it cost?

Pricing has not been set. Pilot participation would be agreed individually; we will not ask a practice to pay for something that is not ready.

Who is building Reedley?

Reedley is at an early stage and is currently founder-led. Its founder, Salim Miah MPharm, is a UK-qualified pharmacist and independent prescriber who has worked across community pharmacy, hospital and general practice.

As Reedley grows, clinical safety, engineering and information governance roles will be filled by suitably qualified people, and we will name them here.

How much of our team’s time does a pilot take?

Stage 1 is about an hour; registering interest takes about a minute and applying about five minutes.

Stages 2–4 are agreed with you in the conversation; we will not guess.

Does it work with EMIS Web or SystmOne?

Not today. Reedley is designed around EMIS Web workflows, but no integration exists, none is claimed, and no supplier has approved or partnered with Reedley.

We intend to pursue the published integration routes, such as IM1 pairing, and will report each step on the integration page.

The same applies as for EMIS Web: designed for SystmOne workflows, with no integration existing or claimed.

All questions and answers