Urban practice · 7,500 patients
Park Street Surgery
Eight weeks of measured access, with every safety indicator reviewed
Reporting period Eight weeks from November 2025 · Measured pilot · Liverpool
- 7,500 Registered patients
- 8 weeks Measured deployment period
- Good CQC overall rating
- Zero Service interruptions in the period
Key results at a glance
Executive summary
Park Street Surgery is an NHS GP practice in Liverpool with approximately 7,500 registered patients. In November 2025 the practice went live with Jackie, and measured the results across an eight-week pilot.
Phone demand at 8am exceeded what the reception team could handle. Calls went unanswered, patients waited in queues, and the administrative workload was crowding out other work — outbound patient contact, care navigation, QOF activity. The practice was not in crisis, but the gap between what the reception team could handle and what the patient list demanded was real, and it was not closing by itself.
Across the pilot Jackie handled 1,226 patient calls, served 641 patients, absorbed 81% of inbound call demand and returned 51.3 hours of staff time — with the reception team fully staffed throughout. Jackie was additional capacity sitting alongside the existing team.
The challenge
Park Street Surgery faced the structural challenge that most practices with a busy patient list recognise immediately. Their decision to trial Jackie was driven by two practical questions: could an AI system actually hold a conversation well enough to handle routine inbound calls, and if it could, what would that mean for the team’s workload in practice?
An 8am peak the team could not absorb
Phone demand first thing exceeded what the reception team could handle. Calls went unanswered and patients waited in queues, with staff managing the pressure as best they could.
Admin crowding out everything else
The administrative workload was displacing other work the team needed to do — outbound patient contact, care navigation and QOF activity all competed with the phone.
A gap that was not closing by itself
The practice was not in crisis, but the distance between reception capacity and what the patient list demanded was real, persistent, and not going to resolve without either hiring or a change in how calls were handled.
The solution
Jackie was integrated with Park Street’s existing telephony platform. No new phone number was issued to patients and no hardware was installed. Setup took one to two weeks and involved configuring Jackie to follow Park Street’s specific protocols — their sick-note rules, their appointment booking eligibility criteria, their form requirements. The practice routed a portion of inbound calls through Jackie initially, with the option to scale, and the reception team remained fully staffed throughout.
- Appointment requests Jackie collected the reason for the appointment, relevant symptoms and preferred timing, and submitted a completed form directly into the practice’s system.
- Sick note and fit note requests Jackie verified whether the patient’s current sick note had expired before processing a new request, applying the practice’s eligibility rules automatically. Patients whose notes had not expired were informed of the self-certification rule and sent an SMS link.
- General admin queries Jackie handled a range of routine questions, escalating to reception for anything that required human judgement or sensitive handling.
- Safety indicator detection Where patients mentioned symptoms warranting clinical escalation, Jackie identified the safety indicators and advised the patient to contact 999, or offered to transfer them to reception immediately.
Quantifiable outcomes
Across the eight-week pilot Jackie handled 1,226 patient calls, covering the routine inbound range that any GP practice recognises.
| Outcome | Calls | Share |
|---|---|---|
| Calls handled | 1,226 | — |
| Patients served | 641 | — |
| Of inbound call demand absorbed | — | 81% |
Jackie’s fully-handled rate across the pilot — the share of calls she carried to a complete outcome once out-of-scope requests and early caller abandonment are set aside. It is the same definition reported at Deddington and Staffa, so the three deployments can be read against one metric, and it is a different measure from the 81% of inbound demand absorbed above.
The 81% call absorption figure means that for every ten inbound calls arriving during Jackie’s operating hours, eight were handled end-to-end by Jackie without a human receptionist being involved. The remaining two were transferred to reception, usually because the patient requested a person or the call involved a matter outside Jackie’s configured scope.
Speed and capacity
- Staff time recovered
- 51.3 hours
- Safety indicators raised for clinician review
- 76
- Peak simultaneous calls
- 17 in pilot, 22 since
- Setup time before go-live
- 1–2 weeks
- Unplanned service interruptions
- Zero
Clinical signal
What the pilot showed clinically
Eight weeks is long enough to answer the question a clinical safety officer actually asks: when something needed a clinician, did it reach one? Park Street is the deployment with the longest measured record against that question.
- 76 safety indicators, every one clinician-reviewed Across the pilot Jackie raised 76 safety indicators and passed each to the practice team. All were reviewed by a clinician and no safety incidents were reported. Jackie does not decide urgency — she records what the patient described and routes it sooner.
- Eligibility applied before an appointment was consumed Sick-note requests were checked against the practice’s own expiry rules on the call. Patients whose notes had not expired were told about self-certification and sent an SMS link, so a category of avoidable admin never reached the team and no appointment slot was spent on it.
- What reached the team was the patient’s own account Jackie collected the reason for the appointment, the relevant symptoms and the patient’s preferred timing, and submitted a completed structured record into the practice’s system — the same fields for every caller, at whatever hour they rang.
Patient and staff experience
The practice anticipated some patient resistance to speaking with an AI system. In practice, the response was largely positive. Patient feedback, collected via SMS at the end of calls, noted the speed of answer, the politeness of the interaction and, notably, the absence of a queue.
What patients valued
“Much more polite than the receptionist.”
“Speaking to Jackie reduced my anxiety, because I did not have to wait.”
The key factor appears to be conversation quality. Jackie adapts in real time to what the patient says, asks contextually appropriate follow-up questions, and does not rush the interaction. Patients who expected a phone menu experienced a conversation instead.
Reliability
The practice experienced no service interruptions during the pilot. Jackie was available throughout every operating hour she was scheduled to cover. For a practice evaluating a technology that sits at the front of their patient access pathway, reliability is not a minor consideration — it is the baseline requirement. Zero unplanned outages across eight weeks met that requirement.
Conclusion
- Immediate access and capacity: 81% of inbound call demand absorbed, and 51.3 hours of staff time returned across eight weeks.
- Clinical routing under measurement: 76 safety indicators raised and clinician-reviewed across eight weeks, with no safety incidents reported.
- Sick-note eligibility logic that created value from day one, preventing unnecessary task creation for the reception team.
- Reliability: zero unplanned outages across the full eight-week measured period.
About Park Street Surgery
Park Street Surgery is an NHS GP practice in Liverpool with approximately 7,500 registered patients. Jackie went live at the practice in November 2025 and the deployment was measured across an eight-week pilot.
Figures are drawn from Jackie’s call analytics across the eight-week measured pilot at Park Street Surgery, and from patient feedback collected by SMS at the end of calls.
More customer results
Take routine patient contact off your team’s day.
See how an Auxilis worker could handle a defined patient workflow, complete approved actions and bring in your team only when they are needed.