Case Study
A London property management group with 1,800 units across Greater London deployed a Softomate-built AI voice agent on Vapi + GPT-4o, handling 1,200 inbound tenant and contractor calls per month, capturing 91% of after-hours calls into qualified callbacks, and lifting daytime call answer rate from 67% to 99%.
13 min read By Deen Dayal Yadav, Founder & AI Automation Director
London property management group, 47 staff, 1,800 managed units across Greater London
A London property management group with 1,800 units across Greater London deployed a Softomate-built AI voice agent on Vapi + GPT-4o, handling 1,200 inbound tenant and contractor calls per month, capturing 91% of after-hours calls into qualified callbacks, and lifting daytime call answer rate from 67% to 99%.
A London property management group with 47 staff and a portfolio of 1,800 residential units spread across Zones 2 to 4 of Greater London had reached a clear operational limit on its inbound phone handling. The firm operated a centralised tenant services line that handled all inbound calls from tenants (reporting maintenance issues, asking about deposits, requesting documents, etc.) and from contractors (confirming attendance, asking for access codes, providing quotes). The line was staffed by three coordinators during weekday office hours, and rolled to a voicemail service outside of those hours.
The firm's call-handling data, pulled from the telephony provider, showed an unambiguous picture. Daytime inbound call volume averaged 240 calls per day across the working week, peaking at over 320 on Mondays. The three coordinators could realistically handle around 160 calls per day at the level of attention each call required. The unanswered calls (roughly 33% of total volume) either dropped into voicemail, were retried by the caller later, or were lost entirely. The operations director had measured, by sampling, that approximately 14% of unanswered tenant calls related to genuinely urgent maintenance issues (water leaks, lock failures, heating outages) that escalated into larger problems because they were not handled at first contact.
The after-hours position was worse. The firm received approximately 80 calls per evening on weekdays and 110 per weekend day, all routed to a voicemail service that produced transcripts the next working day. Around 4% of those after-hours calls were genuine emergencies (security incidents, gas leaks, severe water ingress) that required out-of-hours engineer dispatch through the firm's emergency contractor panel. The current process for triaging emergency calls from a voicemail backlog the next morning was, the operations director acknowledged, structurally inadequate. The firm had absorbed two material insurance claims in the previous twelve months that the loss adjuster had explicitly linked to delayed emergency response.
Adding human capacity was not commercially viable. Three additional daytime coordinators would have cost roughly £108,000 fully loaded, and an out-of-hours human dispatch desk would have added a further £90,000+ annually. The firm's competitive position in the London letting market did not support absorbing those costs into management fees, and clients had made clear in renewal conversations that fee increases were not acceptable.
The regulatory dimension added pressure. As a managing agent operating residential property in London, the firm carried statutory obligations under the Landlord and Tenant Act 1985 around responsiveness to tenant repair reports, with specific timescales for emergency, urgent, and routine repairs. The firm had successfully defended a small number of formal complaints to the property ombudsman in the previous two years, but the operations director was clear that the current call-handling capacity was the underlying risk factor most likely to produce a more serious complaint if not addressed. A formal finding against the firm would have material reputational consequences and would attract scrutiny from the redress scheme on the firm's broader processes.
The contractor dimension was the third part of the inbound call mix that the existing setup handled poorly. Approximately 40% of inbound calls came from contractors (electricians, plumbers, gas engineers, roofers, handymen) rather than from tenants, with queries like “what's the access code for property X”, “is the tenant home for the appointment”, and “here is the quote for the leak repair”. These calls were operationally important but did not require senior coordinator judgment in most cases. The team estimated that around 70% of contractor calls could in principle be handled with structured data lookups (access codes, tenant contact details, work-order references) without any human involvement.
The technology constraints added a fourth dimension. The firm's existing property management system (Reapit) held the data the chatbot would need (property details, tenant contact information, contractor panel directory, work orders) but did not have native voice-channel integration. Any voice automation would need to be built as an integration layer on top of Reapit, which had constrained the firm's previous attempts to address the call-volume issue through more traditional IVR-and-script tooling.
The brief to Softomate was direct. Handle the daytime overflow so the three coordinators could focus on calls that genuinely needed human judgment. Triage after-hours calls so genuine emergencies were dispatched to the emergency contractor within minutes rather than the next morning, and so non-emergency calls were qualified and queued for the appropriate coordinator to action on next working day. Capture every call into the firm's existing property-management system (Reapit) so no information was lost. Handle the high-volume contractor query mix automatically where possible. Sound like a competent member of the team, not an obvious automated system.
Softomate built the AI voice agent on Vapi as the telephony orchestration layer and GPT-4o as the language model, with retrieval-augmented access to the firm's property database (Reapit), the contractor panel directory, and a structured knowledge base of property-management policy (deposit handling, repair categorisation, emergency-vs-routine criteria, statutory landlord obligations). The agent was reachable on the firm's existing main tenant services number, with calls routed first to the agent and escalated to a human coordinator at any point the caller asked or the agent's escalation logic determined.
The platform evaluation deserves explicit note. Softomate compared three voice-AI platforms during the discovery phase: Vapi, Retell AI, and Bland AI. All three offered comparable underlying capability (telephony, real-time speech, LLM integration). Vapi was selected for three reasons: the most flexible custom-function API for the specific Reapit and contractor-panel integrations the build required, the most mature European data-residency story (Vapi could be configured to keep voice data within EU jurisdictions, which was a regulatory requirement for the firm), and the most predictable per-minute pricing structure for the expected call-volume profile. Retell AI and Bland AI both had strong capability but the integration flexibility and the data-residency story were the decisive factors.
The conversation design was the highest-effort part of the build. Property-management calls cover a wide range of intents (maintenance report, deposit query, document request, contractor confirmation, tenancy query, emergency report, complaint, payment query) and each requires a different response pattern, different data lookups, and different downstream actions. Softomate built explicit intent classification at the opening of each call, with the agent asking a single clarifying question if intent was ambiguous (“Is this about a maintenance issue or something else?”). Once intent was classified, the conversation was routed to the appropriate sub-flow.
The emergency classification was the most safety-critical sub-flow. The agent was trained to recognise specific signals indicating a genuine emergency: keywords (gas, smoke, fire, flood, break-in, locked-out, no-heating-elderly), tone signals from the caller, and explicit statements. On recognising an emergency, the agent immediately initiated a parallel action: it confirmed the property address with the caller, looked up the property's assigned emergency contractor in Reapit, dispatched the contractor via SMS to the relevant on-call mobile, and notified the firm's on-call duty manager via SMS and a phone call. The caller stayed on the line throughout this process and was given a confirmed timeline for engineer arrival before the call ended.
The maintenance-report sub-flow was the highest-volume intent. The agent gathered structured information (property address, specific issue, tenant contact details, photographic evidence if the caller could send WhatsApp), wrote a fully formed maintenance ticket into Reapit categorised by urgency level, and either dispatched to the relevant routine-maintenance contractor for category-2 or category-3 issues, or queued for human coordinator review for ambiguous or complex issues. The agent gave the caller a clear expectation of next steps and a reference number for follow-up.
The contractor-query sub-flow handled the 40% of inbound calls from contractors. The agent recognised contractor calls through caller-ID matching against the contractor panel directory (with fallback to opening question if the caller-ID was not recognised), looked up the relevant work order, and provided structured answers to the common queries: property access codes (with security logging of each access-code disclosure), tenant contact details (with same logging), confirmation of the tenant's availability for the appointment (cross-referencing the tenant's stated availability captured at booking time), and acceptance of contractor quotes for work orders under the firm's automated-approval threshold of £300. Contractor quotes over the threshold were captured into the work order and routed to the firm's procurement coordinator for approval.
Brand voice calibration used the firm's existing call recordings from its top three highest-performing coordinators (with appropriate consent). Softomate analysed 240 sample calls to identify the tonal patterns that worked: when to apologise, when to reassure, when to be efficient and brief, when to slow down for elderly or distressed callers. The model was calibrated against these patterns, and the operations director reviewed 100 generated call transcripts before launch to sign off on tone consistency.
The compliance audit layer logged every call interaction in structured form: caller identification, intent classification, data accessed during the call, actions taken, and the final disposition (resolved, escalated, dispatched). The log was queryable in real time by the operations director and produced quarterly reports for the firm's property ombudsman compliance review. This audit capability was the specific feature that allowed the operations director to satisfy the firm's professional indemnity insurer that the automated handling did not increase regulatory risk; it produced a more complete audit trail than the previous human-handled calls, where coordinator notes were inconsistent in detail and rarely captured the full conversational context.
The deployment was phased. Week one was a closed pilot with internal staff calling the agent and reporting transcripts. Week two opened to 10% of inbound traffic, with the rest routing normally. Week three rose to 30%, then 60%, then 100% by week five. Every call during the first six weeks was reviewed daily by Softomate and the operations director jointly, with 34 specific refinements made to intent classification, contractor-dispatch logic, and tonal calibration during that window.
Within the first 90 days of full deployment, the agent was handling approximately 1,200 calls per month directly to completion (resolution, dispatch, or scheduled callback) without human coordinator involvement. The daytime call answer rate rose from 67% (with significant volume going to voicemail or unreached) to 99%, with the remaining 1% being calls the agent escalated immediately to a human coordinator because intent was ambiguous or the caller asked for a person.
The after-hours emergency response time was the outcome the operations director valued most. Before deployment, average response time on after-hours emergency reports (from caller report to engineer dispatch) was over 11 hours, because reports sat in voicemail until the next morning. After deployment, average response time fell to 7 minutes, measured across 43 confirmed after-hours emergencies in the first 90 days. The firm's insurance broker explicitly cited the improved out-of-hours response in renewing the firm's professional indemnity policy at a 4% reduced premium.
The three human coordinators reported, in a structured interview at the 60-day mark, that their working day had changed in character. Routine maintenance reports, deposit queries, and document requests (which had previously consumed the bulk of their time) were now handled by the agent. Their time was concentrated on complex tenancy queries, complaints, multi-property landlord-side queries, and the harder cases the agent escalated. Two of the three coordinators specifically commented that the work was more satisfying and that they felt their senior judgment was being used rather than spent on data lookups.
The cost comparison was unambiguous. The agent handled volume that would have required at least three additional daytime coordinators plus an out-of-hours dispatch desk to service at the same quality level. Total avoided headcount cost was estimated at over £198,000 annually. Softomate's engagement cost was recovered within the first 5 months of go-live, calculated against avoided hire cost alone.
The contractor-query sub-flow produced its own substantial benefit. Contractor calls that had previously consumed roughly 38% of coordinator time were now handled almost entirely by the agent, with structured logging that the procurement coordinator could use for contractor performance monitoring. Average contractor query resolution time fell from 12 minutes (the previous coordinator-handled time, including hold and lookup) to under 90 seconds. Contractors specifically commented in the firm's biannual contractor satisfaction survey that the new responsiveness made the firm easier to work with than competing managing agents.
The unexpected outcome was data quality. Because every call was structured into a formal Reapit ticket with consistent fields, the operations director gained for the first time a clear view of which properties generated the most maintenance contact volume. A pattern emerged showing that 14 specific properties (representing under 1% of the portfolio) generated approximately 11% of all maintenance calls, which led to a targeted capital expenditure review of those properties and a series of landlord recommendations that reduced ongoing contact volume from those properties by an estimated 60% over the following quarter.
The compliance benefit was the outcome that mattered most to the operations director in regulatory terms. The structured audit trail allowed the firm to produce a complete per-property call history on demand for any tenant complaint or ombudsman query, replacing the previous gather-from-multiple-sources approach that had been the single biggest exposure in the firm's compliance posture. The firm's compliance consultancy specifically commented on the improvement in audit-trail quality during the next routine review.
The agent has since been extended to handle outbound calls in two specific workflows: confirmation calls to tenants the day before a scheduled engineer visit, and follow-up calls after engineer attendance to confirm satisfaction with the work completed. Both extensions were delivered as configuration changes rather than new builds and are expected to add a further 200-300 hours of operational saving per quarter.
Three things, with the benefit of hindsight, would have made the build smoother. First, the contractor panel directory in Reapit had significant accumulated inconsistency in caller-ID formatting that the agent's caller-ID matching initially failed on; Softomate added a directory cleanup workstream in week 4 that resolved the bulk of the inconsistencies. Future engagements should include directory data hygiene as a pre-build task rather than an in-flight discovery. Second, the emergency-classification keyword list required several rounds of refinement after launch to handle regional variations in how callers described the same emergency; the operations director's local knowledge of how London tenants typically phrased these reports was material in calibrating the model. Third, the model selection deserves continued re-evaluation as the voice-AI market evolves; the platform landscape has shifted noticeably even in the months since launch and Softomate plans to re-evaluate the platform choice annually.
The downstream effect on the firm's growth capacity was a quietly important outcome. The operations director had previously felt that the firm's portfolio could not grow significantly beyond the existing 1,800 units without proportionally expanding the operations team. With the new call-handling capacity, the operations director estimated that the firm could now grow to approximately 2,500-2,800 units without requiring any additional coordinator headcount. This shifted the firm's growth-planning conversation materially: portfolio expansion became a commercial-team question rather than an operations-capacity question.
The first-year retrospective captured several compounding outcomes that the original engagement scope had not explicitly anticipated. Tenant satisfaction scores, measured through the firm's annual tenant survey conducted approximately ten months after deployment, showed a noticeable improvement in the “responsiveness of property management” question, moving from the firm's historical 3.4-out-of-5 average to 4.2 across the cohort surveyed post-deployment. Several free-text comments specifically referenced the speed of response to maintenance reports as a positive factor in renewal intent, with one tenant commenting that she had renewed her tenancy partly because she felt the agent was “actually reachable” in a way her previous letting had not been. The director's marketing team subsequently used the responsiveness improvement as a specific selling point in new-landlord pitches.
The contractor relationship dimension produced its own measurable improvement. Contractors, whose 38% of inbound call volume had been a quietly persistent operational pain point, reported in the firm's biannual contractor satisfaction survey that working with the firm had become noticeably more efficient. Average time-to-quote-acceptance fell from 36 hours pre-deployment to under 4 hours post-deployment, a change that several contractors specifically attributed to the new responsiveness of the firm's call handling. Two preferred contractors who had been deprioritising the firm in their scheduling moved the firm back to first-tier preference, citing the operational ease of working with the new setup.
The compliance outcome compounded over the year. The firm's first annual property-ombudsman compliance review post-deployment was completed in approximately one-third of the time previous reviews had taken, with the reviewer specifically noting the improvement in audit-trail quality. No ombudsman complaints were upheld against the firm during the year following deployment, compared to two upheld complaints in the preceding twelve months that the operations director had attributed in part to the call-handling capacity gap. The firm's professional indemnity insurer renewed the firm's policy for a second consecutive year at a reduced premium, with the broker explicitly referencing the operational improvements as a factor in the underwriter's pricing decision.
The senior coordinator role evolution that surfaced in the 60-day interview deepened over the year. The three coordinators developed into a more strategic operations function, taking on responsibilities that the firm had previously not had the capacity to address: structured landlord relationship management, proactive property condition monitoring, and a quarterly portfolio performance review with the larger landlord clients. The operations director described the team's transition as moving from reactive call-handling to proactive portfolio operations, a shift that altered both the team's working day and the value the team contributed to the firm's commercial offering.
The portfolio growth that became feasible during the year following deployment was the strategic outcome the firm's commercial team valued most. The portfolio expanded from 1,800 units to 2,140 units across the twelve months without any additional coordinator headcount, with the operations director estimating that the additional 340 units would have required approximately 1.5 additional FTE under the previous setup. The cost of those avoided FTE, plus the management-fee revenue from the new units, produced a combined annualised value of approximately £240,000 that the operations director attributed directly to the operational headroom the AI voice agent created.
Related service: AI Voice Agent Development London. Further reading: AI Receptionist for London Estate Agents, Bland AI vs Vapi vs Retell AI UK and AI Receptionist vs Human. Related case study: AI Chatbot for London Letting Agency.
Anonymised client engagement. Identifying details modified for confidentiality. Outcome ranges reflect typical results from similar projects.
Names withheld to preserve confidentiality.
Work with us
Every project we take on has a measurable outcome. Talk to our London team and we will show you exactly how we would approach your challenge.
Softomate Solutions Limited
Deen Dayal Yadav
Online