The most regulated and customer-impactful conversation in motor claims — handled end-to-end with engineer-set values, symmetric evidence disclosure, and a complete Timeline audit trail. Built for the FOS file you hope you never have to open.
Why TL is Hard
Total-loss is where regulatory weight, customer stress, engineer scarcity, and unpredictable volume all hit the same conversation.
Every TL value should land at the engineer’s number. Variation between handlers is FOS exposure and indemnity drift in the same step.
TL is the conversation customers remember. Long holds, repeated explanations, or perceived pressure all show up in the FOS file later.
Consumer Duty, FOS, vulnerable-customer policy, anti-detriment expectations. TL conversations are audited harder than any other claim touchpoint.
Steady-state TL volume is bad enough; peril events and weekends compress weeks of work into days. Hiring for the peak is impossible.
Engineers should be assessing vehicles, not sitting on phone calls reading comparable evidence. Routine TL conversations eat the technical resource you need.
Some customers want a phone call. Some want a WhatsApp message. Some need an email with the comparable data attached. The TL conversation has to land on whichever channel they pick.
End-to-End Flow
Six steps from engineer assessment to settled case. Every step attributed to a named human in Timeline.
The engineer assesses the vehicle and enters the total-loss valuation as a structured field on the case. Comparable market data is attached. The case is marked ready-for-customer.
Switchboard reaches the customer on the channel they prefer — voice, WhatsApp, SMS, or email. Same evidence pack, same script logic, same Timeline audit trail across all channels.
Comparable valuations are shared in both directions: comps below the engineer’s value and comps above. The customer sees the full market picture. The AI does not haggle, lead, or selectively withhold.
Whatever the customer says is logged: agreement, disagreement, tone, hesitation, repeated questions. Vulnerable-customer signals trigger immediate human handoff. Frustration triggers escalation.
Continued disagreement is not negotiated by the AI. The conversation routes back to the engineer who set the value, with full transcript and structured response data. The dispute is resolved human-to-human.
Agreement triggers the settlement workflow: documentation generated, payment scheduled, salvage routed. Timeline holds the full record — every decision attributed to a named human, every conversation transcribed.
The Outcomes
Engineer time, settlement consistency, FOS exposure, peak-load handling — all shifting in the same direction.
Routine TL conversations stop consuming engineer time. They set values; Switchboard runs the conversation. Engineer attention concentrates on assessments and disputes — the work only they can do.
Every customer hears the same engineer-set value, presented with the same evidence pack, in the same structured way. Handler variation drops out of the equation.
Symmetric disclosure removes the selective-information argument. Full transcripts and structured event capture make every settlement defensible if it ever lands at the FOS.
Peril events do not break the SLA. Switchboard scales sideways — hundreds of concurrent TL conversations, no rota, no overtime, no recruitment crunch.
The customer who wants a phone call gets one. The customer who wants WhatsApp gets that. Same TL flow, same audit trail, same engineer behind it.
Frustration, confusion, repeated questions, or explicit distress signals all trigger immediate human handoff. The platform notices what handlers might miss on a busy queue.
Compliance Posture
Consumer Duty, FOS, vulnerable-customer policy, and anti-detriment are not bolt-ons. They shape the conversation.
Fair customer outcomes are baked into the conversation design — symmetric disclosure, structured response capture, configurable escalation. Not a separate compliance project.
Every TL conversation produces a full transcript, a structured response record, and a Timeline trail naming the engineer who set the value. If the case lands at the FOS, the file is complete.
Frustration and distress signals trigger immediate human handoff with full context. The platform supports — does not replace — your vulnerable-customer process.
The AI presents and listens. It does not negotiate, convince, or attempt to lower the offer. Pressure on the customer comes out of the equation entirely.
Every Channel
The engineer’s value, the comparable evidence, the structured response capture, the Timeline audit — identical across voice, WhatsApp, SMS, and email.
Outbound TL call with natural speech, barge-in, warm transfer to engineer.
TL evidence shared in-thread, asynchronous response, full audit on the case.
Short-form TL summary with link to full evidence pack and response option.
Full evidence pack as a structured email; AI drafts the response, handler approves.
Buyer Questions
The engineer assesses the vehicle and enters the total-loss valuation as a structured field on the case file in SwiftCase. Comparable market evidence is attached. The case is marked ready for customer contact, and Switchboard picks it up from there. The engineer’s value is what the AI presents — the AI cannot generate, modify, or negotiate it.
The AI does not negotiate. It presents the engineer’s value with comparable evidence symmetrically — comps below the value and comps above. Continued disagreement routes back to the named engineer for human-to-human resolution. Anti-detriment is a design constraint, not a configuration setting.
Vulnerable-customer signals — distress, confusion, repeated questions, explicit indicators — trigger immediate handoff to a human handler with the full conversation summary. The receiving handler sees what the customer said and what the AI did, with no cold transfer. Switchboard supports your vulnerable-customer process; it does not replace it.
A chatbot reads from a knowledge base. Switchboard runs the actual TL conversation: presenting the engineer-set value, sharing comparable evidence symmetrically, capturing the customer’s response as a structured event, calling tools to update the case file in real-time, and escalating on configurable triggers. The chatbot answers questions; Switchboard runs a regulated process.
Yes. Agent definitions, evidence pack format, escalation thresholds, and handoff scripts are all configurable per insurer. Most teams start with our defaults during a 30-day pilot and tune from real call data. The hard limits — no AI-generated values, symmetric disclosure, approval queues, Timeline logging — are platform constants, not configurable.
Yes. Switchboard runs total-loss valuation conversations in production at Laird Assessors. Out-of-hours intake, outbound bodyshop chasing, and TL valuation chats — all live, all on the engineer-sets-value flow described on this page. See the Laird year-in-review for production volumes.
Pick a workflow — TL conversations, OOH intake, or your bodyshop chase queue. Measured against your own SLA and cost-per-claim. No platform migration. No long lock-in.
