Mechanic notes on a scrap of paper, the service advisor's guesses and an invoice issued from memory in the evening. The agent turns dictated or typed notes into a draft repair order and invoice with labour times from Autodata or HaynesPro, parts and your rates in Tekmetric or Shopmonkey, and the service advisor checks and issues it.
Built for ISO 27001NIS2 DORA
The mechanic knows best what was found and what was done, but does not like writing and has no time for it. Notes stay on a scrap of paper or in the margin of the work order: "replaced front right, adjusted, oil". In the evening the service advisor tries to assemble an invoice in Tekmetric or Shopmonkey from that: which labour times from Autodata or HaynesPro apply, which parts were ordered, how many hours. Some work is forgotten and goes unbilled, and other work is described so that the customer does not understand what they are paying for and calls to dispute it. Warranty case descriptions are too short for the insurer or manufacturer to accept them.
The solution lets the mechanic simply dictate notes on a phone after the job, or type a short note on a tablet by the lift, after choosing the car from the day's list in Tekmetric or Shopmonkey. A ChatGPT model through the API transcribes the recording, understands shop terminology and builds a structure: what was found during the inspection, what work was done, what parts were used. The agent then applies the standard labour time from Autodata or HaynesPro for each job according to the vehicle variant (or from your own labour time table), adds the parts from that car's parts order and applies your rates. The result is a draft repair order and invoice, created in Tekmetric or Shopmonkey as an unissued document for that car. The service advisor checks it in the usual program window, adjusts the labour times or a discount and issues it. The customer gets a clear description in plain language: what was found, why a part was replaced and what to do next time. We connect to Tekmetric and Shopmonkey through their APIs or exports, depending on the version, and use the Autodata and HaynesPro labour times through your existing subscription; we choose the method after a check. The model runs on the OpenAI platform through the API without training on your data, voice recordings are kept after transcription only in your environment, and if your accounting runs in an ERP such as SAP Business One hosted by us, the invoice travels through the ERP hosting integration.
Four steps from input to a record in your system, with human approval wherever there is risk.
When the work is done, the mechanic opens the app or Teams, picks the car from the day's list taken from Tekmetric or Shopmonkey, and dictates what was found and done. The recording is transcribed, and shop jargon and part names are recognised using your glossary.
The model sorts the notes into findings, work performed and recommendations. For each job it applies the standard labour time from Autodata or HaynesPro for the variant, or from your table, adds the parts from that car's order with prices and builds an invoice draft with your rates.
The draft is created in Tekmetric or Shopmonkey as an unissued repair order for that car. The service advisor checks it in the usual window, adjusts labour times or applies a discount and issues the invoice. A plain-language description for the customer is prepared and can be sent along with it.
Work for which no labour time is found in Autodata, HaynesPro or your table, or a part that was not ordered through the system, is flagged for the service advisor so that nothing goes unbilled. We build up the glossary and labour time tables from your notes and maintain the integration with the shop software.
A simple window on a phone or tablet: pick a car from the Tekmetric or Shopmonkey day list, dictate or type, send. It also works through Teams.
Labour times from Autodata or HaynesPro through your subscription, or your own labour time table, rates by type of work and a shop glossary, according to which every draft is built.
Creating the draft in Tekmetric or Shopmonkey as an unissued repair order with parts from the order, through an interface, API or import, depending on the version.
A description of the work in the customer's language to go with the invoice, a log of original recordings and drafts, and our support.
ChatGPT through the API with voice recordings + labour times from Autodata or HaynesPro + a draft in Tekmetric or Shopmonkey through an interface, API or import, depending on the version. We choose the platform by the task and by where your data may be located. Read more about this service and its limits on the service page.
No. The agent creates only an unissued draft in Tekmetric or Shopmonkey, and the service advisor issues it and sends it to the customer. This keeps your usual accounting process, and a person always sees what will be charged before the customer sees the invoice.
Yes. We write the draft through the Tekmetric or Shopmonkey API, and with other shop software we connect through an API, a file export or an e-mail flow, depending on the version. We use Autodata or HaynesPro labour times through your existing subscription and its terms, and if you have no subscription, we work with your own labour time table. We choose the integration method after a check.
The recording is sent for transcription through an API without training on your data, and after processing the text and the recording are stored in your environment for as long as you set. A recording does not normally contain customer personal data, because the car is chosen from the shop software's list.
Customers call over lunch, write on Messenger in the evening and leave voice messages when the service advisor is busy at the counter.
Tekmetric or Shopmonkey holds everything: last inspection, insurance date, tyre season and mileage, but nobody has time to remind customers.
A customer sends a photo with the question "how much will this cost", and the technician spends half an hour paging through TecDoc and supplier…
An insurer form, an Audatex estimate, a manufacturer warranty claim, photos, parts invoices and the VIN: every case means an hour of paperwork and…
This service is delivered by specialists with valid international certifications. Their expertise is confirmed by independent organisations, not by us.
AI systems are deployed with protection against data leakage and model abuse.
The AI security programme and its controls are managed following the ISACA methodology.
AI risks are identified and managed like any other IT risk.
We reply within 1 business day
