Case · Field sales
A CRM that fills itself on the way back from a meeting.
No more empty CRMs after field meetings. Automatic transcription and structuring of notes.
Model case: we assume the company looks like this and show how much it would yield.
- Model case
- Lovable
- Whisper
- Raynet
Starting point
Data lost in the field
Salespeople in the car don't write up their meetings. Information about deals stays in their heads, on scraps of paper or simply gets forgotten. The CRM stays empty and the follow-up steps fall through the cracks.
- Before
No meeting notes
NO NOTES
- After
Dictating into the phone
VOICE INPUT
What we would build
From voice to record
From a voice recording to organised data in the CRM.
- 01
Voice input
Mobile app (Lovable PWA)
- 02
Transcription
Whisper API (OpenAI)
- 03
Sorting
GPT-5.2 pulls out tasks and notes
- 04
Writing to the CRM
Automatic entry into Raynet CRM
- Lovable · Mobile app
- Whisper · Speech to text
- GPT-5.2 · An AI that understands and sorts the text
- Raynet · Target CRM
Rollout steps
How the rollout would go.
- 01
DAY 01 to 03
Mobile interface
Designing screens for fast one-handed input.
- 02
DAY 04 to 07
Speech transcription (Whisper)
Tuning for Czech business terms.
openai.Audio.transcribe(...)
- 03
DAY 08
Ready for the field
The salesperson can dictate notes straight from the field.
Model assumptions
Where the result comes from.
We take a typical company from the sector and the situation from the brief, add labelled assumptions and calculate the result. If the inputs change, so does the result, so you can recalculate it for your own company.
Model company
A model company with 8 field salespeople. Meeting notes do not get written, information stays in their heads and the CRM is empty.
Inputs
- Field salespeople (assumption)
- 8
- Meetings per day per person (assumption)
- 3
- Working days per week
- 5
- Manual CRM entry (assumption)
- 10 min per meeting
- Dictation and check (assumption)
- 2 min per meeting
- Labor rate (assumption)
- 24 EUR / h
Calculation step by step
- 01
Meetings per week
8 × 3 × 5= 120
- 02
Manual entry per week
120 × 10 min= 1 200 min (20 h)
- 03
Dictation per week
120 × 2 min= 240 min (4 h)
- 04
Time saved per week
1 200 min − 240 min= 960 min (16 h)
- 05
Value of the saved time per week
16 h × 24 EUR= 384 EUR
This is a gross saving of time and money. We include the cost of rollout and running only where it is visible in the calculation.
Model results
What would change after rollout.
- Model case
−16 h/week
10 min by hand versus 2 min by dictation across 120 meetings
Time
- Model case
384 EUR/week
16 h × 24 EUR
Cost of time
Your numbers belong in the model, not ours. The calculator shows where to start, and we work out the real values on your data.
Start here
15 minutes is enough for you to know whether it makes sense.
You tell us what is bothering you. We tell you whether we can help, roughly what it costs and where I would start in your place. No presentation.
- jakub@transformuj.ai
- Phone
- +420 773 070 090
- Address
- Legerova 1820/39, Praha 2