AI at the installer, without exposing your sites or your clients
Pricing a global quote, reading a property manager’s contract before signing, setting up solar for an apartment building, yes, but never by pasting a client’s data into an AI without safeguards.
Electrical, heating, plumbing, solar: your files mix villa plans, door and alarm codes, tenants’ contact details, meter data and your fitters’ payslips. Pasted into a consumer AI without a data-processing agreement, they leave your control; the applicable data-protection law still holds you responsible.
Your office and your site managers already use AI to write. The point is not to ban it, but to set what goes into the tool and what never does.
- Global quotes priced from memory in the evening, then a job that loses money on labor and travel
- Property-manager contracts signed without a full read, with clauses written for every trade
- On-call schedules and hour statements patched together, which the joint commission or an inspector may ask for
- Plans, access codes and tenants’ data pasted into public AIs, beyond any control
See for yourself
A prompt structured in 5 blocks: Instruction · Role and audience · Data · Constraints · Format. An unframed AI invents; the frame stops it.
In a workshop, we adapt these prompts to your company, each with its safeguards: no client data and no access to an installation goes into a public AI.
Self-consumption group
A property manager or a building owner asks for a solar offer. Before a single panel is fitted, the company must explain the self-consumption group, write the agreement, share the electricity between the flats and tell the tenants what changes. This prompt produces the agreement, the explained sharing key, the letter to the tenants and the list of points to settle with the network operator.
Global quote item by item
The evening after visiting a villa to renovate, the owner of the company must price the electrical work, the heating and the plumbing in a single quote. He hesitates over the agreement that sets the labor rate, over travel, and over whether to write fixed price or estimate. This prompt gives him a quote item by item, with payment terms and general conditions written out, that a client can compare and that an inspection by the body monitoring the agreement will not take apart.
Client contract · clause review
A property manager or a large client sends its contract or its terms to sign, often with a short deadline and clauses taken from a model for all trades. The owner has no lawyer at hand and sometimes signs what has not been read in full. This prompt gives the table of risky clauses, drafted counter proposals and the list of what a lawyer should read.
Hours and on call · schedule
The owner plans the week from Monday to Sunday and the weekend on call duty, with jobs that overrun and a call out that may ring at night. Or the labour inspectorate or the body monitoring the agreement asks for the schedules and the records. This prompt checks the schedule against the law and the applicable agreement, and proposes solutions for each gap before the week begins.
Hours and supplements statement
At the end of the month, before payroll, the administrator or the owner has the hour records of ten employees, two different agreements and night jobs. He hesitates over the hourly wage formula, over the counter where Thursday evening hours should go and over the meal for the distant site. This prompt returns a statement per employee with the formula of the right agreement, the supplements, the hour balance and the lines to pay.
30 use cases cover your line of work in the Chaptal catalog, out of 750+ in the corpus · each one states what it produces, what it expects from you, and what it refuses to do.
« Le Collaborateur, augmenté »
You and your site managers learn to frame AI on your real files, quotes, property-manager contracts, schedules, without exposing a client or an employee.
See the training →AI usage audit
A review of how AI is used, a register and clear rules before a villa plan or an alarm code ends up in the wrong tool.
See audit & advisory →Do it in a conversation
Jacquard is the Palambur AI assistant. You describe what you need, it knows your line of work and the laws of your country, asks for what is missing and delivers an answer or a ready-to-use document. You choose the model for every question.
Frequently asked questions
Can I paste a property manager’s contract or a client’s plan into an AI?
Not as is. Without a data-processing agreement, what you paste leaves your control. You anonymize first, or you paste nothing; every catalog card repeats this safeguard.
Does the AI know the collective agreement that sets my hourly rate?
It structures the approach and asks the right questions, but the applicable agreement depends on your trade and on where the job is. You hold the text, the AI helps you apply it, and the decision stays yours.
Are my clients’ alarm codes, access and meter data concerned?
Yes. They bind your confidentiality toward the client. The catalog cards remind you what you may write about them in an AI tool, and what you must never write.
Can AI replace the final inspection or the safety report?
No. It prepares the documents and the list of points to check, but the inspection on the installation and the signature stay with the authorized person.
Do I need a large company for this to be worthwhile?
No. A company with a few employees benefits first, because quotes, contracts and payroll rest on few shoulders. The catalog prompts are used as they are, with no technical setup.