Industry · Property management
AI for property management: every tenant request to the right person
An AI agent sorts tenant requests, turns rental applications into structured files and gathers what each repair needs. Your team approves every reply.
- Drafts in French, German or English
- Alongside your property management software
- Applicant data kept to the minimum
What AI can do for a property management firm
In a property management firm (a régie, in French-speaking Switzerland), much of the day goes into reading and sorting. A water leak, a question about the ancillary costs statement, an application for a 3.5-room flat and a noise complaint all arrive through the same form or email address. Someone has to open everything and pass each request to the right property manager.
An AI agent does that first pass. It recognises the type of request (repair, rent, application, complaint), picks out the building and the urgency, then forwards the message to the right person with a summary and a draft reply in the tenant’s language. Applications that arrive as PDFs become a structured file, with a list of missing documents.
We work alongside your property management software; we don’t replace it. Nothing reaches a tenant or applicant without your say-so, and personal data is limited to what the file needs.
The problem
Where the time goes today
One address for everything
The contact form and the info@ address receive everything, then messages bounce from one department inbox to another.
Rental applications as PDFs
Forms, scans, phone photos: someone has to open every application to see whether the debt collection extract, a payslip or an ID is missing.
Vague repair requests
‘It’s leaking under the sink.’ With no exact address, no photo and no availability, someone has to contact the tenant again before booking a contractor.
Interactive demo
Try the agent on a property manager’s inbox
The demo shows the inbox of a fictional property management firm. Run the agent: it labels each message, extracts the deadline, amount and file number, assigns it to a person and drafts a reply in the sender’s language. You can also paste an email of your own.
Email triage agent
Reads, sorts, summarises and drafts your replies. You keep the final word.
Inbox
Select an email, or run the agent.
Try it with your own email
Everything runs in your browser: nothing is sent or stored. Simplified demo: answers are prepared in advance or computed by simple rules in your browser. In production, a language model suited to your data does this work, and someone on your team signs off.
I want this for my businessWhat’s happening, step by step
-
Emails arrive Input
The agent watches your inbox, like a colleague opening the post the moment it lands.
-
The AI understands AI
A language model reads the message in its own language and recognises what it is: an invoice, something urgent, a new client…
-
It pulls out what matters AI
Deadline, amount, file number, attachments: everything important is picked out and summed up in one line.
-
To the right person Code
Rules agreed with you send each request to the right person. No AI here: clear rules.
-
A draft is ready AI
For routine requests, the agent writes a reply in the client’s language, based on your templates.
-
You approve Human
Nothing goes out without your say-so: you read, adjust if needed, and send.
Run the demo: each step lights up here.
ModelApertus 70B · Swiss open source
Data processedA server in Switzerland or yours
Picture a colleague who reads every email the second it arrives, understands what it’s about, passes it to the right person and drafts a reply. It never sleeps, never loses anything, and always waits for your go-ahead.
Words to know
- Language model
- The “brain” that reads and writes text: GPT, Claude, Gemini, Mistral, Apertus…
- AI agent
- A program that uses a language model to complete a multi-step task, with your tools.
- Human approval
- The moment a person reads and decides. At NotHuman, it’s the default.
Why it’s safe
- Nothing goes out without your say-so: the agent prepares drafts, someone on your team approves them.
- Who gets what follows rules agreed with you, written in code: the AI does not decide.
- When in doubt (an answer in the wrong format, low confidence), the email goes to a person.
- You choose where the AI runs and where your data is processed.
The agent’s pipeline
- Input Mailbox Microsoft 365 (Graph API), Gmail or IMAP. A new email triggers the pipeline.
- Code Pre-processing Clean-up, language detection, masking of sensitive data where needed.
- AI Classification and extraction The model returns schema-validated JSON: category, priority, fields, summary.
- Code Routing rules Your business rules: who gets what, urgency thresholds, office hours.
- AI Drafting A draft in the sender’s language, from your templates and knowledge base.
- Human Approval Draft placed in Outlook or Gmail, or in an approval queue.
AI reads and writes. Code checks. Humans decide.
Stack
Guardrails
- Structured output: if the model’s answer doesn’t match the schema, the email goes to a person.
- Hidden instructions (prompt injection): the agent can label and draft, never send on its own.
- Confidence threshold: below 0.8, the message is flagged for a person.
- Full audit log: every decision is recorded and searchable.
What the agent produces (JSON)
{
"email_id": "f2",
"language": "de",
"category": "urgent_tax_office",
"priority": "high",
"summary": "Reminder from the tax office, due 5 November. The client thinks he has already paid.",
"fields": {
"client": "Thomas Keller",
"deadline": "2026-11-05",
"action": "verify_payment"
},
"route_to": "marc@alvelia-fiduciaire.example",
"draft": {
"language": "de",
"status": "awaiting_approval"
},
"confidence": 0.94
}Choose the engine
How we set it up
- Day 1 Free audit 30 minutes to look at your volumes, your categories and what must stay human.
- Weeks 1–2 Test on your emails We calibrate categories and rules on a sample of your messages and measure the quality.
- Weeks 2–4 Go-live The agent is connected to your email, with your approval rules.
- Every month Care Monitoring, adjustments and a monthly report.
What we need from you
- Access to the mailbox, read-only to start
- Your categories and who handles what
- A few template replies you already use
What we set up
Automations built around your firm
Three flows to automate first, built on your categories, templates and approval rules.
Tenant requests sorted
Each message gets a category, an urgency level and an owner, following your rules: building, property manager, department. See email triage.
Drafts in three languages
For routine requests, the agent drafts a reply in French, German or English from your templates. Your team reads it, then sends.
Structured rental applications
Applications received as PDFs become a file limited to the information needed. A check flags missing documents before the file reaches the property manager.
Well-documented repairs
The agent spots what is missing (photos, location, access, availability) and drafts the request to the tenant. The right person then gets a complete file.
Several inboxes, one clear view
Lettings, maintenance, accounts: each department gets what concerns it directly.
Alongside your software
We connect the tools you already use (email, Microsoft 365 or Google Workspace, your property management software) through their API, an export or email.
How we work
How it goes
-
Free audit
In 30 minutes we look at your incoming channels, your types of request and what must stay in human hands.
-
Test on your messages
We test the sorting on a sample of your emails and applications before anything goes live.
-
Go-live
We aim for a first automation in service 2 to 4 weeks after the audit, with your approval rules.
-
Monthly care
We monitor sorting quality, adjust the categories and send you a report every month.
Our commitments
Tenant data stays under your control
A human approves
By default, nothing is sent without approval. You choose, case by case, what may go out automatically.
Applicant data kept to the minimum
Only the information the file needs is extracted, and it is kept only as long as necessary. Files of unsuccessful applicants are deleted.
Built with Swiss data protection (FADP) in mind
A data processing agreement (Art. 9 FADP), only the data the task needs, Swiss hosting available.
Frequently asked questions
Do we have to replace our property management software?
No. We work alongside your software; we don’t replace it. If it already has AI features, we take them into account in the audit to avoid duplication.
How do you protect applicants’ personal data?
We keep only what is needed, for no longer than needed. The agent extracts only the information the file requires, and files of unsuccessful applicants are deleted. A data processing agreement (Art. 9 FADP) covers the processing.
Does the AI reply to tenants directly?
Not by default. The agent prepares drafts and your team approves them. You can allow automatic sending for simple cases, such as an acknowledgement, and switch it off at any time.
Where is the data processed?
Wherever you decide. Depending on the task and how sensitive the data is, we use a leading model or Apertus, the open Swiss language model built by EPFL, ETH Zurich and CSCS, hosted in Switzerland or on your own infrastructure.
How long does it take to set up?
We aim for a first automation in service 2 to 4 weeks after the audit. Sorting tenant requests is a good place to start: it can be tested directly on your own emails.
How much does it cost?
On quote, depending on your volume of requests and the tools to connect. The audit is free; you then get a clear quote with a set-up cost and a monthly fee. Request a quote.
NotHuman
How many tenant requests does your team sort each week?
In a free 30-minute audit, we look at your incoming channels and propose a concrete plan.