marIA, the attendo AI

AI in every layer. With the bill in plain sight.

marIA drafts, classifies, scores, summarizes and answers questions about your data, inside the system where your team works. You approve what goes out, every operation is logged with its cost, and spending stops at the cap you set.

  • Your provider and your key
  • A monthly budget that stops spending
  • Turn it off module by module
AI Status screen with the provider, the monthly budget and every configured connection
AI Status: the provider, the monthly budget and every piece of marIA, on one screen.

The problem

Nobody worries it will fail. They worry they cannot control it.

When a company considers using AI in its operations, the same three questions always come up. attendo answers all three with one screen.

How much will it cost me each month?

You see it in real time, by provider and by model, with a cap that is never exceeded.

What exactly did it do, and with what data?

Every operation is logged: who ran it, on which document, with which model and what it cost.

Can I turn it off?

Module by module. And without AI, attendo keeps working in full.

The idea

AI is not bolted on top. It is built in.

marIA works on the same data model as your team: the record, its timeline, the contract, the asset and the customer. That is why its proposals come with context, not with a snippet of text pasted into a chat. And that is why it is governed from a single place.

The AI suggests, you decide, and it is logged Three linked steps: the AI suggests, a person reviews and approves, and the operation is audited with its cost. On the right, a monthly budget meter showing what has been used. marIA · THE attendo AI The AI suggests. You decide. And it is logged. 1 Suggests Drafts the reply with the customer history at hand Classifies the incoming ticket Scores the lead Summarizes the call Answers questions on your data 2 You decide Everything is a suggestion you can review You accept, edit or dismiss Anything sent to the customer goes through human approval Never acts behind your back 3 It is audited Who ran it On which document Which model it used What it cost Your key, your provider, your bill MONTHLY BUDGET Usage against your limit It warns you near the limit and stops when you reach it. The AI layer is turned on module by module: the core works without it. YOUR PROVIDER, YOUR KEY OpenAI Google Gemini Anthropic OpenRouter Mistral ElevenLabs Jev AI

marIA in every layer

Where AI works in attendo

LayerWhat marIA does
On the recordDrafts the reply with the history in front of it. Summarizes audio, meeting minutes and voice notes. Answers by citing your manuals
In communicationsClassifies email, detects tone and filters spam. Suggests replies in the inbox. Handles web chat and hands off to a person when needed. With voice bots, it also answers calls on your phone system
In processesDraws the flow you describe in plain language and explains why a run did what it did. AI decision nodes choose the branch of the flow. AI Autopilot (Multiple AI Agents) scores from 0 to 100 and splits the work between AI and people
In dataAnswers plain-language questions about your data, read-only, and shows what it queried. Proposes the chart you describe. Reads a report without inventing figures. In maintenance, the data chat answers questions about the 22 KPIs on the dashboard, with the same figures. It sends the provider you configure for it a summary with the names of plants, assets, plans and clients
In salesWith Sales AI, it scores and assigns leads, writes drafts and the web quote, monitors the health of each customer and prepares prospecting. Its metrics are a tab in your sales metrics
In task complianceAlso sorts the Compliance list by what rules cannot see: the customer’s frustration, the value at stake or legal deadlines. It tells you first how many analyses are needed and has a monthly cap
In maintenanceProposes a probable diagnosis and a criticality score for each breakdown. In predictive maintenance, it works with AI models on your sensor readings. Turns the technician’s voice note into text
In the platformTranslates missing text without touching what a person wrote. Answers how-to questions using the manual. And proposes the dashboard you describe, with the same time limit as any other query

AI Autopilot

Agents that prepare the work. A person who decides.

Each marIA micro-agent has a role: it researches, scores or drafts. The document passes from one to the next, and the last step always belongs to a person.

AI Autopilot (Multiple AI Agents) · sales example

A lead enters the AI Autopilot sales process. marIA researches the company, scores the opportunity and drafts the first email; the sales rep approves sending it.

  1. 01 Research marIA · Researches

    Prospect LD-2026-0318 Distributor · 3 warehouses
    • Industry
    • Size
    • Interest

    Facts ready

  2. 02 Qualification marIA · Scores

    Qualified Opportunity score 78/100
    • Fit · High
    • Urgency · Medium

    Threshold passed

  3. 03 Conversation marIA · Drafts

    Qualified First email to the lead Not sent

    Draft ready

  4. 04 Human review Person

    Waiting for you Area sales rep Pending approval

    Agents paused

Example. Each column is worked by a marIA micro-agent, which hands the document on to the next one; the last column belongs to a person. Statuses, score weights and the threshold are set in the Autopilot editor.
  • A person decides Whatever the supervisor escalates waits for approval, and anyone can claim the case: the agents stop working on it.
  • Every step in view The AI activity log shows what each agent did, and every handoff leaves a summary on the timeline.
  • It works without AI too With no AI provider, the process runs as a manual status flow.

Your assistants, connected

MCP, both ways

attendo works as an MCP server. From Claude or ChatGPT you can ask about your tickets, your customers or your assets. The answer cites its source and respects each person’s permissions. Write access is off by default.

It also works as an MCP client: attendo connects to third-party MCP servers. From a flow or from the record, marIA queries your other systems, for example whether your ERP has a part in stock.

Control

AI proposes. You decide. And it is all on record.

01

You decide

Anything that goes out to a customer waits for your approval by default. The few exceptions, such as automatic sending to low-scoring leads or automatic replies based on your documentation, are off out of the box. Only an administrator can turn them on, and that is logged.

02

Everything is logged

Each operation records who ran it, on which document, with which model and provider, what it generated and what it cost. What was sent and answered is cleared after 90 days; the figures stay.

03

You set the cap

A monthly budget per provider that warns you as you get close and stops the AI when it is reached. The rest of attendo keeps working.

04

Your provider, your key

OpenAI, Google Gemini, Anthropic, Mistral, Scaleway, Microsoft 365 Copilot, OpenRouter, ElevenLabs for voice, or Jev AI (Typesafe AI), built in natively. Models are read live and you can switch providers without redoing anything. Keys are stored encrypted.

05

Your data, with rules

The rows of your tables only travel to Scaleway or to your Microsoft 365 Copilot. So do the pieces that read your customers’ messages, such as sorting the Compliance list or drafting the web quote. Other providers receive the structure and the text of the document at hand. The rule is in the code, not in a policy.

06

It turns off

Module by module. Without AI, attendo is the same attendo.

Your AI, your provider, your bill, your control.

Where it fits (and where it does not)

What marIA does not do

  • It does not decide for you

    It does not close deals or work orders, and it does not approve anything. It assigns leads according to the rules you set.

  • It does not judge people

    When it sorts the Compliance list, it judges the document, never the person handling it. We do not pass it the agent’s or the customer’s name, although the text of the messages may contain them.

  • It does not learn from your data

    We do not train or fine-tune models on your information. The AI reads your documents when it answers, with the provider you choose.

Frequently asked questions

Frequently asked questions

Is my data used to train models?

No. attendo does not train models on your data: the AI reads your documents at the moment it answers. It connects to your provider with your key, and that provider’s terms apply. If your data must not leave Europe or your organization, use Scaleway or your Microsoft 365 Copilot.

How much will I spend on AI?

Whatever you use with your provider, visible in real time and with a monthly cap that stops spending. You can also use attendo AI credits on Scaleway.

Does it send anything to my customers without anyone reviewing it?

Not by default. Automatic sending is off out of the box. Turning it on is a logged decision made by an administrator.

What if it gets something wrong?

You see it before it goes out. And if it does go out, the reply that was sent is on the document’s timeline, and the AI log keeps for 90 days the context it was generated with.

Can it query my database?

Only the authorized tables, read-only, with no free-form queries and only for administrators. And it always shows what it queried.

We already use Microsoft 365 Copilot. Does that work?

Yes. Connect it as the AI provider for attendo, and use attendo as an MCP server from your assistants.

Can it be specialized with our own knowledge?

Yes, with your documentation: search across your documents answers by citing your manuals, procedures and contracts. We do not fine-tune models on your data.

What is Jev AI?

An AI provider from Typesafe AI, built natively into attendo. It removes the language model from the output and gives structured answers, with far fewer inaccuracies and a much lower cost. You use it with your own Jev AI key, like the other providers.

Can I use attendo without AI?

Yes. AI is optional and the whole platform works without it.

Request a demo

Start with a single piece

Turn on the reply draft or the data assistant, set a spending cap and see what happens. We will show you with your own data.

  • With your operation, not a generic demo
  • A real person from our team replies
  • No cold calls afterwards

Would you rather talk first?

Which area do you want to see in the demo?

With your work email we prepare the demo around your case.

In one or two sentences.

If you chose Maintenance (CMMS)

If you chose Field work (Field Service)

If you chose Facility Management

If you chose any other area

Only if you would rather we call you.

Data protection. Controller: AxisOne Group SL. Purpose: preparing the demo you request and replying to you. Legal basis: your consent and the request you make. Recipients: we do not disclose your data; Cloudflare (website) and Brevo (email notices and confirmation) process it on our behalf. Rights: access, rectification, erasure, objection, restriction and portability, at privacy@attendo.me. More information in the privacy policy.

What happens when you send it. Someone from our team reads what you tell us and writes to you to agree on a time for the demo. Our hours: Monday to Thursday 9:30 AM to 6:30 PM and Friday 9:30 AM to 2:30 PM, Spain time.