AI automation · Barcelona and remote
AI automation for businesses: let the machine do the repetitive work.
Classic automation copies data from one place to another. With AI, it can also read, understand and make simple decisions: an email, an invoice, a PDF or a WhatsApp message. We design it, build it and maintain it around your business.
Talk about your caseIn short
AI automation combines automated workflows (n8n, Make or code) with language models that can read and sort unstructured information: emails, documents, forms or messages. That makes it possible to automate tasks that used to need a person to read them. BL Diseno is an AI automation agency based in Barcelona that also works remotely with companies across Europe, with written limits on what the system decides alone and what a person signs off.
What AI changes in automation
Until recently, you could only automate what followed fixed rules: “when a form arrives, create a contact”. Anything that meant reading free text (a client’s email, a PDF invoice, a contract) stayed manual.
Language models change that: they pull the data out of a document, understand what a message is asking and write a draft. Automation is still the backbone; AI handles the steps that used to need someone to read.
Examples of AI automation
Emails that sort themselves
Every incoming email is tagged (order, issue, invoice, sales), assigned to the right person and arrives with a draft reply.
Invoices and documents read by AI
Data from invoices, delivery notes or PDF forms is extracted, checked and entered in your software, with an alert for anything that doesn’t add up.
Qualified leads
Every enquiry from your website or a portal is summarised, scored and answered within minutes, even out of hours.
Reports that write themselves
The week’s figures are gathered and a plain-English summary reaches management every Monday.
Documents from templates
Quotes, proposals or contracts generated from your CRM data, ready to review and sign.
Search across your documentation
An internal assistant that answers from your procedures, contracts or product sheets and cites the source.
How we keep AI errors in check
- AI only decides what can be checked; everything else goes past a person before it leaves.
- Every run is logged: what came in, what the system did and who signed it off.
- Sensitive data is handled with business plans that exclude training, or with models hosted on your own infrastructure.
- We measure the result against how things were done before: hours won back, errors avoided, response times.
How we work with you
- 1
We listen
A first conversation, with no commitment, to understand the problem the way your team actually lives it. The fix is often simpler than it looks, and if so, we’ll tell you.
- 2
We propose
Fixed scope, timeline and price, in writing, before we start. We look for what makes sense for both sides: no open-ended hours and no surprises on the invoice.
- 3
We build
Short delivery cycles: you see real progress every week and test it on your own cases, not on a staged demo.
- 4
We stay
Maintenance, adjustments and direct support from the same person who built it. Everything is documented and in your name.
Frequently asked questions
What is the difference between automation and AI automation?
Traditional automation runs fixed rules on tidy data. AI automation adds the ability to read and understand messy information (text, documents, messages), which means tasks that used to need a person can now be automated.
Which tasks in my business can be automated with AI?
The repetitive ones that involve reading something and taking a simple action: sorting emails, extracting invoice data, answering frequent questions, summarising documents, qualifying leads or preparing reports. One first conversation is usually enough to spot the ones that pay off most.
Is AI automation safe if we handle client data?
Yes, if it’s designed for it: providers with data processing agreements, plans that exclude training, access limited to what’s needed and human sign-off on sensitive steps. We review it with you before we build, with the GDPR in mind.
How long does it take to set up AI automation?
A first, tightly scoped workflow can usually be tested within a few weeks. The exact timeline, scope and price are fixed in writing in the proposal, before we start.
Keep reading
Automation
We automate your company’s repetitive tasks: invoices, email, CRM, spreadsheets and reports. Using n8n, Make or custom code, always with human oversight.
n8n expert
n8n expert for businesses: workflow design, self-hosted setup on your server, AI workflows, migration from Zapier or Make, and upkeep. Barcelona and remote.
Email automation with AI
Sort, summarise and reply to your company’s email with AI in Gmail or Outlook: automatic labels, draft replies, data extraction and alerts for what’s urgent.
Case study: a studio that runs on agents
How BL Diseno works inside: shared memory, daily reports, automated prospecting and verified research with AI agents, and the rules that make it reliable.
How to implement AI in a business: 7 realistic steps for SMEs and professional firms
A realistic path to implementing AI in an SME or professional firm: find repetitive work, measure it, pick one pilot, check GDPR, build, measure and scale.
How to automate supplier invoices with AI, and what Verifactu and B2B e-invoicing mean for companies in Spain
How to automate supplier invoices with AI: intake, extraction, validation and ERP posting, plus where Spain's Verifactu and B2B e-invoicing rules stand.
Let’s talk
Tell us what you need. We reply within one business day.