Skip to content
  1. Home
  2. Services
  3. AI agents
AI agents

AI agents built into your company

The Baller Company is a digital marketing and development agency based in Spain that builds AI agents inside companies, working in English with businesses across Europe. The agents connect to your tools and take on the repetitive work in customer service, sales, admin or operations. Anything with consequences is approved by a person. We start with one process, leave it measured and running, and what we build belongs to you.

Before you choose

Who can build AI agents for your company?

Your own team

With n8n, Make or Zapier, if the process is simple and someone technical has the time. It is the cheapest route, but maintenance and failures are on you.

A specialist freelancer

Quick and affordable for a first workflow. The risk is that everything depends on one person: ask for documentation and keep the accounts in your company's name.

An agency or consultancy

Worth it when the agent touches several systems, sensitive data or processes your revenue depends on. That is what we do: design it, build it, measure it and hand it to your team.

For a large corporate project with heavy regulatory risk, a big consultancy may be a better fit. To compare Spanish agencies that do both marketing and development, see our comparison of seven agencies, which includes us.

By area

Where the bottleneck usually sits

Customer service

Handles the questions that repeat — order status, lead times, returns, invoices — by querying your systems, not by making things up. What it cannot answer goes to a person with the context already gathered.

Sales

Qualifies every form that comes in, researches the company, scores it against your criteria and leaves it in the CRM with the summary written. Your rep starts the day with the list already sorted.

Administration

Reads invoices and delivery notes, pulls the data out, matches it against the order and flags what does not add up. Somebody stops typing and starts reviewing exceptions.

Operations

Watches stock, lead times and incidents and raises the alert before the customer notices. Puts together the reports somebody builds by hand every Monday.

Marketing

Drafts in your voice and with your data, checks that campaigns stay inside budget and builds the monthly report without anybody exporting anything.

Management

Pulls together sales, cost and campaign numbers every week, compares them against target and flags what has drifted. You stop asking for reports and start reading them.

Scope

What we do and what we don't

What we do

  • Agents that work inside your tools: email, CRM, ERP, online shop or WhatsApp
  • The connections to your systems, the rules and the control over what it may do alone
  • One process at a time, measured before and after
  • The documentation and training for your team to run it

What we don't do

  • Chatbots that answer without checking your data
  • Agents that decide payments, large refunds or legal matters on their own
  • Projects designed to cut headcount
  • Automating several critical processes at once
Why it compounds

One area saves hours. Several change the company

Automating customer service gives you hours back. Automating sales too means those hours go into selling. And when operations raises its own alerts, the sales team stops firefighting. That is why we do not sell a single agent: we sell an order to do it in.

  • 01The area that hurts most, first

    The one eating the most hours, or the one losing you customers. Measured before and after.

  • 02Then the one that feeds it

    Every automated process leaves clean data that makes the next agent more accurate.

  • 03And the team moves up

    Nobody becomes redundant: people stop doing the mechanical part and start deciding, selling and serving better.

How we build them

With limits, with a log and with an owner

  • It works with your data. It connects to your tools and only reaches what its task needs. Nothing is trained on your company's information unless you decide so.
  • It knows what it may do alone. We write down what it executes without asking and what needs a person to approve. Refunding €40 is not the same as refunding €4,000.
  • It leaves a trail. Every action is logged: what it read, what it decided and why. So it can be audited and corrected instead of trusted blindly.
  • Somebody owns it. You get the panel to watch it run and the documentation for your team to keep it. It is not tied to us.
  • It gets measured. Before we start we record how long the process takes today and what it costs. Three months in, we measure again. If it has not improved, it changes or it goes.
  • It starts small. One area, in production, genuinely working. The AI projects that fail are usually the ones that tried to start with everything.
Process

What does an AI agent project look like?

Four steps for the first process. The next ones build on the connections already in place.

  1. Step 1

    Audit and map

    With the people doing the work, we measure how long each task takes today and choose the process to start with.

  2. Step 2

    Limits and data

    We write down what the agent does alone, what a person approves, and which information leaves the company and which does not.

  3. Step 3

    Build and test

    We connect it to your tools and test it with the team who will use it, with human review wherever a mistake is costly.

  4. Step 4

    Live and measured

    Training, panel and documentation. Three months in, we measure again: if it has not improved, it changes or it goes.

Deliverables

What your company gets

  • The agent in production, connected to your tools
  • Written limits: what it does alone and what a person approves
  • A log of every action and a panel to watch it work
  • Documentation and training for your team to run it
  • The code, workflows and documentation belong to your company
  • The process measured before we start and three months in
Pricing

AI agent pricing

From 2,900 € First agent in production · 4 to 6 weeks

Reference price, excluding VAT. It is not a fixed rate: every project is quoted in its own proposal. It covers analysing the process, building it, testing and going live. Later agents cost less because the connections are already in place.

FAQ

AI agents

What do you build them with?
It depends on the process. We work with Make to connect the tools you already use. When the agent touches sensitive data or internal systems, we write it as custom code and connect it to the AI models through their API. We use whichever model on the market fits each task best: what makes the difference is what we build around it: the connections, the rules and the controls.
Is the agent mine, or do I depend on you?
It is yours. The code, workflows and documentation belong to your company, and you get the panel and the training for your team to run it. If one day you want to carry on without us, you can. With any supplier, ask for this in writing in the contract too.
Where is my data? Is it GDPR compliant?
Before we connect anything, we decide with you which information leaves the company and which does not. The agent only reaches what its task needs and, where required, the data is hosted in the EU. Nothing is trained on your company's information unless you decide so.
What does the EU AI Act require of an agent like this?
It depends on the risk of the use. A customer service, sales or admin agent is not usually high-risk, unless it assesses or makes decisions about people, such as screening job applicants or assessing someone's creditworthiness. If the agent talks to your customers, the Act requires them to know they are talking to an AI, unless it is obvious. The full text is Regulation (EU) 2024/1689.
What if the agent gets it wrong?
That is why we define up front what it may do alone. Anything with financial or legal consequences goes through a person. And because everything is logged, when something fails you can see exactly where and fix it.
Who maintains it when a tool changes or something breaks?
We agree it in the proposal: who monitors it, who fixes it when a tool or its API changes, and how quickly. Your team can run it with the documentation we hand over, or we can carry on looking after it.
Do I need my data tidy first?
Not entirely, but you do need to know where it is. Part of the first few weeks is exactly that. If your data lives in a spreadsheet and in two people's heads, you can still start — the first agent will simply be a simpler one.
How much does an AI agent cost?
The reference price for the first agent, excluding VAT, is shown above. Every project is quoted in its own proposal once we have seen the process, and it covers analysis, build, testing and going live. Later agents cost less because the connections are already in place.
Can I see client case studies?
Our case studies include three named real projects, the ABM strategies for Dcycle and Enginy and the Massive Ball website, and typical projects by sector that describe common situations, not specific clients. We do not publish client figures: their results are theirs. The most useful way to check whether we are a fit is to start with one small, measured process.
Is this going to put somebody out of a job?
It is not what we are after, and not what happens on the projects we run. What gets automated is the mechanical part: copying data, looking up an order, writing the same reply again. The person stays, handling what actually needs judgement. If your goal is to cut headcount, we are probably not the right agency.
What if I only want to try one process?
That is exactly how we recommend starting. One area, measured before and after. If it does not work, you will know in weeks rather than in a year.
Further reading

Before you choose a supplier

Getting started

What does your team repeat every week?

Tell us, and we will say whether automating it is worth it, what it would cost and how much time it would give back. If it is not worth it, we will say that too.