Automate a process with AI agents
An agent does the repetitive part of a process. A person approves what matters.
Proof: invoices into the ERP, AI-assisted hiring at a global CX operator, a public services front desk.
First step: AI Diagnostic
Six processes where we already have AI working for mid-sized companies and enterprises.
TodayEvery document retyped into the ERP
With AIData read and matched to the bank statement; a person approves every record
TodayFive windows open to answer one question
With AIOne screen for every attendance, and an assistant that knows your services
TodayRecruiters screening every candidate by hand
With AIAI interviews and classifies candidates; people make the decision
TodayCritical logic nobody dares to touch
With AIAudited, covered by tests and rebuilt with agents, with a person reviewing every change
TodayShadow AI, no rules, no view of cost
With AIApproved tools, a register of use cases and an audit trail for the AI Act
TodayThin requirements, surprises found late
With AIAn idea becomes requirements, user stories, tests and wireframes, straight into your backlog
Short conversations where the hours go, then a written plan: opportunities ordered by impact and effort, and the first project named and sized.
Talk to an expertEach service line starts small, has delivered work behind it, and ends in something your people use and we can keep running.
An agent does the repetitive part of a process. A person approves what matters.
Proof: invoices into the ERP, AI-assisted hiring at a global CX operator, a public services front desk.
First step: AI Diagnostic
AI features inside the applications your people already use, with the cost of every call visible.
Proof: an AI tutor in production for children learning to code, an AI layer serving several education products.
First step: AI Diagnostic
We audit what you run, cover it with tests, then rebuild or evolve it with agents.
Proof: 20 gaps closed in an AI-built prototype, a platform MVP in two months, agents working inside low-code platforms.
First step: Code audit
Approved tools, training, a register of use cases and an audit trail for the AI Act.
Proof: a country AI framework for a European food retailer, presented to its head office as a model.
First step: Team training or AI Diagnostic
Support and evolution in hours packages or a dedicated squad, with the same people who built it. You are never left holding a system nobody understands.
Each entry point ends with a decision you can take on your own, and leads to one of the services above.
Two weeks, fixed scope, one written plan.
A production readiness review with a prioritised fix plan.
Hands-on sessions by area, on your real cases.
Our first AI work dates from 2023, and our AI products have been in client hands since 2024. Every story on this page comes from delivered or ongoing work.
The Claude Partner Network is how Anthropic works with the firms that put Claude into production for customers. The Services Track recognizes partners for building a certified delivery team, delivering Claude use cases for clients, and proving the work through public customer references.
Our people hold Claude certifications, and we are building from here.
About the programEvery engineer delivers with agents. Our career framework names the human line in every role: what AI may draft and what a person must decide.
About 30 functional tests written by an agent from a spec, then about four hours of human review. The typing goes; the judgement stays.
Every estimate starts from a written work list, is sized by an engineer and is checked by script before it leaves. No figure is typed by hand.
A Product Engineer owns the what. An Agentic Engineer owns the how. Agents do the repetitive work. You always talk to people.
We agree what to build and how to accept it.
Gate: scopeThe agent proposes a plan. A person approves it.
Gate: planAgents implement, test first.
An engineer reviews and owns the merge.
Gate: reviewTested, documented, traceable.
Phased deliveries with acceptance gates.
A dedicated team, monthly and renewable.
Blocks of hours, used as needed.
Four answers, in place from the first day. Built for the EU AI Act.
On your infrastructure when it must. Local models when needed.
No production personal data in prompts.
A person approves every change and every release.
Every AI call traced: model, cost and time.
Eight anonymised stories from retail, customer experience, accounting, education and insurance. One per tab.
Cashierless stores in Italy had to register every sale under Italian fiscal law, through a certified provider, by a fixed mid December deadline. The provider asked for payment data the client did not hold.
A week of working sessions with the client and the provider mapped the API and the data. One Bool developer and an AI agent then built it: the agent wrote and tested the code, the developer designed and reviewed it.
Anonymised client case · Delivered December 2025 · Java, fiscal API integration
Every manager ran financial simulations in a personal spreadsheet. The client needed one platform it could trust.
Two engineers and a product owner built it through agentic delivery, with a person reviewing every pull request.
Anonymised client case · In production · React, .NET, agentic delivery
A supervisor coaching tool with AI suggestions, prototyped fast with an AI app builder, had to become safe to run.
A production readiness audit first, then re-engineering on an enterprise stack with a security auditor agent, a pre-deploy audit and CI gates that fail the build.
Anonymised client case · .NET, SQL Server, CI security pipeline
A platform already interviewing and classifying real candidates, never built for enterprise security, scale or new countries.
A Bool team with an agent-based method took it from AI prototype to enterprise product.
Anonymised client case · Since May 2026 · TypeScript, agentic delivery
Accountants retype invoices into the ERP and match bank statements by hand.
Conto AI reads the Portuguese ATCUD code first, at no cost and with no AI. Only damaged photos, scans and foreign documents go to AI reading. Deterministic where it can be, AI where it must be.
Bool product · In production · Document AI, bank reconciliation
An AI tutor that helps without giving the answer away, using only the blocks a child has unlocked.
A hint service that works out the gap to the goal before asking the model for a short hint. It is in production: if a safe hint cannot be produced, nothing is shown.
Anonymised client case · In production · AI gateway, tracing and evaluations · 2026
Complex, long-lived OutSystems applications where one change touches backend, widget and frontend modules.
Claude working through the platform’s MCP server, locally in the IDE, on complex legacy modules.
Anonymised client case · OutSystems, MCP, Claude · 2026
Teams using AI with no shared rules, no view of cost and AI Act duties nobody owned.
A country framework in three streams, now presented to the international head office as a model for other countries.
Anonymised client case · AI Governance, AI Act · 2026
Thirty minutes to agree which door fits: an AI Diagnostic, a code audit, team training, or a first agent built on your real process. No commitment, and no forty page proposal.
Office Lisboa
R. do Centro Cultural 27A
1700-106 Lisboa
sales@bool.pt
A 30-minute call, then an AI Diagnostic or a code audit with a fixed scope and a written outcome.
A Product Engineer who runs discovery with your people, writes the spec and owns the backlog and the weekly demo. Agentic Engineers who build with AI agents and own every merge. Specialised agents handle specs, code, tests, reviews and documentation. You always talk to people.
The right one per task: Claude, OpenAI-compatible models or local open models. You can choose. An AI gateway lets us change models without touching your applications.
Not when it must stay. Models can run on your infrastructure, and agents reach your data only through registered tools.
You do, on acceptance.
We keep it running, in hours packages or with a dedicated squad.
Yes. Our agents work through MCP inside the low-code platforms you already run. See our OutSystems and Mendix practices.
We have AI work delivered or in delivery in retail, customer experience, education, accounting, public sector, insurance, construction, postal and logistics.
Yes. Nearshore from Portugal: your time zone, English by default, and teams that start small and grow with you. Offices in Lisboa, Porto, Açores and Castelo Branco.
Within one working day of your message.