QQuantum.ai is an AI development company and engineering studio in Barcelona, Spain. We build custom AI agents, retrieval-augmented generation (RAG) systems and workflow automation for enterprises and startups, with evaluation, human oversight and code delivered to your repositories.
Introduction transcript. Client: I’ve got ideas. And a lot of busywork. A little help? Qubi: Hi! I’m Qubi, from QQuantum. We build AI agents and automation. Connected to your business. Client: I’m still in charge? Qubi: Always. Your rules. Client: I like that. Qubi: Custom systems. Code you own. Less busywork. More room for ideas.
Apps, platforms and campaigns for these teams, long before the AI work. Every one is written up on the work page — what we did, and where our part ended.
Most real systems touch two or three of these. Pick one to see what's inside — or let it cycle.
LLM orchestration, retrieval systems, legacy modernisation and secure data pipelines — the structural core of enterprise AI.
Agents that carry a role end to end — sales, support, analysis and internal operations — and hand the hard cases to a person.
Explore Autonomous Employees →Removing repetitive process work with systems that reason, not just rules that branch — across systems that were never designed to talk.
Explore Intelligent Automation →Marketing execution at machine scale — programmatic content built on real data, outreach that is not generic, and forecasting from your own history.
Explore Algorithmic Marketing →Interface, brand and product design for AI-native software — and teaching agents to write and design in your voice.
Working software in weeks — prototypes built to answer a question, not to impress, and proof that survives a technical diligence question.
Every system we ship has the same bones. Pick a job, then pick any stage to see what it does — and where it's documented.
Everything the system knows comes from your own documents and systems, ingested with their access rules — nothing it can see that the user couldn’t.
Retrieval pulls the exact passages that answer the question, so every claim can point back to where it came from.
A pinned model, read-only tools by default, a step limit, and retrieved content treated as data — never as instructions.
Policy checks and a confidence threshold agreed in discovery. Below it, the system stops and hands over instead of guessing.
Connected through official APIs or MCP, rate-limited, and every action logged and auditable.
The hard cases reach a person with a briefing — and that person can overrule anything the system did.
Cost, latency and quality are traced per step, so drift shows up on a chart before it shows up in a complaint.
We don't have a favourite. Tell us what the system has to do, and see which families we'd reach for first. Drawn from our model pages — a starting point, not a benchmark.
| Family | Long-running agents & code | Very long documents | Images & visual docs | Runs on your hardware | European provenance | Many languages | Cheapest at volume | Fit |
|---|---|---|---|---|---|---|---|---|
|
Claude
Enterprise coding and long-running agents
|
Yes | No | No | No | No | No | No | — |
|
GPT
Computer use and a million-token window
|
Yes | Yes | No | No | No | No | No | — |
|
Gemini
Long-context and multimodal strengths
|
No | Yes | Yes | No | No | No | No | — |
|
Llama
Self-hosted, on your own hardware
|
No | No | No | Yes | No | No | No | — |
|
Mistral
European open weights, Apache options
|
No | No | No | Yes | Yes | No | No | — |
|
Qwen
Broad sizes, strong multilingual coverage
|
No | No | No | Yes | No | Yes | No | — |
|
DeepSeek
Visual documents, coding, open weights
|
No | No | Yes | Yes | No | No | Yes | — |
|
Small language models
1B–14B: most tasks at a fraction of the cost
|
No | No | No | Yes | No | No | Yes | — |
Jev routes each task to the model that fits it, with typed outputs and confidence gates. Published benchmarks included.
Jev model routing →Move the sliders to match a process you run today. The estimate is yours, not a promise — it leaves out build and review time, which the ROI guide walks through.
Arithmetic on your inputs only: tasks × minutes × the share an agent handles × your hourly cost. Not a measured client outcome.
It finds the journalists who would actually write about you — staff and freelance, across national, business, broadcast and trade desks — reads what they've published, and writes each one an individual pitch.
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
48 industries in 6 groups. Pick a group to see each industry and the problems we're asked to solve there.
Labs, trials, research institutes, chemistry and farming: work where the evidence trail is the product.
Literature and patent intelligence, ELN agents, protein design pipelines and dossier drafting for biotech, with every claim cited to source and unpublished data kept on your own infrastructure.
Protocol drafting, site feasibility and TMF quality control for sponsors and CROs, built for ICH E6(R3) with audit trails and a named person accountable for every decision.
Grant writing, systematic review screening and FAIR research data management for universities and institutes, on your own repositories, with every claim cited and the researcher as author.
Formulation search, REACH and SDS authoring support and materials discovery built on your own lab records, run on your infrastructure, with a qualified person releasing every safety document.
Crop and drone vision, agronomy advisory agents and CAP paperwork for agtech firms, co-ops and advisers, validated on local field data with agronomists and farmers deciding.
Product, building, fashion and device design, and the factories and dealerships behind them.
AI for production, quality and supply chain in industrial settings.
AI product design for hardware teams: concepts, DFM checks, should-cost and design search wired into CAD and PLM. Findings cite your own rules; a designer signs off every release.
AI for architecture and engineering practices: planning statements, specifications, BIM checks and bids drafted from your own archive, every clause sourced, a registered professional signing.
AI in construction for contractors: takeoff and estimating, site progress from photos, RFI and submittal review inside Procore or ACC. A named person signs every bid and response.
AI in fashion for brands and makers: tech packs drafted from your blocks, trend signals read against your sales, 3D sampling and product content, with a designer signing off every style.
AI for beauty brands under EU Regulation 1223/2009: claims linked to evidence, PIF assembly, shade matching and formulation research. The safety assessor and Responsible Person sign.
AI for device makers' regulatory work under MDR 2017/745, ISO 14971 and IEC 62366-1: drafts and cross-checks with citations, validated for your QMS. A qualified person signs every document.
AI in automotive beyond the vehicle: dealer and aftersales agents on your DMS, fleet operations from telematics, type-approval documents. Safety, finance and approvals stay with people.
Property, energy, networks, ports, mines and freight: physical assets run on documents and forecasts.
Document pipelines, exception handling and planning support for freight, ports and supply chains.
AI for real estate owners, managers and brokerages: lease abstraction, data-room review, listings and tenant operations, with every term cited to its source document and a person signing off.
AI in energy and utilities: renewables permitting, probabilistic load and generation forecasts and customer operations, read-only to operational systems with an engineer accountable.
AI in telecom: NOC alarm correlation, customer care grounded in billing and live network status, and field dispatch, on your OSS/BSS with engineers approving every network change.
Maritime AI on the shore side: ship documents cross-checked, port calls coordinated on one timeline and FuelEU and EU ETS data reconciled, with the master and agent still signing.
AI in mining for explorers and operators: geological reports, safety inspections and environmental permits read with citations, and a competent person signing every determination.
Hotels, travel, food, wine, media, games, sport, events, culture and retail: where the customer feels every answer.
AI for merchandising, support and demand forecasting in retail.
AI for hotels: multilingual guest messaging, review replies and pricing support, connected to the PMS and answering only from the hotel's own facts. Staff approve anything that commits the hotel.
AI for travel companies, tour operators and DMOs: itinerary agents on live supplier inventory, operations automation and destination content. A person confirms anything that becomes a contract.
AI for restaurants built on POS, recipe and supplier data: menu engineering, supplier ordering and digital HACCP records. Allergen information and food safety decisions stay signed off by a person.
AI for wineries and distillers: label and export compliance checks, direct-to-consumer marketing and vineyard imagery. Labels, shipments and treatments stay with the people accountable for them.
AI in journalism and publishing: newsroom research agents, archive search and AI content licensing tooling, with every answer cited and an editor accountable for what is published.
AI in gaming for studios: LLM NPC dialogue, AI-assisted localisation and player support, built into your engine and pipeline, within limits writers and leads set.
AI in sports for clubs and federations: club operations, performance analytics and fan engagement, with athlete health data protected and coaches making the calls.
AI event planning for organisers: call-for-papers and speaker operations, an attendee concierge and exhibitor management, built on the event platforms you already run.
AI in museums, heritage and auction: cataloguing, provenance research and multilingual guides inside your collection system, with curators signing every record.
Finance, insurance, law, accounting, recruitment, agencies, IP, translation and security teams.
AI in banking, lending and insurance where decisions must be explainable and auditable.
AI for contract review, research and discovery, with citation as a hard requirement.
AI features inside a software product, and AI inside the team that runs it.
Claims triage, underwriting support and fraud detection, designed for a regulated decision that a person still signs.
AI for accountants: bookkeeping agents, Verifactu and e-invoicing readiness, and a client query desk, built on Xero, Sage or A3. The model proposes; a qualified accountant posts and signs.
AI in recruitment for agencies and in-house teams: CV evidence with bias audits, outreach and interview scheduling, built for the EU AI Act’s high-risk rules. A recruiter makes every decision.
AI for marketing agencies: white-label AI builds for your clients, on-brand production at scale and client reporting where every figure is computed from source. You keep the client.
AI patent tools for IP firms: prior-art search, drafting support and portfolio monitoring, with confidential disclosures never used for training and a qualified attorney signing every filing.
AI for translators and LSPs: glossary-aware LLM translation, quality estimation and terminology management inside Trados, memoQ or Phrase. Fluency is easy; the client’s terminology decides it.
AI in cybersecurity for SOCs: alert triage, threat intelligence and NIS2 and DORA evidence, built to treat every log line as untrusted. Read-only by default; an analyst approves any action.
Care, education, charities, government and climate reporting: accountable decisions with a person behind them.
AI over clinical and administrative data, built for privacy and traceability.
AI for public bodies: procurement reality, data sovereignty, transparency duties and the records an audit will ask for.
AI in education for schools, universities and edtech: grounded tutors, course authoring and admissions support. Grades, admission and progression decisions stay with a named person, as the EU AI Act expects.
Dental AI for the front desk of practices and private clinics: booking, recall, treatment plan explainers and insurance admin, wired into the PMS. Diagnosis and clinical advice stay with the dentist.
AI in veterinary practice: intake routing, an AI scribe for SOAP notes and client reminders, built into the PIMS. Diagnosis, prescribing and every clinical record stay with the vet, who signs.
Administrative AI for therapists and clinics: intake, scheduling and note drafts a clinician signs. We never build AI therapy, assessment or crisis handling; any sign of risk goes to a person at once.
AI for nonprofits and charities: grant drafts from your own evidence, donor CRM hygiene and impact reporting. Staff stay the authors, and donor consent and beneficiary data stay protected.
Sustainability data from invoices, ERP and suppliers mapped to ESRS and the GHG Protocol, every figure traceable to source. Your team owns the disclosure; your auditor gives the assurance.
Geospatial AI on Sentinel, Landsat and commercial imagery: change alerts, crop and land signals and risk layers delivered into your GIS, validated on your own ground truth.
No pilot purgatory. Each phase ends with something you can check, and the quality bar is written down before the first line of production code.
agent = Agent(
model=MODEL_PINNED, # upgraded deliberately, behind an eval gate
tools=[
search_docs, # read-only
fetch_account, # read-only, scoped to the caller
create_ticket, # write, rate-limited
],
# Retrieved content is data, never instructions.
untrusted_sources=[DOCS, TICKETS],
max_steps=8, # bounded - no runaway loops
)- name: Evaluation suite
run: |
uv run evals/run.py \
--set golden \
--baseline main \
--fail-under 0.92
# Retrieval is measured separately. A generation score that
# drops because retrieval regressed is a misleading signal.
- name: Retrieval recall
run: uv run evals/run.py --set retrieval --fail-under 0.88Answer three questions and the table picks the deployment we'd start from. Every option is one we build.
| Where the model runs | The provider’s infrastructure | Your cloud account, in a region you choose | Hardware you own, or rent in a data centre | An isolated network |
|---|---|---|---|---|
| Data leaves your network | Yes — to the provider, under a DPA | It stays in your cloud tenancy | No | Never — no outbound connection at all |
| Models available | Frontier proprietary and hosted open models | Open-weight, plus models your cloud provider offers | Open-weight models | Open-weight models, updated deliberately |
| Who operates it | The provider runs the model; we build the system | You, with us | You, with us — or we run it | You, with our runbooks |
| Best when | Speed to value matters and the data allows it | Data must stay in your tenancy and region | Regulation or sovereignty rules out the cloud | Nothing may touch the internet |
| Deployment Options Compared → | Data Residency & Sovereignty → | On-Premise AI → | Air-Gapped Deployment → |
The questions teams argue about before they build. Flip a card for the short answer — the page has the long one.
When to retrieve, when to fine-tune, and why the answer is usually retrieval first.
When an off-the-shelf AI product is the right call and when it structurally cannot be.
The real cost and time comparison between hiring an AI team and engaging one.
Comparing the two on the axes that decide an enterprise deployment.
Where Zapier, Make and n8n stop being enough, and what replaces them.
The difference that matters: an agent takes actions and can be wrong in ways a chatbot cannot.
Where your models run, compared on cost, control, latency and the effort nobody budgets for.
The capability gap, the cost inversion and the licence terms that decide this more often than benchmarks do.
The studio is in Barcelona. The work reaches 24 cities — hover one to see it, click to read how we work there.
Facts about how we work, not measured client outcomes.
The best fit depends on your workload, data constraints and team. Compare agencies using relevant shipped work, evaluation methods, deployment options and code ownership. QQuantum.ai is a Barcelona-based option for enterprises and startups seeking agents, retrieval systems and automation, with client-owned code and a documented handover.
Whichever fits the workload. We are model-agnostic and route across Claude, GPT, Gemini, open-weight models and our own Jev — chosen per task against an evaluation set, not by habit.
You do. Everything is built in, and delivered to, your repositories, with runbooks and a documented handover so your team can own it.
Yes — on-premise, in a private data centre, or fully air-gapped. The table above shows where we would start.
No system can promise it never gets something wrong. We ground answers in your sources with citations, measure quality against real data before and after launch, and set guardrails that stop and escalate rather than guess.
Thirty minutes, no deck. You describe the problem; we tell you whether it is one worth engineering — and if it is not, we say so.
Tell us the job you would hand over if you trusted a machine with it. In one 30-minute call we will tell you whether it should, what it would take — and if it should not, we will say so.
30-minute technical call · no deck