mourente.ai

Alejandro Gutiérrez Mourente

Manual processes retired. In production in weeks.

Former F-18 pilot and Operational Safety Officer. I retire manual processes in regulated companies, built end to end.

How much are manual documents costing your company? Three minutes, and you see the number before anyone asks for your email.

What does your company do?

Or write to me directly:alex@mourente.ai
Cockpit portrait of Alejandro Gutiérrez Mourente, oxygen mask on, level flight

By the numbers

€5M/yr

Manual process retired

DocFields · projected 12-mo run-rate

100+ FTE

Equivalent workload

Purchase validation · field UAT

1+ yr

In production

Onboarding engine, 35 nodes, 3 languages

323,110

Legal documents searchable

Ponente, validity checked nightly against the BOE

9

Products shipped solo

5 prod, 2 pre-prod, 1 alpha, 1 build

Calculate your paperwork tax, 3 minutes

Your company is paying people to read documents, copy fields, and chase each other for approvals. I find that process, I put it in front of its own numbers, and I retire it: specified first, built end-to-end, in production with real users in weeks. €5M a year retired so far, 100 people worth of work, in one regulated group.

One person means one accountable. You get the same builder from the first call to the first production incident. And you never depend on me: every system ships with the spec it was built from, every decision written down, tests on every delivery, and a handover your team can run without me.

Strategy, execution, and the on-call phone number. One person, accountable.

Selected work

Three systems in production or user testing, two of them open to try live.

DocFields.ai

Situation: a regulated group extracting fields from 34 document types by hand. Result: €5M/year retired, one normalized output, live in production.

Twenty-four enterprise processors, confidence-tiered fallback, one normalized output. Most contracts stop at the cheapest tier.

Design rationale
Domain
Document intelligence
Stack
Python, Document AI, Anthropic, OpenAI
Status
Production, docfields.ai
Scope
24 processors, €5M/yr manual process retired (projected, 12-mo run-rate)
NOYESNOYESDocument receivedREGEXRegex parser · 4 detectors~0 cost · < 50 msCritical fieldsextracted?DOC AIDocument AI · 24 processorsDNI · vehicle reg · invoices · contractsConfidence≥ threshold?VISIONVision · Anthropic | OpenAIclaude-sonnet-4 · gpt-4o · selectableUNIFYNormalize + provenancesingle shape · provider trace · signature checkStructured payload out~70% of docsstop here.LEGENDStart / EndStepFocal decisionDecisionMergeConvergent output

Auto Financing Onboarding

Client portal for an auto retail group, powered by DocFields.ai

Cross-document conflict detection, append-only attestation per field. No human keystroke between document upload and the underwriting payload.

Design rationale
Domain
Client onboarding
Stack
Next.js 16, Hono BFF, GraphQL, DocFields.ai
Status
Pre-production
Scope
Auto-financing onboarding for a multi-tenant dealer group
Try it liveView the full diagramSynthetic data

Business Management System

Situation: 100+ people re-reading purchase files. Result: files clear on their own; operators see only what disagrees. Field QA: nine findings, closed in 48 hours.

Every field on the contract cross-checked against every other document in the bundle. Most files clear without an operator touch.

Design rationale
Domain
Backoffice automation
Stack
Multi-tenant BMS, DocFields.ai, cross-validation engine
Status
Pre-production, UAT
Scope
100+ FTEs of projected equivalent workload
Try it liveView the full diagramSynthetic data

More work

  • Onboarding Questionnaire

    Thirty-five nodes. Thirty-four document types. Three languages. The graph decides which papers a customer must upload, and which stack to demand when the easy answer fails.

    Production, 1+ yearDiagram
  • Business-Native Assistant

    It knows the case, the document, the calendar and the law that applies, because it runs inside the system that holds them. Every capability gated per tenant. Every action traced.

    Production, multi-tenant rollout
  • Prism Engine

    Thirty-six primitives, intensity-scaled, anchor-grounded to the verbatim review text. Reputation noise becomes a queryable underwriting signal.

    Engine in productionDiagram

My product

Ponente

Spanish law, cited and in force.

Ponente answers legal and tax questions with the exact article or ruling, whether it is still in force, and a link to the official source. I designed it, built it and run it.

323,110

documents of Spanish and EU law and case law

18

legislations: the State and the 17 regions

Nightly

validity checked against the BOE

47

curated legal areas

Two verifiers with different lenses check every report: one that each cited article exists and says what the draft claims, one that it was in force.

Design rationale

In use for months inside a leading Spanish law firm, and by independent lawyers through ponente.ai.

Claude, MCP, Qdrant, Qwen3 embeddings, PostgreSQL, Temporal, Inngest, Next.js, Hono, LiveKit, Deepgram

Visit ponente.ai

Three ways in. Each one ends with something in users' hands.

Somewhere in your company a process still runs on people re-reading documents. That is the one I retire first.

Calculate your paperwork tax, 3 minutes

Diagnostic

Two weeks. One process, on paper, with its price tag.

I map the process, measure what it costs you today, design the system that retires it, and write the plan. You keep the document whether or not we continue.

Fixed fee · credited against the pilot

Pilot

Six to eight weeks. One process, in production, with real users.

End to end: data model, extraction, rules, interface, integration with what you already run. Specified before it is built; tested on every delivery; handed over with the decisions written down.

Half on start · half when it is in users' hands

Retainer

Month by month. The next process, and the one after.

Same builder, same method, a standing capacity to keep retiring manual work and to answer the phone when production calls. Priority on your roadmap, no re-onboarding.

Monthly · cancel with a month's notice

If the diagnostic finds no case worth building, I say so, and you keep the report.

F/A-18 Hornet in vertical climb

Decade as a fighter pilot.

A decade as a fighter pilot and Operational Safety Officer in the Spanish Air Force. Operational discipline transferred to software architecture: systems either work under pressure or they fail people. That standard runs through every project here: the audit trails, the deterministic guards, the field-level provenance.

Portrait of Alejandro Gutiérrez Mourente

Thirty minutes. One process. A number.

If you are a CTO, head of operations or founder in a regulated business, write for a diagnostic call. You leave with three things: which process to retire first, what it costs you today, and whether I am the right person to do it. If there is no case, I say so.