Services

Seven lines of work, four ways to engage

It starts with the business, not the tool. Every engagement is fixed scope and fixed price, and closes with documentation so your team runs the system without me.

What changed

Five years ago companies still bent their processes to fit whatever software the market offered, because building something custom was expensive.

Today we build solutions that adapt to the processes the company already runs — from the architecture up, and flexible enough to fit the budget.

Marcos de Bernard de la FosseFounder, Markit Ventures

The seven lines

01

Process diagnosis and redesign

Where the work actually goes: who decides what, which system is the source of truth, where the edge cases live. Then what to simplify, what to automate, and what to leave alone.

  • Mapeo de procesos
  • BPM
  • Entrevistas
  • Documentación

02

Solution architecture

The design decision before the build: what the system has to do, where judgment is genuinely required, and what a rule or a schema resolves better and cheaper.

  • Claude
  • Diseño de flujo de decisión
  • Validación por schema

03

App and custom build

When nothing off the shelf fits the way your business actually works, the solution gets built: an internal app, a client-facing tool, or the piece that closes the gap between two systems that were never meant to talk.

  • Apps internas
  • Portales de cliente
  • APIs
  • Bases de datos

04

Integration with your systems

The solution reads and writes in the systems you already pay for, not in a copy of them. Often the right integration is the cheap one the client will keep paying to run.

  • CRM
  • Airtable
  • QuickBooks
  • Google Workspace
  • MCP

05

Productized deliverables

A proposal, a report, a client brief: the judgment written down once, so the output stops depending on who happened to build it that day.

  • Claude Skills
  • Generación de documentos
  • Especificación de voz

06

End-to-end automation

The circuit running on its own, with a model only in the steps that need judgment. This is the line with the longest track record.

  • n8n
  • Make
  • Airtable
  • APIs

07

Generative production pipelines

For teams producing volume with generative tools, where the real risk is budget: a human gate before anything expensive runs, and a dry run on every stage that spends.

  • Python
  • Validación por schema
  • Routing de proveedores

How to engage

Fixed scope. Fixed price.

Every engagement starts with a free thirty-minute call to confirm the fit. Prices are the floor for that scope, not a starting bid.

01

AI & Process Diagnostic

USD 850 · fixed

One week

The entry point. A deliverable of its own, not a sales proposal in disguise. If the honest answer is that a process should not be automated yet, that is what the report says.

What you get

  • One to three processes mapped end to end
  • Opportunities ranked by impact and effort
  • An implementation roadmap you can act on without me
Book a Call

02

Agent Build Sprint

USD 4,500 – 9,000 · fixed

Two to four weeks

The core offer. Design, build against an isolated environment, and layer-by-layer validation before anything touches production.

What you get

  • Built against sandbox accounts and copies of your data
  • Validated in layers: logic, creation, delivery, full circuit
  • Technical documentation and an operating guide at close
  • Your team runs it without me. That is the point of the engagement.
Book a Call

03

Production Pipeline Build

USD 6,000 – 12,000 · fixed

Scoped per series

Parallel to the Build Sprint, not above it — a different buyer. For small production companies, content channels and agencies that want volume without generation cost running away from them.

What you get

  • Idempotent stages against a manifest, resumable at any point
  • A human approval gate before the expensive step, with no flag to skip it
  • Schema validation everywhere judgment is not required
  • A dry run on every stage that spends
  • Generation credits are excluded and paid by the client in their own name
Book a Call

04

Fractional AI Architect

USD 2,500 – 4,000 / month

Three-month minimum

The retainer, after a diagnostic or a build. Architecture, continuous implementation, and support on the systems already delivered.

What you get

  • Ongoing architecture and prioritization
  • Continuous implementation on the agreed backlog
  • Support and iteration on systems already in production
  • Team enablement so capability stays in-house
Book a Call

Scope and currency for projects outside the United States are quoted per project.

After the diagnosis, we build the solution that fits.

Not the most impressive one, and not whatever is in fashion that month: the one your stack supports, your budget sustains and your team can keep running once I am gone. The diagnosis is mine; for the build I bring in solution architects, so the project never depends on one person’s calendar.

What decides it

  • The tools you already pay for, before adding anything new
  • What the budget sustains month after month, not just at launch
  • What your team can operate and fix without calling me
  • What the process actually needs — sometimes a rule beats a model

FAQ

The usual questions

How I work, step by step
Where do most AI projects actually fail?

Not on the model. On the process underneath it. Nobody mapped who decides what, which system is the source of truth, or what happens when the edge case shows up. So you end up with a chatbot nobody opens twice.

Do I need a technical team to work with you?

No. I build on no-code and low-code tools that do not require developers, and I handle setup and training. Every engagement closes with technical documentation and an operating guide, so your team runs the system without me. That is the point of the engagement, not a consolation prize.

Is automation enough, or do I need strategy too?

Automating a broken process just makes broken things happen faster. That is why I start with a process audit: organize and simplify first, then automate. Strategy without execution is useless. Execution without strategy is expensive.

How do you make sure nothing breaks in production?

Everything is built against an isolated environment first — sandbox accounts, copies of the live data. Nothing touches production until it has been validated layer by layer: assembly logic, then creation, then delivery, then the full circuit end to end.

What size companies do you work with?

Professional services firms, agencies and remote teams of 2 to 50 people, with a document-heavy process that eats skilled hours. Not a fit: model training, infrastructure, or one-off prompt writing.

What happens if my processes are a mess today?

They get reviewed and organized first. The audit defines where to simplify before automating. If the honest answer is that a process should not be automated yet, that is what the report says.

Which tools do you actually work with?

Claude Code, MCP, Claude Skills, n8n, Make, Airtable, the QuickBooks API, Google Workspace, Trello, Gmail and Zapier. If a tool is not on that list, I say so, name the equivalent I do know, and offer to evaluate it during the diagnostic.

Let's talk

Send me the process that costs you the most time.

I will tell you whether it is worth automating before you spend anything. Thirty minutes, no commitment, no pitch deck.