JAVIER OLIVIERI, home
ESEN
Book a call

Hybrid approach

AI where it adds value. Reliable code for everything else.

I don't use AI for everything. I apply it where language, documents, images or context have to be understood, and I handle rules, calculations, permissions and integrations with traditional software. That way your company gains productivity without overpaying or taking unnecessary risks.

A concrete example

Quoting from a floor plan

AI

Reads the drawing and the customer conversation.

CODE

Applies pricing, business rules and stock. Validates everything.

PERSON

The team reviews the quote and sends it.

See the D'Angelo case →

Try it

Does this task need AI?

Tap a task and see what it is best solved with.

THE TASKRead a floor plan or a scanned PDFBEST SOLVED WITHAI + validation

An image has to be interpreted. AI extracts the data and code checks that it makes sense before moving on.

How a task flows

Five stages. Only one uses AI, and only if needed.

  1. 1 · InputA task arrivesEmail, drawing, form or chat
  2. 2 · RulesRoutingCode decides what it needs
  3. 3 · Selective AIInterpretsOnly when understanding is needed
  4. 4 · ValidationChecksAmounts, limits and, if needed, a person
  5. 5 · OutcomeReady to useA quote, a reply or a record

Path: input → rules → selective AI → validation → outcome

Decision matrix

Code, AI or a person?

TASK CODEAI PERSON
Calculate a price with known rulesCode Primary——
Read a floor plan, a photo or a scanned PDFCode SupportAI Primary—
Understand the intent of a message—AI Primary—
Validate stock, limits and permissionsCode Primary——
Summarize a conversation for a salesperson—AI PrimaryPerson Support
Sync CRM, spreadsheets and systemsCode Primary——
Approve an out-of-policy discountCode Support—Person Primary

Illustrative examples. Each real case is assessed during discovery.

Before adding a model

What I weigh, in business terms

The goal is net operating benefit: every model call should pay for itself.

Cost per operation

What each run costs at your real volume.

Time saved

How many hours it frees up, and for what.

Reliability

How often it gets it right unaided.

Latency

Whether the answer has to be immediate.

Maintenance

What breaks when something changes.

Exceptions

Who handles the edge cases.

Governance

What data leaves your company.

Under control

How I keep it reliable

01

Validation

The model proposes; code verifies amounts, formats and limits before moving on.

02

Logging

Every step is logged so you can see what happened and why.

03

Oversight

If confidence is low or the impact is high, a person decides.

04

Cost caps

Usage limits, right-sized models and paths with no AI.

Frequently asked questions

Questions about the approach

Still have a question? We'll talk it through on the call.

If the task has clear, stable rules, use code. If it requires understanding text, documents, images or intent, use AI, always followed by validation. If the decision has serious consequences, a person approves it.

Where would AI make sense in your business?

We'll work it out in 30 minutes, with your real process on the table.

Book 30 min