Advisory

Most AI projects do not fail on the model. They fail on everything around it.

The workflow nobody redesigned, the data nobody owns, and the people expected to absorb the change. I design the system that survives contact with all three, and I build enough of it to prove it works.

How engagements are shaped

Four ways in. Most organisations start with a briefing or a diagnostic, and the diagnostic is what usually decides whether there is a bigger piece of work worth doing.

Start here

Board briefing

Half a day with your leadership team. Where AI actually applies to your operation, and where it does not.

Half day · fixed fee
Most common

Diagnostic

A written architecture and a sequenced ninety-day plan, scoped and priced before we begin.

2–3 weeks · fixed fee
Build

Architecture sprint

The design plus a working reference implementation your team can carry forward.

6–10 weeks · scoped
Ongoing

Executive AI Advisory

A senior architect at the leadership table while your organisation builds: setting direction, owning the technical decisions and keeping the board informed. Capped days, monthly.

Retainer · capped days

Selected work

Anonymised to sector. Each one started with an operational problem, not a technology.

Man-days of month-end reporting Professional services. The monthly reporting became a view of one model of the business, so the time now goes on reviewing the mismatches the system flags itself.

Healthcare R&D · Portugal

Clinical notes captured during the shift, and accurate enough to trust

Getting nurses' notes written down as the shift unfolds was only half the problem. The R&D team could not guarantee that what was written was clinically accurate.

I designed a language model working in the vocabulary of the CIPE nursing manual, paired with a clinical reviewer agent that checks each note and flags anything inconsistent for a person to review. The model drafts. The reviewer decides what needs a human.

ResultIn laboratory testing, more than 98% of ambiguities were correctly identified and sent for human review. Note-taking time fell by 45 minutes per user per shift.

Document-heavy operations

Document extraction that cost too many tokens to scale

Sending every document through a language model worked, and was far too expensive to run at volume.

I redesigned the pipeline so the model does as little as possible. A Python extractor reads each PDF, a lightweight classifier identifies it, and a script generated for each document provider pulls out the fields. The cost falls because of how the work is divided, not because of a cheaper model.

Result86% fewer tokens used, with similar extraction performance.

Non-profit sector

Funding calls found too late to answer, or not found at all

A group of NGOs needed to follow grant opportunities from international programmes down to the hyperlocal, and the calls surfaced too late to answer or never surfaced.

I built a crawling and classification system that gathers very different kinds of opportunity into one canonical database, then scores each against the organisation: how well it fits, how large the potential is and what pursuing it would cost.

ResultMore than 800 sources monitored, with a median time between a call being published and captured of under 24 hours.

Professional services

Month-end reporting that took 19 man-days

Every month, a team spent 19 man-days producing activity and status reports, then distilling them into a short executive overview and a decision matrix.

I designed a system that integrates the organisation's separate data sources into one canonical state-transition model of the business and derives the reports and the matrix from it. The reporting becomes a view of that model rather than something assembled by hand.

ResultFrom 19 man-days to 0.5, spent mostly reviewing the mismatches the system flags itself. It learns from that input, so the figure should keep falling.

Who this is not for

  • ✕Organisations looking for a proof of concept to show the board. I build things intended to stay in production.
  • ✕Teams who want a tool selected rather than a problem solved. The tool is the last decision, not the first.
  • ✕Anyone who needs the answer to be that AI is the answer.

Discuss an engagement

Tell me what is actually going wrong and I will tell you whether this is work I can help with. If it is not, I will usually know who can.

Prefer email? [email protected]

Engagements are contracted through Entropic Ventures Unipessoal Lda, Figueira da Foz, Portugal.