Sergio Rico Lucena

ProjectsB5

Evolutia

Adaptive training where the AI proposes and the person decides.

Role
Creator / Product Lead — AI-assisted development
Since
July 2026
Status
In development, with a private Android demo.

SummaryAerial view

Evolutia plans, logs and adapts strength training. An AI suggests changes to the next week, and nothing happens until the person reviews them. It started at the end of July 2026, when I started training in a conventional gym after CrossFit.

Review an AI proposal

Synthetic data

The AI proposes three changes for next week. Accept, edit or reject each one, then create the draft.

This demo needs JavaScript. The case below reads the same without it.

CaseOn foot

Lens

Problem

Logging and adapting training is only useful if an automatic suggestion cannot break the rules of the plan or change a week without anyone looking at it.

Decisions

  1. The AI proposes, the person applies

    BusinessA suggestion is a document to review, not an action. The person can accept, edit or reject each change.

    TechnicalThe model generates a TrainingProposal. Applying it creates a new draft week. It is never published or activated automatically.

  2. Deterministic rules around the model

    BusinessThe plan's rules hold whatever the model suggests. The AI works within them.

    TechnicalRules and permissions live in Postgres with row-level security and RPC functions. Edge Functions call OpenAI and validate what comes back.

  3. Test what cannot be checked by eye

    BusinessBefore showing it to anyone, the planning, logging and proposal flows had to pass automated checks.

    TechnicalThree separate suites: Bun for logic, pgTAP for the database and Playwright for end-to-end flows.

How I checked it

The planning, logging and proposal flows passed three automated test suites, and there is a private Android demo.

What I learned

Putting a person between the proposal and the plan made the product simpler to reason about. The rule that an apply only creates a draft removed a whole class of problems.

Role

Product, plan rules, limits of the AI, requirements, acceptance criteria and review. Codex implements a substantial part, with cross-review between ChatGPT and Codex.

EvidenceBelow the surface

Architecture

Plan and availability
Logged sessions
OpenAI
Postgres · RLS · RPC
TrainingProposal
Human review
Draft week
The model writes a proposal. Rules and a person stand between it and the plan.
  • Data
  • Person
  • AI model
  • Storage

The same flow, step by step

  1. The plan and the logged sessions are stored under database rules.
  2. OpenAI receives the context and returns a TrainingProposal.
  3. The proposal is validated against the plan's deterministic rules.
  4. The person reviews, edits or rejects each change.
  5. Applying creates a draft week. Publishing it is a separate, human step.

Product plates

  1. Plate 1 of 6Opening screenEditorial compositionSynthetic data
  2. Plate 2 of 6The weekEditorial compositionSynthetic data
  3. Plate 3 of 6Logging a sessionEditorial compositionSynthetic data
  4. Plate 4 of 6ProgressEditorial compositionSynthetic data
  5. Plate 5 of 6Check-inEditorial compositionSynthetic data
  6. Plate 6 of 6Proposal, review and applyEditorial compositionSynthetic data

Stack

  • React
  • TypeScript
  • TanStack Start
  • Supabase (Postgres, Auth, RLS, RPC)
  • Edge Functions
  • OpenAI
  • Bun
  • pgTAP
  • Playwright

Page last revised:

Next territoryVexploreWhere to explore

Pages

A1HomeB1ProjectsC1Professional systemsD1ExperienceE1SkillsF1AboutG1ContactH1Privacy

Projects

B2VexploreWhere to exploreB3NuboriaWhen to watch the skyB4AnuahHow to support each otherB5EvolutiaHow to adapt training

Professional systems

C2Reporting close automationC3Path-to-Conversion Analyzer

Actions

ESEspañolFRFrançaisDEDeutsch

Arrow keys to move, Enter to open, Esc to close