Skip to content
← Folt Labs/Case study

Agnicio SSP

Their audit demanded the reason behind every score; the old system showed only the number. Now every score arrives with its explanation, and an audit trail records who changed what.

SectorAI · Asset management
TypeWeb application
Year2025

Problem

Their team lost hours each week to spreadsheets: risk scores nobody could explain, and an audit that demanded the reason behind each one. Legacy tooling gave the number but hid how it got there. Agnicio is the company one of our founders worked at before Folt Labs. They came back to us for this build.


What we did
  • Discovery of the process and written spec before the first invoice
  • Product design and UI system in Figma, validated against real data
  • Full-stack build on Next.js + Postgres + Supabase Auth
  • LLM steps integrated to explain scoring decisions, not to make them
  • Deploy, monitoring, and a handover packet for their internal team

Approach

We watched their team work for a week before writing code. We modelled the scoring pipeline as a sequence of explainable steps, not a black box. Every number links back to the supporting data and the input parameters. The LLM layer summarises the reasoning in human language but never makes the decision. The audit log shows exactly who changed what and when.


Stack
  • Next.js
  • TypeScript
  • Postgres
  • Supabase Auth
  • Tailwind
  • Vercel

Outcome
  1. 01Onboarding a new operator dropped from weeks to days
  2. 02Every scoring decision now carries an audit-ready explanation, generated automatically
  3. 03SSO + role-based access covers the split between analyst, audit, and management
  4. 04Running in production on Vercel with monitoring and weekly backups

See it running.

Faster to open the live site than to read about it. Public, no login required. Have a look around.

Visit →

Related services

The services behind this project.


More projects

Other recent launches.


Have a similar project in mind?

Tell us briefly what you are building. A reply lands within 1 business day, and we come to the first call with a written scope rather than a template quote.