Tridasoft

AI

RAG

We build systems that answer from your documents and show where the answer came from.

The situation

The knowledge sits inside documents but finding it takes time. Locating the right document often takes longer than asking the question.

Our approach

We make the documents searchable. When a question comes in, the relevant passages are found and the answer is built from them.

What we do

  • Document processing and chunking
  • Semantic search infrastructure
  • Source attribution and citation
  • Document access by permission
  • Measuring answer accuracy

Technologies we use

Backend
Node.js · Express · PHP · Payload CMSNode.js speaks the same language as the frontend in most projects; we use PHP where only shared hosting is available.
Database
PostgreSQL · Supabase · SQLite · MySQL · Prisma · DrizzlePostgreSQL for multi-user, relational work; SQLite for small, single-site setups.
Servers & hosting
Linux (Ubuntu) · Nginx · PM2 / systemd · Let's EncryptA dedicated Linux server is enough for most projects and keeps costs predictable; server access is handed to you.
AI
Claude API · Gemini APIWe pick the model by the sensitivity and cost of the task, and state in writing where your data goes.

How we work

  1. 01

    Discover

    A map of the current state and a prioritised list of needs.

  2. 02

    Define

    A scope document, success criteria and a schedule.

  3. 03

    Design

    A clickable interface prototype and the design system.

  4. 04

    Develop

    Working builds delivered at regular intervals.

  5. 05

    Test

    Test scenarios, a closed bug list and an acceptance test signed off by you.

  6. 06

    Deploy

    The live system, technical documentation and a hand-over session.

  7. 07

    Grow

    A usage report and a prioritised improvement plan.

Common questions

Which document formats are supported?

PDF, Word, Excel and plain text are commonly supported. For scanned documents we add a text extraction step.

Can everyone access every document?

No. Permissions work at document level, so a user only gets answers from documents they are allowed to see.

Let's talk about this

A short call to get clear on what you need. We will tell you plainly which approach fits.

Start your project