How we build it

Every change approved, planned, reviewed, and proven.

Every change to this tool is approved before it starts, planned before it's coded, checked by a second AI, and proven before it goes live. Every step is recorded.

Try the Tradify answer tool →
Engraving of a tradesperson's workbench: an open, tabbed manual beside a phone showing a chat bubble, with tools around them
Plate I · The manual, made instant.

What RAG is

Look it up first, then answer

RAG stands for retrieval-augmented generation. Instead of asking an AI to answer from its general memory, we first retrieve the right passages from your own documents, then have the AI write the answer from them.

It works like an expert who checks the manual before answering, then shows you the page.

  • Grounded: answers are drawn from your own documents, not the AI’s general knowledge, so made-up steps are much less likely.
  • Checkable: every answer links the articles it drew on, so anyone can confirm a step before acting on it.
  • Current: when an article changes, the next update of the help centre brings the new version into answers. No retraining.
  • In your control: you choose which documents go in.

RAG explained · a beginner's guide (PDF)

New to RAG? Ten slides, plain English, using Tradify as the example.

Read the guide

Read the guide ↗Download PDF ↓

The answer path

1 · Ingestion

Help centre articlesPublic or approved private documents
↓
CrawlReads every article
↓
SplitInto short passages
↓
EmbedMaps each passage's meaning

2 · The special database

Vector databaseEvery passage is stored with numbers that capture its meaning.passage 1 → [0.12, −0.48, 0.91 …]
passage 2 → [0.07, 0.33, −0.25 …]
passage 3 → [−0.61, 0.18, 0.44 …]

2,631 passages live

● Chat session

How do I turn an accepted quote into a job?

Illustrative example
Here are the steps
1. Open the accepted quote.
2. Choose to create the job.
3. Check the details, then save.
Sources
Help article ↗
Ask a question…→
Your question, searched by meaning → closest passages, used to write the answer

Identify the gaps

Find what your help centre is missing

When a question can't be answered well, that's useful information: it points to an article your help centre doesn't have yet, or one that needs rewriting.

01 · Today

Store

The tool tells people when it can’t find an answer, and questions with only weak matches are logged.

02 · Next

Group

Every unanswered question kept in people’s own words, with similar ones grouped so you see the topic and how often it comes up.

03 · Next

Suggest articles

A weekly report with a suggested article title and outline for each group, for your help desk team to write.

By the numbers

The Tradify example so far

Article and passage counts are live. The cost covers the AI model for each answer; hosting and the database are a fixed monthly cost, not per question.

826help articles indexed
2,631searchable passages
1,000+questions answered
under 20cAI cost per question

The answers

Where the answers come from

The tool is built to answer only from your help-centre articles. It finds the most relevant passages, writes a step-by-step answer from them, and links the articles it drew on, so you can check it.

If the articles don't cover a question, it's built to say so instead of guessing.

The stack

What it runs on

Vercel for the product experience, Supabase for state, n8n for workflows, and Cloudflare at the front door.

A full build record

Since October 2026, every Issue, plan, review and change for this tool is recorded. Ask us and we'll walk you through it.

Ask for a walkthrough →

For your business

Need a tool like this, built the same careful way?

Talk to us about having your own knowledge base tool, built on your help documents.

I need this tool for my business