Skip to content
← cd ../services

cat services/ai-assistants.md

Answers your customers and staff can trust, from your own documents.

Chatbots and document assistants that answer from your policies, manuals and records, cite the source for every answer, and say "I don't know" instead of guessing.

cat who-its-for.md

Businesses whose team or customers keep asking questions that are already answered somewhere in their documents. Clinics, schools, law and finance firms, support teams, e-commerce.

Most AI chatbots are confident and sometimes wrong. Ours are built the other way round: they find the right passage first, answer only from it, and decline when nothing matches. You see the test results before launch.

cat outcomes.md

  • Fewer repeat questions reaching your staff
  • Customers get an answer at 2am, not the next working day
  • Every answer shows its source, so you can check it
  • Leads captured from the conversation and sent to you
timeline:
2 to 4 weeks
price:
On request

ls included/

What's included

  1. 01

    Website chatbot

    Answers visitors from your site content, books calls and collects contact details.

  2. 02

    Chat with your documents

    A private assistant over your internal files, with a citation for every answer.

  3. 03

    Fine-tuned models

    A model trained on your examples when a prompt alone is not enough, for your tone, format or task.

  4. 04

    Testing before launch

    A written test set and measured results, so you know how it behaves before customers use it.

cat work.log

Built and measured

Projects in this area, with the test results and the code public.

Kendot Legal

liveconcept buildLegal

A law firm website with a cited AI assistant for visitors, a private one for lawyers, and paid consultation booking from Google Calendar.

100%
Answer correctness on a 40-question test set
65/65
Citations checked against their source page
100%
Prompt-injection attempts resisted
  • Astro
  • Tailwind
  • FastAPI
  • Claude Haiku 4.5
  • Voyage embeddings
  • Postgres + pgvector

case study →: Kendot Legallive demo ↗code ↗

FlyFit Fashion Store

liveconcept buildRetail and e-commerce

An online fashion store with checkout that can't oversell, payments that survive duplicate webhooks, AI search and a shopping assistant that can't make up a price.

0
Items oversold with 200 buyers racing for 10 units
98.3%
Shopping assistant tasks completed (40 scenarios, 3 runs)
0
Made-up prices shown, audited against the database
  • Python
  • FastAPI
  • Postgres + pgvector
  • Next.js
  • TypeScript
  • Tailwind

case study →: FlyFit Fashion Storelive demo ↗code ↗

Naija Law RAG

liveLegal information

An assistant that answers questions on Nigerian law strictly from the official texts, cites every claim, and declines what the documents don't cover.

11/11
Citations verified against the source text
5/5
Out-of-scope questions correctly declined
8/9
Answerable questions answered correctly
  • Python
  • FastAPI
  • Claude
  • Voyage embeddings
  • BM25
  • Qdrant

case study →: Naija Law RAGlive demo ↗code ↗

Helpdesk RAG

liveIT support

An IT helpdesk assistant that answers staff questions from the company's own knowledge base, with a source for every claim and a clean "I don't know" for everything else.

6/6
Answerable questions answered correctly
18/18
Citations verified against the source
5/5
Out-of-scope questions declined
  • Python
  • FastAPI
  • Claude
  • Voyage embeddings
  • BM25
  • Postgres + pgvector

case study →: Helpdesk RAGlive demo ↗code ↗

ls services/

Often combined with

cat next-step.md

Find out what you could automate

Book a free 30-minute strategy call. You'll leave with at least one concrete idea, whether or not we work together.

Book a Free Strategy Call