---
title: "A one-week knowledge-assistant build at Nezasa | SamuylovAI"
description: "Built with Nezasa on an existing data platform, an internal assistant answered 55% of questions without an expert. The talk also showed how to estimate the value of time saved."
url: https://www.samuylov.ai/stories/the-45-hour-ai-build-that-returned-2-2-fte-a-year
language: en
---

Article · May 29, 2024

# A one-week knowledge-assistant build at Nezasa

On 29 May 2024, Denis Samuylov gave “GenAI for All: How SMEs can Harness Generative AI for Success?” at [GenAI Zürich](https://www.genaizurich.ch/), the conference he co-founded, at Technopark Zürich.

Two sentences, from two different rooms that year.

A large corporation, on stage at every conference: _we built a proof of concept and took it to production._

A mid-sized company, in the corridor afterwards: _should I be spending my time on this at all?_

The second question is the more serious one, and it rarely gets a straight answer. Enterprise case studies are told at a scale that doesn’t transfer – the platform team, the governance board, the seven-figure budget. A 100-person company hears them and concludes, correctly, that none of it applies.

![A talk slide titled Key outcomes, contrasting what generative AI means for large organisations and for SMEs.](https://www.samuylov.ai/_img/stories/the-45-hour-ai-build-that-returned-2-2-fte-a-year/stage.27e7e209.w1600.webp)

From the talk: what generative AI looks like for an enterprise, and for an SME.

## The arithmetic

Start small. A 100-person company working forty-five-hour weeks that frees one hour per person each week gains about 2.2 full-time equivalents of capacity. A focused assistant on an existing data platform can take about 45 hours to build.

Swap in your own headcount, hours and time saved, and count the cost of running the system. Our [AI ROI calculator](https://www.samuylov.ai/ai-roi-calculator) does the sums for you.

## The proof behind the slide

The talk paired the arithmetic with a real system. Together with Patrick Hammer, Co-Founder and Product Manager for Data & AI at Nezasa, we built Yoda: an assistant that answers questions from company knowledge, with links to its sources.

![A Slack question and answer with links to the wiki and knowledge-base sources.](https://www.samuylov.ai/_img/stories/the-45-hour-ai-build-that-returned-2-2-fte-a-year/yoda-answering-in-slack.275137d9.w1506.webp)

Yoda at work: asked in Slack, answered in the thread, with links to the pages behind the answer.

Nezasa measured 55% of evaluated questions answered without a product expert, and estimated the capacity released at roughly two full-time employees. The full story is in the [case study](https://www.samuylov.ai/stories/internal-knowledge-assistant-for-a-travel-technology-sme).

## Three delivery choices

**Define your goals, you must.** The first goal was simple: show useful access to company knowledge with a small build.

**The basics, you build.** Nezasa’s data platform already handled the plumbing, so the assistant only had to extend it to Confluence and Zendesk.

**Existing tech available to your users, utilize you should.** Yoda answered in Slack threads, where people already worked, and every answer could be rated with a thumbs up or down.

## Where a smaller team can start

Pick one workflow, check which foundations already exist, and estimate the capacity a focused build could free. Then measure what people actually gain.

![Attendees talking at a conference stand.](https://www.samuylov.ai/_img/stories/the-45-hour-ai-build-that-returned-2-2-fte-a-year/booth.e7d1e64d.w1600.webp)

Conversations continued at the stand.

A one-week build was possible here because the data foundation already existed. Keeping an assistant useful as its documentation and questions change requires ongoing operation and evaluation. See [Agents-as-a-Service](https://www.samuylov.ai/ai-as-a-service#pricing), or [Start a conversation](https://www.samuylov.ai/contact).

[Download as PDF](https://www.samuylov.ai/stories/the-45-hour-ai-build-that-returned-2-2-fte-a-year/pdf)

## Have a project in mind?

Tell us what you are building or improving. We'll help you choose a practical next step.

[Book an intro call](https://www.samuylov.ai/contact?book=1&topic=other)

## More stories

[All stories](https://www.samuylov.ai/stories)

[What artists learned about GenAI first](https://www.samuylov.ai/stories/what-artists-learned-about-genai-first) – Article · November 2024

[A Slack knowledge assistant for Nezasa, built in one week](https://www.samuylov.ai/stories/internal-knowledge-assistant-for-a-travel-technology-sme) – Case study · Nezasa AG · April 2024 · Questions answered without involving a product expert: 55% · Capacity benefit estimated by the client: ≈2 FTE
