Skip to main content
This guide walks you through creating your first AI assistant from scratch. By the end, you’ll have a configured assistant ready to use — and optionally shared with your team.
Time to complete: 5-10 minutes
What you’ll build: A custom AI assistant configured for your use case
What you’ll learn: The three creation paths, configuration basics, and testing in chat

​
Prerequisites

1

Create an Account

Sign up at app.quiva.ai
2

Verify Your Email

Check your inbox and verify your email address

​
Three Ways to Create an Assistant

QuivaWorks offers three paths to create an assistant:

Create with AI

Start from a blank assistant with just a name. Best for building a configuration from scratch.

Clone Assistant

Duplicate one of your existing assistants as a starting point. Best when you have something similar already.

Add from Marketplace

Install a pre-built assistant from the community. Best for common use cases with a head start.
In this guide, we’ll use Create with AI — the fastest path for most people.
Despite the name, this path doesn’t generate any configuration for you — it’s the quickest way to land on a new, empty assistant that you then fill in yourself. If you’d rather start from a working configuration, Clone Assistant or Add from Marketplace may suit you better.

​
Step 1: Start Creation

  1. In the left sidebar, navigate to Assistants
  2. Click the Create Assistant button
  3. Select Create with AI
A dialog appears with two things to fill in:
  • Type — Private (visible only to you) or Team (visible to everyone in your account)
  • Assistant Name — a name for the assistant
Click Create.
There’s no description or instructions field here — the assistant is created empty, with everything else configured in the steps below.

​
Step 2: Fill In the General Tab

You’ll land on the General tab of the assistant editor. This is where the assistant starts empty — name and description are the only things carried over from creation, and description is still blank.

​
Name & Description

Give your assistant a clear name and description that team members will recognise:
Whether the assistant is Private or Team was set when you created it. To change that later, open the assistant’s settings and switch it there — team members won’t be able to use it until you do.

​
Step 3: Write Instructions

Click the Instructions tab. This is where you write your assistant’s role, personality, and behaviour — the most impactful part of your configuration, and where the real setup work happens:
Good instructions include: role, responsibilities, personality, tone, and specific behavioural guidelines. Think of it as onboarding a new team member in writing.

​
Step 4: Configure Provider Settings

Click the Provider tab to set the AI model. All assistants use a fast Claude model by default — cost-effective and included in all QuivaWorks plans. No API key required. Your plan’s credits are used automatically. The default model handles customer service, research, content, data extraction, and the vast majority of business workflows extremely well. It’s the right starting point for almost every assistant.
On accounts with bring-your-own-key enabled, you can connect your own Anthropic API key to use a different Claude model. This doesn’t take you off QuivaWorks credits entirely — BYOK calls still draw a smaller platform-side credit charge, on top of what your own key is billed by Anthropic. Learn more →
For this guide, leave the default selected and move on.

​
Step 5: Add Knowledge (Optional)

Click the Knowledge tab to give your assistant access to your specific content. Knowledge lets your assistant answer questions based on your documentation, FAQs, policies, or any other reference material — not just its general training. You can add knowledge from:
  • File upload — PDFs, Word documents, text files
  • URL — Web pages and documentation sites
  • Manual entry — Paste text directly
For your first assistant, you can skip this and add knowledge later. The assistant will still work based on its instructions alone.

Learn more about Knowledge

How to add and manage knowledge sources →

​
Step 6: Connect Integrations (Optional)

Click the Integrations tab to connect your assistant to external systems via MCP. Integrations give assistants the ability to take actions — look up orders, search a CRM, create tickets, or call your APIs. For your first assistant, skip this for now and add integrations as you need them.

Learn more about Integrations

How to connect tools and APIs →

​
Step 7: Save and Start Chatting

Click Save, then open the assistant and click New Chat to test it. Try a few questions that match your use case:
  • “What features does your product have?”
  • “I’m having trouble logging in, can you help?”
  • “I want to speak to a human”
Evaluate the responses: are they on-brand? Does the assistant stay in scope? Do edge cases (like asking for a human) behave correctly? If something is off, go back to Instructions and refine the guidance — then test again.
Use the thumbs up/down buttons on responses to flag what works and what doesn’t. These votes feed into the Learning system so you can improve the assistant over time.

​
Step 8: Share with Your Team (Optional)

If you created a Team assistant, your team can already find and use it in their own sessions. To collaborate on a specific conversation in real-time:
  1. Open the assistant in chat
  2. Type @ to mention a team member
  3. They’ll receive a notification and can join the session instantly

Learn more about Collaboration

Real-time session sharing and @mentions →

​
What’s Next

Your assistant is live. Here are the most impactful ways to build on it:

Add Knowledge

Give your assistant access to your documentation and content

Connect Integrations

Link to your CRM, ticketing system, or custom APIs

Improve with Learning

Use feedback votes and insights to refine behaviour over time

Automate with Flows

Trigger your assistant automatically via webhook, schedule, or email

Prompt Engineering

Write better instructions for better results

Advanced Configuration

Explore all configuration options in depth