# Intro to Calk AI

## Welcome to Calk AI! 🚀

Where does Calk AI comes from and why we decided to build this software for businesses.

Calk AI is your AI workspace — designed to build smart agents trained on your own knowledge, documents, and workflows.

It’s not another chatbot or automation tool. It’s a foundation for creating intelligent assistants that actually understand your business.

You bring the content (Google Drive, PDFs, links, notes), and Calk AI turns it into a context-aware AI agent that helps you write, think, decide, and get things done faster.

### Why We Built Calk AI <a href="#h_d88fe086b6" id="h_d88fe086b6"></a>

AI is everywhere — but its impact on real business is still limited.\
You get cool outputs, but no real return. And it only gets worse when every model (GPT-4, Claude, Mistral, Gemini…) lives in a separate tool, behind different accounts.

We built Calk AI because we were tired of that mess.

{% embed url="<https://youtu.be/VlCSUiaeCIA>" %}

***

We wanted:

* A tool where all top models live under one roof — no extra accounts
* A system to give those models context by connecting them to our internal knowledge and tools
* A way to turn AI into ROI — something that helps teams actually work better

So instead of asking random questions to a generic model, you build agents that know your business, your docs, your goals — and act like teammates.

### What You Can Do With Calk AI <a href="#h_a5dfc9be51" id="h_a5dfc9be51"></a>

* Train agents on your own content (files, links, notes, FAQs…)
* Chat across models to compare results and dig deeper
* Build agents to handle multi-step workflows
* Adapt agents to different specific roles — sales, support, research, product…
* Stay in control — everything is private, searchable, and transparent

Calk AI is flexible by design. It adapts to how *you* work — not the other way around.

<figure><img src="https://2442470273-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FBGWv9tHN4FLRiQu7ou5P%2Fuploads%2FuJtPDbAptpLmkS6WXfsv%2Ftag-calk.png?alt=media&#x26;token=60956b42-c651-4de8-b1c5-8aee4fc7f2c8" alt="" width="348"><figcaption></figcaption></figure>

***

### Why the Name “Calk AI”? <a href="#h_8abbf0b9f3" id="h_8abbf0b9f3"></a>

Calk AI comes from the French word *“calque”* — which means tracing paper.

Just like architects layer information to design something precise, Calk AI lets you layer your company’s content and context on top of powerful AI models.

\
So your agents aren’t just smart — they’re aligned, fine-tuned, and ready to act.

It’s not just about speed. It’s about building with intention.

👉 Next up: [How It Works →](https://chatgpt.com/c/684c20ed-9104-800a-9f7a-30f7908b021c)

***

### 🧩 How Does Calk Actually Work?

Calk follows a simple logic:

**Connect** your tools →\
**Import** your knowledge →\
**Link** that knowledge to a smart agent →\
**Ask** your agent anything, and it responds with context.

Behind the scenes, Calk uses **RAG (Retrieval-Augmented Generation)**:

> It pulls the most relevant content from your sources and feeds it into the AI model live — so it always has your team’s latest info.

<figure><img src="https://2442470273-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FBGWv9tHN4FLRiQu7ou5P%2Fuploads%2FbtkzjKkAOM4kCf0DCFmb%2Flogic-calk.png?alt=media&#x26;token=8a4142f3-53d0-4b23-b160-747e7470f4e0" alt=""><figcaption></figcaption></figure>

#### 🤖 Try Asking a Real Question

Ask your agent things like:

* “What does {{client}} need from us?”
* “How do we onboard new hires?”
* “What’s our refund process?”

You’ll get an answer based on your actual docs, tickets, and tools.

***

#### 🧠 Talk to Top AI Models (and Compare)

Switch between models like:

* GPT-4o (OpenAI) — brainstorming and document analysis
* Claude (Anthropic) — clear writing
* Mistral — fast + flexible
* Deepseek — technical precision
* GPT o4-mini (OpenAI) — deep reasonning
* Gemini 1.5 : good for large files
* Cohere - Really good at retrieving information

🧪 *Tag up to 4 models or agents and compare answers instantly.*\
→ You choose the best brain for the job.

***

#### 🧠 Create Focused, Specialized Agents

Don’t build a “do everything” AI.\
Build small, smart agents like:

* **Support Bot** trained on Intercom + Slack
* **Sales Prep Bot** trained on Hubspot + Notion
* **Onboarding Guide** trained on internal docs

They answer like experts — because they’re trained only on what matters.

🎥 *(Insert agent creation screenshot or Loom)*

***

### 🚀 Next Up: Launching Calk Inside Your Company

In the next section, we’ll cover:

* How to roll out Calk internally
* How to pick the first 1–2 use cases
* How to invite your team
* Where to get inspired (Slack, YouTube, Notion Toolbox)

🎬 Head to **Part 2 – Implementing Calk in Your Company →**

***

#### 🤖 Try Asking a Real Question

Ask your agent things like:

* “What does {{client}} need from us?”
* “How do we onboard new hires?”
* “What’s our refund process?”

You’ll get an answer based on your actual docs, tickets, and tools.

***

#### 🧠 Talk to Top AI Models (and Compare)

Switch between models like:

* GPT-4o (OpenAI) — deep reasoning
* Claude (Anthropic) — clear writing
* Mistral — fast + flexible
* Deepseek — technical precision

🧪 *Tag up to 4 models or agents and compare answers instantly.*\
→ You choose the best brain for the job.

***

#### 🧠 Create Focused, Specialized Agents

Don’t build a “do everything” AI.\
Build small, smart agents like:

* **Support Bot** trained on Intercom + Slack
* **Sales Prep Bot** trained on Hubspot + Notion
* **Onboarding Guide** trained on internal docs

They answer like experts — because they’re trained only on what matters.

🎥 *(Insert agent creation screenshot or Loom)*

***

### 🚀 Next Up: Launching Calk Inside Your Company

In the next section, we’ll cover:

* How to roll out Calk internally
* How to pick the first 1–2 use cases
* How to invite your team
* Where to get inspired (Slack, YouTube, Notion Toolbox)

🎬 Head to **Part 2 – Implementing Calk in Your Company →**

***

Calk isn’t just software—it’s the future of how businesses interact with AI. Start building your custom AI solutions today and see the difference it makes for your team.

### Let's get started!

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="files"></th><th data-hidden></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Chat with the AI Models</strong></td><td><a href="broken-reference">Go Here.</a></td><td></td><td></td><td><a href="broken-reference">Broken link</a></td></tr><tr><td><strong>Create and Manage Agent</strong></td><td><a href="agents/whats-calk-agent/create-and-manage-agent">Go Here.</a></td><td></td><td></td><td><a href="broken-reference">Broken link</a></td></tr></tbody></table>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.calk-ai.com/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.