Build your first agent

In this page you'll find a comprehensive guide to build your first agent.

πŸ› οΈ Build Your AI Agent β€” Step by Step

With Calk AI, creating an AI Agent is fast, flexible, and designed to fit your exact needs. Whether you’re building an assistant for onboarding, sales support, or document summarization, here’s how to do it in three simple steps:


Before that get to the Agent Creation Page β‡’

β‘  Define the Task (Prompting)

This is where you teach your agent what to do.

🧠 How it works You write a clear instruction, also known as a prompt. This tells the agent its job. The more specific, the better. You can read our Class on how to prompt : Here !

πŸ”Ή Example: For an assistant that summarizes sales calls, your prompt might be: "Summarize this conversation and highlight key objections, buying signals, and next steps."

🧩 Tips for writing a good prompt

  • Be clear and direct.

  • Break tasks into steps.

  • Use bullet points and examples.

  • Try loading from our Prompt Library to get started fast.

✨ You can test the prompt live before continuing.

🧠 Need a hand to write your prompt?

Calk gives you 3 quick tools to build great prompts, even if you're not a prompt expert:


Check out our range of tools designed to assist you effectively!

Cover

1️⃣ Help Me

Type one line describing your goal. Calk turns it into a full prompt structure instantly. πŸͺ„ Magic for when you don’t know where to start.

Cover

2️⃣ # Add Section

Insert smart building blocks like steps, tone, formatting, etc. Helps you structure complex prompts in seconds.

Cover

3️⃣ $ Variables

Make your prompt reusable with variables like $company or $companydetails. Perfect for scaling across teams or use cases.


β‘‘ Connect Knowledge & Tools

This is where your agent gets context and capabilities.

πŸ”— Connect Integrations

We support two types of integrations:

  • Knowledge Integrations β†’ Notion and Google Drive These fetch documentation, playbooks, notes, and structured files.

  • Information Integrations β†’ Slack, Intercom, HubSpot, GDrive, Notion, Web pages... These provide up-to-date business context directly into the agent’s hands.

🧠 Agents with connected integrations = smarter, faster, more relevant.

πŸ“‚ Upload Local Files

Want to train your agent on a few PDFs or internal memos? Just drag and drop.

🌐 Add a Website

Need your agent to "read" a public page? Add any URL and let it ingest the content directly.

πŸ› οΈ Enable Tools

  • Web Search β€” for live internet browsing

  • Web Scraper β€” for turning sites into internal knowledge

  • Reasoning Engine β€” for more logic-heavy tasks

  • Data Tools β€” for generating charts from insights

A possible use case ‡️

Spy on your competitors blog or website with a scraper!


β‘’ Set Identity

Now define who your agent is.

πŸ§‘β€πŸ’Ό Name & Icon Make it easy to recognize and reuse!

🧠 Model Choice Choose from top LLMs: GPT-4o, Claude, Mistral, Cohere. Each has strengths β€” pick the best for your use case.

🎭 Tone Slider

  • 0 = Serious and direct

  • 1 = Creative and human-like It adapts your agent’s language to fit the brand voice or target audience.

🏷️ Tag by Domain Organize by team or function: Marketing, HR, Customer Care, Dev, etc.


πŸ’‘ The Power of Ultra-Specific Agents

Don’t build one general-purpose agent. Specialize.

  • One agent = one task = better results

  • Shorter prompts, cleaner outputs

  • Easier to troubleshoot and iterate

πŸ” Use agents in sequence Build workflows where agents feed each other:

Ask @accountSummary to scan your Hubspot and extract client insights. Then tag @coldemailer to generate a hyper-personalized outreach with those insights from Hubspot.

This layered logic allows your team to mix domain expertise with automation, boosting precision and saving time.

✨ See examples in the Use Cases section β€” from Marketing to Onboarding.️

You have pre made Assistants on your Assistants Page here β‡’ Calk's Assistant Page.

You just have to click on one with made by : Calk Team and tailor them to your needs!

Our Agent Template Library

Last updated