# Welcome!

Dagploy helps you to automate repetitive tasks with AI Agents

<button type="button" class="button primary" data-action="ask" data-icon="gitbook-assistant">Ask a question...</button>

<button type="button" class="button secondary" data-action="ask" data-query="How do I get started?" data-icon="rocket-launch">Get started</button>&#x20;

<table data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="image">Cover image</th></tr></thead><tbody><tr><td><h4><i class="fa-server" style="color:$primary;">:server:</i></h4></td><td><strong>Welcome</strong></td><td><p>Lets start your first automation!</p><p><br></p></td><td><a href="/documentation">Welcome</a></td><td><a href="https://content.gitbook.com/content/tPy2liJmqqT0tlbC6YqW/blobs/iOKK54oCSx0yccHQNAS0/no-code.jpg">no-code.jpg</a></td></tr></tbody></table>

<h2 align="center">Join a community</h2>

<p align="center">Join our Github community or create your first PR in just a few steps.</p>

<table data-card-size="large" data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-cover data-type="files"></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><h4><i class="fa-github">:github:</i></h4></td><td><strong>GitHub</strong></td><td>Check DAX and Dagwork open source project. Head to our GitHub repository to learn more.</td><td></td><td><a href="https://www.gitbook.com/">https://www.gitbook.com/</a></td></tr><tr><td><h4><i class="fa-comments-question-check" style="color:$primary;">:comments-question-check:</i></h4></td><td><strong>Enterprise Support</strong></td><td>Contact us for enterprise integration features and professional services</td><td></td><td><a href="https://www.dagploy.com/contact">https://www.dagploy.com/contact</a></td></tr></tbody></table>

&#x20;


# Welcome

Welcome to Dagploy Blog

Have a look on showcases and use case for DAX and DAGWork in real production.&#x20;


# Build Claude Alternative in 20 Mins

Running DAX, OpenWork and GPT OSS 20B in GCP

Here are few steps to setup and run Claude alternative using OSS that runs in your cloud. Everything full in your control without any external API or sharing data required.

{% embed url="<https://www.youtube.com/watch?v=vI6Oqr1OpI8>" %}

### 1. Install DAX

This provide automated GPU instance provisioning in our cloud without dealing with complexity like NVIDIA drivers, stuck in downloading large models, docker setup and many others things. This step will required 5 minutes of setup and make sure you have `GPU Quota` activated in your GCP project.

Go to <https://github.com/dagploy/dax> and run the installation

### 2. Download GPT OSS 20B and VLLM

Start by caching Docker images and models first, around 100GB in total.

#### Step 1: Cache the VLLM docker <a href="#step-1-cache-the-vllm-docker" id="step-1-cache-the-vllm-docker"></a>

<a class="button secondary">Ask</a><a class="button secondary">Copy</a>

```
dax run download_docker vllm/vllm-openai:nightly,ghcr.io/open-webui/open-webui:main --images vllm-lib --image-size 100
```

#### Step 2: Cache GPTOSS 20B from Huggingface <a href="#step-2-cache-gptoss-20b-from-huggingface" id="step-2-cache-gptoss-20b-from-huggingface"></a>

<a class="button secondary">Ask</a><a class="button secondary">Copy</a>

```
dax run download_hf openai/gpt-oss-20b --image-size 50
```

You can start tunneling from host into your GCP VM or using VPN.

### Step 3: Run inferencing <a href="#run-inferencing" id="run-inferencing"></a>

<a class="button secondary">Ask</a><a class="button secondary">Copy</a>

```
dax run create_vm_inference --stack-name gptoss --config-json '{"images":["models--openai
```

### 3. Install OpenWork in your Laptop

Download Openworks&#x20;

{% embed url="<https://github.com/different-ai/openwork/releases>" %}

Connect openwork with your GPT OSS 20B VM instance. Follow their tutorial. For Linux, you need to edit `vim ~/.config/opencode/opencode.json`&#x20;

Make sure to match the `model` , `port` and `url`&#x20;

```
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "my-api": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "GPT OSS 20B",
      "options": {
        "baseURL": "http://localhost:8000/v1"
      },
      "models": {
        "model-name": {
          "name": "model"
        }
      }
    }
  }
}

```

Author tested that **Qwen 3.6 27B** [**https://huggingface.co/Qwen/Qwen3.6-27B**](https://huggingface.co/Qwen/Qwen3.6-27B)  perform better on integration with OpenWork.

Do you need assistance to build Sovereign AI infra in your organization? feel free to drop message at [**https://www.dagploy.com/contact**](https://www.dagploy.com/contact)

Or, learn more about Dagploy&#x20;

{% embed url="<https://www.dagploy.com>" %}

&#x20;


# Welcome

Lets make your manual operational data managed with AI agents.

<button type="button" class="button primary" data-action="ask" data-icon="gitbook-assistant">Ask a question…</button>

<button type="button" class="button secondary" data-action="ask" data-query="How do I deploy my first project" data-icon="rocket-launch">Scan Photos/Images</button><button type="button" class="button secondary" data-action="ask" data-query="How do I set up a custom domain" data-icon="globe">Chatbot from Google Sheet</button>

***

## Where to start

<table data-card-size="large" data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><h4><i class="fa-rocket-launch" style="color:$primary;">:rocket-launch:</i></h4></td><td><h4>Getting started</h4></td><td>Learn the high level about Dagploy platform, target users and solutions.</td><td><a href="/documentation/getting-started/getting-started">Getting Started</a></td></tr></tbody></table>

## Popular tasks


# Getting started

Dagploy offers the easy way to build AI agent automating  repetitive tasks in the back office. The AI Agents can read any data from document, images, PDF, videos, voices and others. Process the information and store it into system.&#x20;

## Any Data

All kind of data can be received by AI Agent. Right now, its only support the data being pass via link. Make sure the link is accessible either with public access or limited access using private key.&#x20;

## Channel

This is where AI Agents will receive input, message, data or returning answer to the users. There are several channels that you can use&#x20;

* Email
* Web Chat
* Telegram Bot
* Google Chat
* API

The last one is mostly use for system-to-system communication between AI Agents or ERP / internal system.

## Work

are multiple steps that what a AI Agent will automation. For example, "Sales Order input from Whatsapp Image" work have several steps:

* [x] Receive the image
* [x] Run OCR on the image
* [x] Cleaning and Re-format the OCR results
* [x] Check the items with inventory
* [x] Check the items with historical success record
* [x] Send it into ERP&#x20;

You can see there are several steps required to complete one job.

## Preparation to Build AI Agent

Before build the AI agents, make sure you already have clear defined manual work steps, data and how the interaction will be performed.


# Quickstart

Build your own AI Agents under 1 minute.

This quickstart gets you to your first AI Agents as fast as possible. We'll skip most configuration for now, you can refine it later once everything is running.

## Pre-requisites

1. Account (Gmail, Microsoft or Github Account)
2. Data source

## Steps

{% stepper %}
{% step %}

#### Create a new account (\~5 secs)

Go to "Login/Sign-up" page
{% endstep %}

{% step %}

#### Create Agents (\~10 secs)

Select the menu "Agent" on the sidebar. Expand the sidebar if its closed. You can choose "Quick Agent" as the easy way to create or Choose "Add Agent" for more configuration "TEXT", "GOOGLE SHEETS", "MICROSOFT SHEETS" or "API/MCP"

For quickstart, you can start with "Quick Create Agent" and choose "Plain Text" as the main source knowledge for the AI Agent.

<figure><img src="https://2967462928-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1ihwSpws3fgJmUYzJFWJ%2Fuploads%2FK6w9RocayhIfhB0mLLM3%2Fimage.png?alt=media&amp;token=f34d892f-8809-4427-a641-10e0e5f0e0c9" alt=""><figcaption></figcaption></figure>
{% endstep %}

{% step %}

#### Channel  (\~10 secs)

Email and chat AI Agents via web will be created automatically by default.  You can click the url or test the email asking the AI Agent to retrieve the information. Congrats! Now your AI agents is already live and running 🎉

<figure><img src="https://2967462928-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1ihwSpws3fgJmUYzJFWJ%2Fuploads%2FGRsEZ8bIbbH0cM5ncjTs%2Fimage.png?alt=media&amp;token=7ce8ceb4-748d-4960-8dd8-d1cb1d96486f" alt=""><figcaption></figcaption></figure>
{% endstep %}
{% endstepper %}

## What's next?

Create more AI agents tailored to your own use case. Happy exploring!


# Scan Photos or Images

Many raw photos coming from outside like Sales Order, Fuel notes, Reimbursement, Paper document, checklist and other thing. We are building AI agent to read those image, restructure the information and pass it into next AI Agent or internal system.

### Create Agent

Go to "Agent", select "Add Agent" menu on the top right. Once the page showing-up, choose the "New Connection"&#x20;

<figure><img src="https://2967462928-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1ihwSpws3fgJmUYzJFWJ%2Fuploads%2Fl0wl8kVxLNUaf1kph9Bo%2Fimage.png?alt=media&amp;token=4338c780-0ccc-4e10-880a-e1ff932efec1" alt=""><figcaption></figcaption></figure>

### Choose the OCR model

There are several OCR model you can try. Its recommended to use "OCR-G001" for heavy tasks to manage handwritten notes.

<figure><img src="https://2967462928-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1ihwSpws3fgJmUYzJFWJ%2Fuploads%2F7QzsEnWTO8d3fSMyrRHU%2Fimage.png?alt=media&amp;token=23739083-be37-4f19-90ad-bdaaa70b48ac" alt=""><figcaption></figcaption></figure>

### Setup the AI Agent name&#x20;

You can give name for the AI agent and also see how the default prompt being used for this OCR

<figure><img src="https://2967462928-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1ihwSpws3fgJmUYzJFWJ%2Fuploads%2Foc4BvObem2qoNfs41S5L%2Fimage.png?alt=media&amp;token=0838f561-522c-4610-81a9-285a3908aca1" alt=""><figcaption></figcaption></figure>

### Bonus: Next Agent to Parse

This is only scan image and convert into text. The result will be unstructured and need to be re-formated to make it works with system integration that you needed. In that case, you can chain with another AI Agent to manage it.

To chain it, you can tick which the AI Agent will be activated once the OCR completed&#x20;

<figure><img src="https://2967462928-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1ihwSpws3fgJmUYzJFWJ%2Fuploads%2F3fyzwlFdPeXbELhVuK8c%2Fimage.png?alt=media&amp;token=218c42cb-a6b3-4813-bceb-cf1f4430f597" alt=""><figcaption></figcaption></figure>

### Give a shot!

![](https://2967462928-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1ihwSpws3fgJmUYzJFWJ%2Fuploads%2FGXw0hoA6GmTud0iwVCuI%2Fimage.png?alt=media\&token=8809bae4-6ba4-4876-abc6-07cbef1c1d49)

Url: <https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcTWfmugKdj2iTRTeLb2qWDFMF7YIjc2Ui_rCbG-nykAqv13MdpvHav_xdM&s=10>

You can paste the image url into the chat

<figure><img src="https://2967462928-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1ihwSpws3fgJmUYzJFWJ%2Fuploads%2FqW5SQXmMLxq8t3r2M94Z%2Fimage.png?alt=media&amp;token=373369c4-72d9-439b-b481-2cf055816425" alt=""><figcaption></figcaption></figure>

### API Integration

You can submit the URL into AI Agents via API. Go to "Channels", Select "Add" and Choose "API". Generate the "API Key" and use that as the authentication during API call.&#x20;

![](https://2967462928-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1ihwSpws3fgJmUYzJFWJ%2Fuploads%2FOFyAupdfpqW0mrfNYGBt%2Fimage.png?alt=media\&token=a4b4a868-a3bf-414b-8e44-fa892759f53f) &#x20;

Congratulations! Now you made OCR AI agent successfully!&#x20;


# Support

Dagploy offer enterprise features and professional services to help speed up and bring AI agents into their internal systems

This is including:

* System and API integrations
* Custom tools development
* and many more.

Feel free to contact us

<table data-card-size="large" data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><h4><i class="fa-globe" style="color:$primary;">:globe:</i></h4></td><td><strong>Contact Us</strong></td><td>For enterprise and professional services</td><td><a href="https://www.dagploy.com/contact">https://www.dagploy.com/contact</a></td></tr></tbody></table>