> For the complete documentation index, see [llms.txt](https://docs.digibee.com/documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.digibee.com/documentation/release-notes/digibee-digital-workers/now-in-early-access-digital-worker-mode.md).

# Now in Early Access: Digital Worker Mode

{% hint style="info" icon="star-sharp" %}
**Release status**

Digital Worker Mode is currently in **Early Access**. To join early access, please submit your info using the form below.
{% endhint %}

### Integration work, reimagined

Behind the scenes, we’ve been quietly rearchitecting Digibee to be AI-native so we can help you deliver faster and with better quality for your stakeholders. 

Your starting point remains the same: defining a business objective that integration solves. What’s new is how that work gets done when you switch to Digital Worker Mode. 

Rather than opening a blank canvas and wiring everything by hand, you delegate the work to a digital worker: an AI specialized in integration that owns the work end to end. It designs the integration, builds the pipelines, and helps you monitor and troubleshoot them in production.

You stay in control the whole way. The digital worker serves as a senior teammate who does the heavy lifting: proposes a design, asks the right questions, and hands you working pipelines—while every decision remains yours to review, edit, or override.

{% embed url="<https://www.youtube.com/watch?utm_campaign=45745415-Launch+AI+Native+US&utm_content=docs-ea-page&utm_medium=referral&utm_source=docs&v=uVOEKkLedTo>" %}

### What’s new at a glance

<table data-header-hidden><thead><tr><th width="214.46875"></th><th></th></tr></thead><tbody><tr><td><strong>Digibee Digital Workers</strong></td><td><ul><li>AI with deep specialization in integration. </li><li>Own assigned integration projects end to end. </li></ul><p><br></p></td></tr><tr><td><strong>Digital Worker Mode</strong></td><td><ul><li>Operating the Digibee platform to design and build integrations through delegation. </li></ul></td></tr><tr><td><strong>Manual Mode</strong></td><td><ul><li>Execute integration work “by hand” rather than delegating to your digital workers. </li></ul></td></tr><tr><td><strong>Digibee AI-native integration platform</strong></td><td><ul><li>The Digibee platform you know, now optimized for your digital worker teammates. </li></ul></td></tr><tr><td><strong>The Spec</strong></td><td><ul><li>The primary collaboration surface for you and your digital workers. </li><li>Creates comprehensive requirements and documentation. </li><li>The source of truth digital workers build against. </li></ul></td></tr><tr><td><strong>Lifecycle stages supported by Digital Worker Mode</strong></td><td><ul><li>Design</li><li>Build</li><li>[Coming soon] Deploy</li><li>[Coming soon] Monitor<br></li></ul></td></tr></tbody></table>

### This isn’t an assistant or an intern&#x20;

Most "AI for integration" tools bolt a chat box onto an existing builder. Digibee AI Native is built the other way around: a platform designed to be operated by AI, with the digital workers that operate it and a shared way of working that keeps humans and AI aligned.

That combination is what makes the work trustworthy at scale:

* It's comprehensive, not a point solution. The digital worker doesn't just generate a snippet, it produces an aligned design, generates and tests real pipelines, and helps you keep them healthy in production.
* It's grounded in a shared source of truth. Everything the digital worker knows and proposes lives in a living document, the Spec, that you and the worker develop together. Nothing is a black box.
* It's built on Digibee's integration platform. The pipelines the digital worker produces are real Digibee pipelines, running on the same enterprise-grade runtime Digibee customers already trust, not a parallel, throwaway system.
* You are always at the helm. The digital worker proposes; a person approves. Nothing reaches a live environment on AI output alone.

### What you can do today

Collaborate with and delegate to digital workers across **Design and Build**. Describe the outcome you want in plain language. The digital worker co-develops a detailed specification with you, then generates fully tested pipelines from it.

*\[Coming soon]* **Deploy**: Delegate deployment planning and execution to your digital worker.

*\[Coming soon]* **Monitor**: Ask questions about your running integrations and launch investigations. The digital worker analyzes logs and metrics, gathers evidence, and produces a root-cause analysis.

And because it's the same Digibee platform underneath, you can switch into Manual Mode at any point to fine-tune what the digital worker produced, take over by hand, or build entirely from scratch.

### How to get access

To join the Early Access program, the first step is to schedule a demo. Please submit your info below and your account team will reach out to book.

{% embed url="<https://share.hsforms.com/2op89vvHmTWWuGUTIt0M5ggcczql>" %}

### &#x20;FAQs

<details>

<summary>When will this be available to all customers?</summary>

Digibee Digital Workers are targeted for General Availability in late Q3/early Q4 2026.

</details>

<details>

<summary>What models are used to power digital workers?</summary>

Several large language models are used based on best fit for the task—and we’re continuously evaluating and adapting as models evolve. Users benefit from this ongoing engineering work to ensure performance and cost are optimized for you.

</details>

<details>

<summary>Will my data be used to train AI?</summary>

No. Each customer's institutional knowledge—your systems, configurations, and everything you build—will never be shared or reused in other contexts.&#x20;

What **is** shared across all customers are Digibee's platform standards, structures, and public knowledge. This separation is a non-negotiable principle.

</details>

<details>

<summary>Will this be a paid feature?</summary>

Digibee's platform pricing will evolve as a whole to reflect the new way of working. While we refine pricing, speak with your account team for more information.

</details>

<details>

<summary>What will this change for me?</summary>

Today, nothing will change for customers unless you opt in to Early Access. Once you have access to Digibee Digital Workers, you’ll be able to choose when you work in Manual Mode or Digital Worker Mode.

</details>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.digibee.com/documentation/release-notes/digibee-digital-workers/now-in-early-access-digital-worker-mode.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.