DocuMind for Jira

Getting started

Setting up DocuMind is a sequence: the categories come first, then the scheme that groups them, then the project that uses that scheme. Automation is the last step and it is optional.

Categories

A category is a label you can put on an attachment, plus the instructions that tell automation when that label fits.

Writing good prompting text

Prompting text is the single biggest influence on how well automatic sorting works. Describe the document and name the words that give it away:

Documents arrive in more than one language, so list the terms in every language your teams receive. DocuMind matches meaning rather than exact words, but naming the real vocabulary makes it considerably more reliable.

Extracting fields

A category can do more than label a file. Turn on extraction and list the values you want pulled out of the document, and DocuMind reads them from the file itself.

An invoice category might extract:

Field names are treated as business concepts, not literal labels. A field called Company name will match Rechnungssteller, Lieferant, supplier or vendor depending on the document. Formatting that matters, such as IBANs, invoice numbers and VAT IDs, is preserved as printed.

Extracted values appear under the attachment in the work item, behind Show extracted fields and values.

Writing values into Jira fields

A category can also map its extracted values onto fields of the work item itself. Turn on field mapping for the category and pair each extraction field with the Jira field that should receive it. DocuMind then fills those fields when it processes an attachment, so the information is available to boards, filters and automation rules like any other field.

Schemes and projects

Categories are defined once for the whole site. A scheme decides which of them a given project may use, and in what way.

One scheme can serve many projects. Changing the scheme changes every project mapped to it, which is the point: you maintain one list instead of twenty.

Working in a work item

The DocuMind panel sits below the attachments on the work item. Every attached file is listed with the categories it carries.

Assigning by hand

Select the attachment and choose a category from the scheme mapped to the project. If the scheme allows multiple categories, add as many as apply. You can clear categories from a file at any time.

Reviewing suggestions

When automation is set to Suggest only, DocuMind proposes categories and marks them as suggestions. Nothing is applied until someone accepts it. Each suggestion can be accepted or rejected on its own, or you can accept every suggestion on the work item at once.

When automation is set to Auto confirm above threshold, a suggestion the provider is confident enough about is applied directly, and anything below the threshold still waits for review.

Finding documents

DocuMind indexes what it knows about each work item's attachments so you can search for documents the way you search for anything else in Jira.

Examples

documindCategories ~ "Invoice"
documindCategoryKeys = "invoice-billing"
documindExtractedText ~ "EU-2026-1188"
documindSearchText ~ "Acme GmbH" AND project = FIN

There is also a read-only field called DocuMind Search Text that you can add to a board or a filter view to see at a glance what a work item's attachments contain.

AI providers

DocuMind ships with automation switched off. When you turn it on, you choose which engine does the work, and that choice decides whether anything leaves your Atlassian instance.

Settings

Use Test provider after entering a key to confirm the connection before you rely on it.

Rovo agent

If Rovo is available on your site, you can open DocuMind Agent from the DocuMind panel in a Jira work item. Select an attachment and click Open Rovo Agent.

The agent can:

• Review attachment information and recommend DocuMind categories. When a category scheme is assigned to the project, recommendations are restricted to that scheme.
• Summarise supported attachments and answer follow-up questions when readable content is available.
• Apply DocuMind categories to an attachment at your request.
• Propose a new Jira work item based on readable attachment content and ask for confirmation before creating it.

Supported attachment content

Text-based files, such as TXT, CSV, JSON and XML, can be read directly. PDFs are supported when their text can be extracted; scanned PDFs without extractable text cannot be read directly.

Excel, Word, PowerPoint and image files cannot be read directly by the Rovo integration. For supported binary files, DocuMind may use a configured external AI provider to prepare document context. This sends the attachment to that provider and depends on its file-format support. When Rovo is the selected provider, these files are limited to attachment metadata.

Content processing is limited to files up to 4 MiB, and extracted text is limited to 12,000 characters. Larger files are handled using metadata only.

Interactive workflow

Rovo is an interactive agent in the current DocuMind integration. Selecting Rovo in AI Settings does not enable automatic classification of newly uploaded attachments.

Audit log

Every change to categories, schemes and project mappings is recorded, together with automation results and provider tests. Each entry carries who acted, what changed, the work item involved and the time.

For automated assignments the entry also records which provider ran, how confident it was, and which categories it proposed, so a decision made weeks ago can still be explained.

Where your data lives

DocuMind is a Forge app. Everything it stores — categories, schemes, project mappings, assignments, extracted values and audit records — is held in Atlassian Forge storage inside your own Atlassian Cloud instance. teams2tech keeps no copy and has no access to it.

The files themselves are never copied. They stay as Jira attachments, where your existing project permissions already govern who may see them.

The one case where content leaves your instance is an external AI provider you have selected and supplied a key for. How that works is set out in the teams2tech privacy policy.

Security

Architecture

DocuMind for Jira is built on Atlassian Forge and runs entirely on Atlassian's infrastructure. teams2tech operates no servers, databases or backend services for the app, and has no access to customer data.

Data storage

• All data DocuMind stores (categories, category schemes, project mappings, attachment assignments, folders, extraction results, upload events and audit records) is kept in Atlassian Forge storage inside the customer's own Atlassian Cloud instance.
• Documents uploaded through the DocuMind project page are stored in the Atlassian Forge Object Store of the customer's instance.
• Attachment content sent for AI classification is processed in memory for the duration of the request and is not persisted by the app.
• Data at rest is encrypted by the Atlassian Forge platform. Data residency follows the customer's Atlassian Cloud configuration.

Encryption and secrets

• All traffic between the app, Atlassian APIs and external AI providers uses HTTPS/TLS.
• AI provider API keys entered by an administrator are stored in Forge secret storage in encrypted form. They are never returned to the user interface and never written to logs.

Access control

• Every app action checks the calling user's Jira permissions through the Jira permissions REST API before the app reads or changes Jira data. Users can only see and change what their own Jira permissions allow.
• Global configuration requires the Jira administrator permission; project configuration requires the project administrator permission; categorising and organising documents requires the Edit Issues permission.
• The app requests only the Forge scopes it uses, and these are reviewed with every release.

External connections

AI processing is optional and disabled by default. When a Jira administrator enables it with their own API key, the app connects only to the provider they select:

• OpenAI — api.openai.com
• Anthropic — api.anthropic.com
• Google Gemini — generativelanguage.googleapis.com

These are the only external domains declared in the app manifest, and the Forge platform blocks connections to any other domain. Administrators can instead use Atlassian Rovo, rule-based classification, or disable AI entirely; in those modes no data leaves Atlassian.

Secure development

• Source code is kept in a private repository; changes are reviewed through pull requests.
• An automated security check runs on every pull request and on the main branch. It scans for committed secrets and audits third-party dependencies for known vulnerabilities.
• Dependencies are updated when vulnerabilities are reported.

Vulnerability management and reporting

If you believe you have found a security vulnerability in DocuMind for Jira, please report it to kontakt@teams2tech.com with the subject "Security". We acknowledge reports within 5 business days, investigate them, and fix confirmed vulnerabilities according to their severity, in line with Atlassian's Marketplace security requirements. Please do not disclose the issue publicly until it has been fixed.

Incident response

If a security incident affects customer data, we notify affected customers and Atlassian without undue delay, and in any case within the timelines required by the Atlassian Marketplace Partner Agreement and applicable law.

Compliance

DocuMind for Jira does not currently hold independent security certifications. As a Forge app it inherits the security controls of the Atlassian Cloud platform.

Contact

T2T teams2tech GmbH, Siedlungsstrasse 3, 63607 Wachtersbach, Germany
kontakt@teams2tech.com

Support

Raise a request in the teams2tech support portal, or write to kontakt@teams2tech.com. Support hours are Monday to Friday, 08:00–18:00 CEST.

When reporting a problem with automatic sorting, the work item key and the attachment name let us find the matching audit entry quickly, which usually explains what happened.