Skip to main content
The Jira integration connects your Jira Service Management instance to Rallied.ai. The agent can read and update issues, post comments, and manage Jira Assets (Insight) objects. When a new Jira issue is created, Rallied.ai is notified automatically and the agent begins working on it without any manual trigger.
Jira is configured from MSP Settings → Integrations.

How to connect

1

Open the Integrations tab

Navigate to MSP Settings → Integrations.
2

Connect Jira

Find the Jira card and click Connect. An Atlassian authorization window opens.
3

Authorize via Atlassian

Sign in to Atlassian and grant Rallied.ai access to your Jira instance. Atlassian manages the OAuth flow — Rallied.ai receives a scoped access token, not your login credentials.
4

Complete post-connect setup

After authorizing, the dashboard prompts you to select the Jira project to monitor. This tells Rallied.ai which project’s new issues should wake the agent.
5

Confirm the connection

The Jira card shows Connected. Incoming tickets from the selected project will now trigger the agent automatically.

Incoming tickets (webhook)

When a new issue is created in the connected Jira project, Jira sends a webhook to Rallied.ai. The agent wakes up with the ticket context already loaded — summary, description, reporter, and priority — and starts diagnosing the issue. If a matching workflow exists for the ticket type (based on historical tickets from the learning pipeline), the workflow is injected into the agent’s context to guide resolution.

Approval channel

When the agent’s plan includes an action that requires technician approval, it posts a comment on the Jira issue describing the proposed steps. Technicians see the comment in Jira and reply to approve or deny.
If you also have Slack connected for the same client, the agent sends a Slack DM to the technician in addition to the Jira comment. Technicians can approve from either channel — whichever they see first.
When a technician approves or denies via Slack, a note is automatically posted back on the Jira issue recording who resolved it and when.

Tools

Issue management

ToolDefault policyDescription
jira:jira-get-issueAutoGet a Jira issue by key or ID, including summary, status, assignee, and description
jira:jira-add-public-commentAutoAdd a comment visible to the reporter and customer
jira:jira-add-internal-commentAutoAdd a comment visible only to the service desk team

Jira Assets (Insight)

The agent can also manage objects in Jira Assets, the asset management module built into Jira Service Management.
ToolDefault policyDescription
jira:jira-assets-searchAutoSearch Assets objects using AQL (Assets Query Language)
jira:jira-assets-countAutoCount Assets objects matching an AQL query
jira:jira-assets-getAutoGet a single Assets object by numeric ID
jira:jira-assets-get-attributesAutoList all attribute values for an Assets object
jira:jira-assets-list-schemasAutoList all object schemas in the Assets workspace
jira:jira-assets-list-typesAutoList object types within a schema (Computer, Hardware, Software, etc.)
jira:jira-assets-get-type-attributesAutoGet attribute definitions for an object type
jira:jira-assets-createApproval neededCreate a new Assets object
jira:jira-assets-updateApproval neededUpdate attributes of an existing Assets object
jira:jira-assets-deleteApproval neededDelete an Assets object (irreversible)
Asset deletion is irreversible. The jira-assets-delete tool defaults to approval needed and cannot be changed to auto. Confirm this policy is appropriate for your client before deploying.

Internal comments

The agent uses internal comments (jira-add-internal-comment) for its own reasoning, audit trail, and status updates visible only to your service desk team. Public comments (jira-add-public-comment) are used when the agent needs to communicate directly with the reporter or customer. Both default to auto — the agent does not need approval to post comments.

Workflow injection

Rallied.ai’s learning pipeline analyzes your historical Jira tickets and generates resolution workflows. When a new ticket arrives that resembles a known issue pattern, the matching workflow is automatically injected into the agent’s context. This guides the agent toward the resolution steps that have worked before, without requiring any manual configuration. See the Workflows documentation for details on how workflows are generated and managed.