Case Study

AI Beyond Migration Assistants: Reengineering Silicon Labs’ Atlassian Cloud Journey

How Empyra combined AI agents, Model Context Protocol (MCP), Atlassian Forge, and enterprise engineering to tackle the migration challenges traditional tools alone couldn't solve.

Get Consultation

AtlassianCloud

AI agents

Model Context Protocol (MCP)

Atlassian Forge

Enterprise engineering

Customer

Silicon Labs

Industry

Semiconductors and Wireless Technology

Technology Partner

Empyra, Atlassian Platinum Solution Partner

Engagement

Enterprise Cloud Migration and Modernization

2025–2026

Solutions

Jira CloudConfluence CloudAtlassian ForgeRovoAtlassian GuardScriptRunnerAI-assisted AutomationEnterprise Integrations

At a Glance

The Transformation at a Glance

Enterprise complexity, assessed scale

Jira 1,170,000+

Jira issues

approximately1,300

Jira projects

2,794

Jira dashboards

approximately3,000

Users

Filters

25,217

Jira saved filters

3,528

Filters containing advanced ScriptRunner functions

Confluence

306,000+

Confluence pages

1,894

Confluence spaces

1,253

Documented remediation milestone: 1,253 Jira filters updated through a coordinated remediation process by October 30, 2026.

Environment figures reflect pre-migration assessment snapshots. They represent the scale and complexity evaluated, not independently verified final migration totals.

The Challenge

Moving a Million Issues Is One Thing. Preserving What Makes Them Work Is Another.

An enterprise migration can move every Jira issue successfully and still leave teams unable to work as they did before.

Saved filter

BreaksA saved filter may no longer recognize a ScriptRunner function.

Confluence page

BreaksA Confluence page may load, but its embedded Jira report might reference an outdated filter ID.

Quality-management workflow

BreaksA quality-management workflow may appear intact while the integration that validates product information no longer functions.

Not minor inconveniences

For organizations with highly customized Atlassian environments, these are not minor technical inconveniences.

They can affect reporting, traceability, engineering decisions, and operational continuity.

Reporting

Traceability

Engineering decisions

Operational continuity

That was the challenge facing

Austin, Texas

Headquartered in Austin, Texas, Silicon Labs is a leading innovator in low-power wireless connectivity, developing technologies that power connected devices across smart homes, industrial IoT, and other intelligent edge applications.

Behind that innovation is an interconnected ecosystem of engineering teams, business processes, software systems, and organizational knowledge.

Atlassian Data Center

Over years of growth, its Atlassian Data Center environment had evolved into a deeply customized platform supporting approximately 3,000 users, more than a million Jira issues, thousands of dashboards and filters, and hundreds of thousands of Confluence pages.

The platform's value extended well beyond the records it stored.

Above the surfaceThe records

Its workflows incorporated business-specific logic.

Its reports depended on advanced queries.

Its applications supported engineering and quality processes,

and its knowledge base contained years of interconnected technical information.

Below the surface

Not simply

Moving to Atlassian Cloud was therefore not simply a matter of transferring data from one platform to another.

The real need

Silicon Labs needed to preserve the intelligence embedded in its existing ecosystem while adapting that ecosystem to an entirely different Cloud architecture.

To address that challenge, Silicon Labs partnered with Empyra, an Atlassian Platinum Solution Partner specializing in complex Cloud migrations, enterprise integrations, software development, and AI-driven innovation.

A Different Approach

Engineer the Transformation, Not Just the Migration

Traditional migration utilities provide an essential foundation for transferring Jira projects, issues, users, and Confluence content.

But even sophisticated migration tools cannot automatically reproduce every custom integration, application behavior, scripted function, or business dependency built over years of Data Center usage.

Beyond standard migration tooling

Custom integrationsApplication behaviorScripted functionsBusiness dependencies

Migration utilities: the foundation

Jira projectsIssuesUsersConfluence content

Empyra approached the engagement as a broader engineering and modernization program.

The team began with detailed assessments of the existing Atlassian estate, mapping application dependencies, custom workflows, automation rules, identity configurations, reporting components, and third-party integrations.

Application dependencies

Custom workflows

Automation rules

Identity configurations

Reporting components

Third-party integrations

Every significant capability was evaluated against its business importance and its ability to function in Cloud.

Every significant capability

Native Cloud functionality

Where native Cloud functionality could satisfy the requirement, Empyra explored replacing legacy customization.

Replace

Marketplace applications

Where Marketplace applications offered supported migration paths, the team assessed compatibility and configuration changes.

Assess

Custom engineering

Where critical functionality could not be reproduced through available tools, Empyra designed custom engineering solutions.

Engineer

This process also required collaboration with application owners, engineering teams, administrators, and business stakeholders to distinguish between what was technically possible and what the organization actually needed.

Application ownersEngineering teamsAdministratorsBusiness stakeholders

The guiding principle was simple:

Preserve the business requirement—not necessarily the legacy technology used to deliver it.

That approach became particularly important in the areas where AI-assisted remediation and Cloud-native engineering could provide solutions beyond standard migration tooling.

1Innovation 1

AI-Assisted ScriptRunner Migration

Restoring The Logic Behind Thousands of Filters

One of the most technically challenging aspects of Silicon Labs' migration involved saved Jira filters.

A pre-migration assessment identified 25,217 saved filters, including 3,528 containing advanced ScriptRunner functions. These filters were not merely user preferences. They helped drive engineering dashboards, planning activities, cross-project reporting, and operational visibility.

25,217saved filters

3,528containing advanced ScriptRunner functions

Many relied on Data Center-specific JQL expressions such as linked Issues Of All, issues In Epics, and related functions that did not have straightforward Cloud equivalents.

Because ScriptRunner's execution model and supported functions differ between Data Center and Cloud, directly transferring these expressions could produce invalid queries or results that no longer represented the intended business logic. Manually reviewing thousands of interdependent filters would require substantial specialist effort.

Empyra developed an AI-assisted remediation approach to address this challenge.

The solution combined AI-based JQL analysis, ScriptRunner Enhanced Search capabilities, Model Context Protocol (MCP) integration, and Atlassian REST APIs.

AI-based JQL analysis

ScriptRunner Enhanced Search

Model Context Protocol (MCP)

Atlassian REST APIs

AI-assisted remediation approach

Rather than treating every broken query as an isolated ticket, the workflow was designed to:

01
Analyze legacy JQL expressions and identify unsupported functions.
02
Interpret the original query's purpose and relevant dependencies.
03
Translate supported patterns into Cloud-compatible alternatives.
04
Preserve original query definitions for traceability and recovery.
05
Apply corrections through controlled integrations and validate the resulting filter configurations.

This provided a more systematic way to handle large groups of incompatible filters. The team also addressed another class of problem: filters that failed to transfer through the Jira Cloud Migration Assistant. For those cases, Empyra developed a custom MCP-based capability to recreate missing filters through Jira Cloud APIs, extending remediation beyond objects that had already reached the destination environment. The effort required coordination with Atlassian to resolve migration mappings, dependencies, and platform-side corrections.

Milestone1,253

By October 30, 2026, 1,253 filters had been updated through the coordinated remediation effort.

Beyond the immediate customer requirement, the solution established a reusable engineering pattern for evaluating, translating, and recovering complex Jira configurations. What had previously been a largely manual troubleshooting exercise could increasingly be approached through intelligent analysis, structured automation, and validation.

2Innovation 2

Intelligent Confluence Macro Remediation

Keeping Enterprise Knowledge Connected

Jira was only one part of the challenge.

306,000+

pages

1,894

spaces

Silicon Labs' Confluence environment contained more than 306,000 pages across 1,894 spaces.

Years of technical documentation and collaboration had created an extensive network of embedded reports, diagrams, templates, cross-space references, and third-party macros.

Moving those pages to Cloud did not automatically guarantee that every embedded component would continue to display or behave correctly.

Embedded reports Diagrams Templates Cross-space references Third-party macros

Migrated Confluence pagePage loads

A Confluence Jira macro, for example, might still reference a Data Center filter ID.

Another macro might use a custom field identifier that had changed during migration.

A third-party formatting macro might require different parameters or an alternative Cloud application.

Even when the page itself migrated successfully, these dependencies could leave important information missing or inaccessible.

Empyra addressed these problems through a combination of migration mapping, scripting, application-specific remediation, and AI-assisted content analysis.

The AI-assisted macro-remediation approach was designed to inspect Confluence page definitions, recognize unsupported or incompatible macros, identify references requiring translation, and apply approved transformations.

For Jira and Jira Issues macros, the solution used Data Center-to-Cloud mapping information to correct references to filters, fields, and projects.

This enabled remediation to be approached systematically rather than exclusively through manual page-by-page editing.

The team also evaluated broader application compatibility challenges.

For example, Brikit Blueprint Maker supported specialized page and space creation processes in Data Center but lacked a directly equivalent Cloud migration path. Empyra investigated replacement approaches involving native Confluence templates, automation, and custom utilities to preserve the essential business workflow.

Native Confluence templatesAutomationCustom utilities

The same principle guided work involving HTML content, diagram applications, SQL-based macros, and other specialized Confluence capabilities.

The goal was not merely to preserve the pages. It was to preserve the usefulness of the knowledge and the connections between that knowledge and ongoing work.

3Innovation 3

A Forge and Rovo Approach to Migration Cleanup

Large enterprise migrations can introduce configuration anomalies that are difficult to identify through conventional checks alone.

Fields may be duplicated.

Roles, priorities, and resolutions may appear more than once.

Legacy HTML content can migrate into fields that no longer support the original formatting.

These issues become especially challenging when moving into an existing Cloud environment containing configuration objects of its own.

Empyra's engineering work included a Forge-based, Rovo-assisted migration-cleanup approach designed to identify and address these anomalies.

The solution architecture combined AI-assisted assessment with controlled remediation capabilities.

AI-assisted assessment

Its intended functions included:

identifying duplicate custom fields,
examining legacy HTML in field descriptions and message content,
and evaluating duplicate configuration entities for appropriate cleanup.

Controlled remediation

Where a correction could be defined safely, Forge-based actions provided an implementation path.

This approach reflects an important distinction in enterprise AI adoption.

AI can help interpret complex configurations, detect patterns, and recommend corrections. But changes to production environments still require appropriate safeguards, permissions, and validation.

Empyra's approach emphasized that separation between intelligent analysis and controlled execution. The broader opportunity was to turn repetitive migration cleanup into a more structured, reusable capability—reducing the dependence on manual investigation while retaining engineering oversight.

4Innovation 4

Rebuilding Business-Critical Integrations with Atlassian Forge

Some of the most important migration challenges were not generic Atlassian problems.

They originated in the specialized business processes that Silicon Labs had built around its engineering systems.

OPSNET

A particularly important example was OPSNET, Silicon Labs' internal product-information platform.

OPSNET supported Jira workflows associated with product quality and engineering activities, including Quality Investigation and Corrective and Preventive Action processes.

Quality InvestigationCorrective and Preventive Action

In the original Data Center implementation, custom scripts communicated with OPSNET to validate product identifiers and retrieve information needed by those workflows.

For example, when a user entered an affected part number, the integration could check that value against product data and return related information used in the issue.

Data Center

This integration depended on Data Center-specific Groovy scripting, custom field behavior, and access to internal services.

Groovy scriptingCustom field behaviorInternal services

Those capabilities could not be copied directly into Jira Cloud.

Jira Cloud · Forge

Empyra engineered a replacement using Atlassian Forge and API-driven integration patterns.

The Forge solution was designed to retrieve dropdown values from OPSNET, validate user selections, and populate dependent fields using authoritative product information.

The engineering effort involved addressing the differences between server-side scripting and Cloud-hosted application execution, including how integrations access external systems and enforce field-level business rules.

The team also developed a configuration-driven approach to unique issue identifiers.

For selected issue types, Silicon Labs required identifiers that would remain meaningful and stable even if issues moved between projects or their Jira keys changed.

Empyra's Jira Cloud application design supported automatic generation and assignment of unique identifiers based on defined administrative rules.

Project A

ABC-142Unique ID

Project B

XYZ-87Unique ID

Jira key changesIdentifier stays stable

Together, these solutions demonstrated a different role for custom development in Cloud transformation. The objective was not to recreate Data Center's architecture. It was to preserve essential business capabilities using a Cloud-native design.

Choosing the Right Tool

Why Not Every Problem Needs AI

One of the most important lessons from the Silicon Labs engagement was knowing when not to use an AI agent.

Evaluated

AI browser-agent approach

The migration included thousands of dashboards, many of which depended on third-party gadgets or configurations that could not migrate directly. Empyra evaluated an AI browser-agent approach for dashboard reconstruction.

Direction taken

Jira Cloud APIs and deterministic scripts

The team ultimately identified a more practical direction for supported dashboard operations: using Jira Cloud APIs and deterministic scripts rather than relying on browser-driven AI interactions.

When the task involvesBest fit

Defined workFor tasks with clearly defined inputs and supported API operations, conventional automation offered a more predictable and controllable approach.

Conventional automation

InterpretationAI-assisted analysis was better suited to situations requiring interpretation of complex legacy expressions or content.

AI-assisted analysis

The engineering decision was therefore not simply whether a task could be automated. It was determining which combination of AI, APIs, scripting, and human validation would produce the most reliable result. This practical approach helped avoid unnecessary technical complexity while concentrating AI capabilities on problems where they could provide meaningful value.

Business Readiness

Turning Migration Risks into Actionable Decisions

Enterprise Cloud transformation is not complete when the data reaches the destination. Users must still be able to find information, perform their work, understand the new interface, and trust the business processes that depend on the platform.

Empyra and Silicon Labs established a structured validation program that included dry-run migrations, application testing, business-owner engagement, and governance reviews.

Dry-run migrations

Application testing

Business-owner engagement

Governance reviews

Between April and June 2026, the team conducted extensive migration preparation and dry runs, addressing application configurations, compatibility gaps, and post-migration corrections before business validation. A migration council provided a recurring forum for reviewing decisions, risks, dependencies, and readiness.

187Tracked UAT findings

User acceptance testing generated 187 tracked findings. The project analysis classified approximately 93 as Cloud user-experience or platform differences, with 94 relating to technical data or application migration issues. This separation was important.

approx.93

Cloud user-experience or platform differences

Some concerns reflected expected Cloud differences, such as changes to navigation, field presentation, or issue hierarchy.

NavigationField presentationIssue hierarchy

Technical data or application migration issues

Others required technical fixes involving macros, field mappings, scripts, permissions, or app-managed data.

MacrosField mappingsScriptsPermissionsApp-managed data

Rather than treating every report as the same kind of failure, Empyra used the findings to clarify ownership, explain expected changes, and prioritize engineering remediation.

The team also evaluated whether Silicon Labs should migrate in a single coordinated cutover or through multiple phases.

Single coordinated cutover

Multiple phases

A phased migration could reduce immediate change for selected users, but it also introduced serious dependencies.

Projects shared workflows and custom fields. Dashboards referenced issues across teams. Confluence spaces embedded Jira content, and Marketplace applications maintained data models that could not easily operate across separate Data Center and Cloud environments.

The team documented the technical and business trade-offs of both approaches, including configuration duplication, reporting fragmentation, identity dependencies, application migration limitations, and support overhead.

These analyses informed the final cutover planning and the decision to prepare as much configuration and supporting functionality as possible in advance.

Beyond Silicon Labs

A New Model for AI-Assisted Enterprise Migration

The challenges encountered at Silicon Labs are not unique to the semiconductor industry. Organizations that have operated Atlassian Data Center environments for many years often develop similar layers of customization. They depend on scripts, complex filters, third-party applications, historical content, and business integrations that have become essential to daily operations.

Traditional migration tools remain fundamental to moving supported data. But the most difficult work often involves capabilities beyond those tools. The Silicon Labs engagement points toward an evolving model for enterprise transformation:

1
AI-assisted assessment
Identify incompatible configurations, interpret legacy logic, and prioritize remediation opportunities.
2
Intelligent recovery and transformation
Use MCP integrations, Atlassian APIs, and controlled automation to recreate or correct unsupported objects.
3
Cloud-native modernization
Replace server-dependent customizations with supported Forge applications, native features, and modern integration patterns.
4
Business-led validation
Keep engineering corrections tied to operational requirements, with clear ownership, testing, and recovery planning.

The value of this model lies not in replacing engineers with AI, but in giving engineers better ways to investigate, solve, and validate complex migration challenges.

Instead of viewing unsupported functionality as an unavoidable compromise, teams can evaluate whether intelligent tooling or targeted Cloud-native development can close the gap.

The Empyra Difference

Engineering Beyond the Migration Assistant

The Silicon Labs engagement required several disciplines to work together.

Enterprise architects needed to understand how Jira and Confluence were configured.

Application specialists needed to assess Marketplace functionality.

Developers needed to translate legacy customizations into Cloud-compatible designs.

Migration engineers had to reconcile complex data relationships,

while business stakeholders needed confidence that essential work could continue.

AI-assisted remediation introduced new capabilities, but it did not eliminate the need for careful planning, engineering judgment, testing, or collaboration.

Empyra brought these disciplines together through an integrated approach combining Atlassian platform expertise, enterprise integration, custom development, AI-assisted automation, and business validation.

Atlassian platform expertiseEnterprise integrationCustom developmentAI-assisted automationBusiness validation

The engagement illustrates how an Atlassian Platinum Solution Partner can contribute value beyond product configuration and data movement.

By solving the problems behind the migration, Empyra helped create a path toward a more modern, supportable, and intelligent Atlassian ecosystem.

Looking Ahead: From AI-Assisted Engineering to AI-Enabled Teamwork

With Jira, Jira Service Management, and Confluence operating in a Cloud-based environment, Solarity can evaluate opportunities to extend intelligent capabilities into its internal collaboration and service workflows.

Potential areas include

Rovo-assisted knowledge discovery,

service-management support,

engineering context retrieval,

and more intelligent automation.

Those capabilities represent future opportunities rather than production Rovo outcomes delivered under this migration.

For Solarity, a company whose core business already combines AI and human expertise, the next stage is an opportunity to bring the same thoughtful balance into internal ways of working.

For other enterprises considering similar migrations, the message is practical:

Modernization does not always require carrying forward every legacy application.

With the right architectural decisions, AI-assisted engineering, and human validation, organizations can rebuild the capabilities they need for a more sustainable Cloud future.

Articles

Our Latest Blogs

October 28, 2026

Atlassian AI Costs: Where Your Rovo Credits Really Go

Atlassian AI costs are measured in Rovo credits. Every paid Jira, Confluence and collection plan includes a mo

October 23, 2026

Atlassian AI Agents and AMP: A Guide to Identity, Governance and What's Live

Atlassian AI agents are becoming visible, accountable teammates, and AMP (Agentic Multiplayer Protocol) is the

October 14, 2026

Jira Automation Pricing Is Changing: From Flow Runs to Steps, Explained

Jira automation pricing no longer counts flow runs. It counts steps: every trigger, condition, action, branch

View All

Customer Success Stories for Atlassian

See What our customers have to say

View Case Studies

Tufts University

Rakuten

Victoria’s Secret

Jira Work Management Implementation

OTC

Financial Data Company Cloud Adoption Success Story

What Our Customers Have to Say

"Empyra has been extremely helpful in getting Cohen & Company’s Atlassian environments up and running. They have been able to provide great guidance in the options available and also have been able to execute on implementation of those options in a timely and effective manner. They have helped us bring in other departments outside of IT to utilize the service desk options to manage requests and workflows with great reviews from those teams."

Chief Technology Officer

Cohen and Company

"The Empyra consultant has allowed us to take the use of Atlassian's Jira product to new levels across the organization, providing significant improvements in workflows in IT as well as many Finance and Operations teams. There have been some complex requests that Empyra have dealt with, and all have been completed professionally, collaboratively, and efficiently. Empyra have always been super responsive, and are keen to work with the various OTC teams to solve their individual business needs."

Roger Abrahams, Senior Vice President - IT

OTC Industrial Technologies

"As our exclusive Atlassian partner, we brought Empyra in to plan, execute and manage our Atlassian migration to the cloud. From pre to post migration activities and support, Empyra was there to support our project team every step of the way. The migration went as smoothly as possible, and there was no major impact to our business operations."

Sr. Manager, Portfolio Management

"I was very pleased with the consistent can-do attitude the Empyra team brought to each meeting, they quickly came up with solutions, suggestions, recommendations on our various challenges and pitfalls during the migration. My team and I really appreciated that the Empyra team made themselves available 24/7 to troubleshoot with us or answered any questions raised in a timely manner."

Sr. Manager, Portfolio Management

"I'd like to extend a heartfelt thank you to the Empyra team for their exceptional support during our migration of Confluence and Jira from server to Cloud including 14 managed apps. Their expertise and dedication were instrumental in navigating this complex transition smoothly. We truly couldn't have achieved this milestone without their guidance and hard work. Their efforts were a crucial factor in the success of our migration project, and we are deeply appreciative of their partnership. Thank you, Empyra, for being such a reliable and effective ally in our journey to the Cloud!"

Gavi Ornelas-Morales, Tools Support, Supervisor

University of California Office of the President

"monday.com and Empyra provided us with a scalable solution that allows my team to respond quickly to client requests. Additionally, the user-friendly UI with improved workflows helped our underwriting team manage the business in one platform alongside business development. Empyra has done a wonderful job and I envision a long-term relationship on a go-forward basis."