--- title: From a Jira Ticket to a Running Salesforce UI Test,... description: A Capgemini architect describes a workflow where an AI coding agent takes a Jira/Xray test ticket and generates a running UTAM-based Salesforce UI test. The... canonical: https://daily.dev/posts/from-a-jira-ticket-to-a-running-salesforce-ui-test-written-by-an-ai-un9gyvfgm twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: From a Jira Ticket to a Running Salesforce UI Test, Written by an AI | daily.dev og:description: A Capgemini architect describes a workflow where an AI coding agent takes a Jira/Xray test ticket and generates a running UTAM-based Salesforce UI test. The... og:url: https://daily.dev/posts/from-a-jira-ticket-to-a-running-salesforce-ui-test-written-by-an-ai-un9gyvfgm og:image: https://api.daily.dev/og/posts/Un9gYVfgm.png og:image:alt: From a Jira Ticket to a Running Salesforce UI Test, Written by an AI og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # From a Jira Ticket to a Running Salesforce UI Test, Written by an AI **[Medium](https://daily.dev/sources/medium_js)** · 10 min read · 1 upvotes · 0 comments ## Summary A Capgemini architect describes a workflow where an AI coding agent takes a Jira/Xray test ticket and generates a running UTAM-based Salesforce UI test. The setup feeds the agent the raw ticket XML, project conventions (in a CLAUDE.md file), and live org feedback. Key design decisions include verifying outcomes against the database via SOQL rather than DOM/toast messages, splitting tests into UI-lane specs and fast browserless config-guards, and enforcing a rule that assertions are never weakened to make a test pass. When tests fail, the same agent classifies the failure (configuration drift, missing data, etc.), suggests a concrete fix, and routes the result with the responsible developer to Teams or Slack before a human opens the log. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How can I get an AI agent to write Salesforce UTAM UI tests directly from Jira tickets? Feed the agent the raw Xray export of the Jira test ticket (its Acceptance Criteria and Manual Test Steps serve as the spec), give it project conventions in a file like CLAUDE.md describing login, navigation, and shadow-DOM helpers, then let it run the generated UTAM/WebdriverIO/Jasmine spec against the org and iterate on failures. The key rule: never weaken an assertion just to make a red test pass. _Teams automating Salesforce UI test authoring track workflows like this one on daily.dev._ ### Why should Salesforce UI end-to-end tests verify the database instead of a success toast on the screen? A success toast only confirms the save fired, not that the correct values persisted or that post-save triggers and flows ran correctly, so tests should poll the data layer with a SOQL query until the record exists with the expected values and assert against that. Screen signals are transient and timing-sensitive, making them unreliable for confirming a real outcome. _Developers deciding how to make Salesforce UI tests less flaky can compare approaches like this on daily.dev._ ### How can failing CI tests be automatically triaged and routed to the right developer? A pipeline can send the raw assertion diff from a failed test back to an AI agent, which classifies the failure type (configuration drift, missing data, an unreached page, or a known defect), proposes one concrete fix, and resolves the developer who built the story from ticket history, then posts the result as an adaptive card to Teams or Slack before any human reads the log. _Engineers building automated CI failure triage can follow real implementations like this on daily.dev._ ## Similar posts on daily.dev - [Engineering Multi-Agent AI Teams That Build and Test Themselves](https://daily.dev/posts/engineering-multi-agent-ai-teams-that-build-and-test-themselves-ehcixev11) · Salesforce Engineering · 1 upvotes · 0 comments - [Why better tickets help agents write better code](https://daily.dev/posts/why-better-tickets-help-agents-write-better-code-suwct5vww) · Atlassian · 1 upvotes · 0 comments - [Fire Your QA Today: Automate QA testing with AI](https://daily.dev/posts/fire-your-qa-today-automate-qa-testing-with-ai-7jyqjppkp) · Product Hunt · 0 upvotes · 0 comments - [Sauce Labs Launches AI Agent to Automate Test Creation and Close the DevOps “Velocity Gap”](https://daily.dev/posts/sauce-labs-launches-ai-agent-to-automate-test-creation-and-close-the-devops-velocity-gap--pp5hm6kbq) · InfoQ · 0 upvotes · 0 comments --- Tags: [#testing](https://daily.dev/tags/testing), [#ai-agents](https://daily.dev/tags/ai-agents), [#salesforce](https://daily.dev/tags/salesforce) [View this post on daily.dev](https://daily.dev/posts/from-a-jira-ticket-to-a-running-salesforce-ui-test-written-by-an-ai-un9gyvfgm) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"From a Jira Ticket to a Running Salesforce UI Test, Written by an AI","url":"https://daily.dev/posts/from-a-jira-ticket-to-a-running-salesforce-ui-test-written-by-an-ai-un9gyvfgm","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/from-a-jira-ticket-to-a-running-salesforce-ui-test-written-by-an-ai-un9gyvfgm"},"datePublished":"2026-07-21T07:31:33.094Z","dateModified":"2026-09-13T18:40:06.319Z","description":"A Capgemini architect describes a workflow where an AI coding agent takes a Jira/Xray test ticket and generates a running UTAM-based Salesforce UI test. The...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fa528541ced4d9aa2a370a0dcef36f9c?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fa528541ced4d9aa2a370a0dcef36f9c?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Medium","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/from-a-jira-ticket-to-a-running-salesforce-ui-test-written-by-an-ai-un9gyvfgm","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"testing,ai-agents,salesforce","timeRequired":"PT10M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"From a Jira Ticket to a Running Salesforce UI Test, Written by an AI"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/from-a-jira-ticket-to-a-running-salesforce-ui-test-written-by-an-ai-un9gyvfgm#faq","mainEntity":[{"@type":"Question","name":"How can I get an AI agent to write Salesforce UTAM UI tests directly from Jira tickets?","acceptedAnswer":{"@type":"Answer","text":"Feed the agent the raw Xray export of the Jira test ticket (its Acceptance Criteria and Manual Test Steps serve as the spec), give it project conventions in a file like CLAUDE.md describing login, navigation, and shadow-DOM helpers, then let it run the generated UTAM/WebdriverIO/Jasmine spec against the org and iterate on failures. The key rule: never weaken an assertion just to make a red test pass. Teams automating Salesforce UI test authoring track workflows like this one on daily.dev."}},{"@type":"Question","name":"Why should Salesforce UI end-to-end tests verify the database instead of a success toast on the screen?","acceptedAnswer":{"@type":"Answer","text":"A success toast only confirms the save fired, not that the correct values persisted or that post-save triggers and flows ran correctly, so tests should poll the data layer with a SOQL query until the record exists with the expected values and assert against that. Screen signals are transient and timing-sensitive, making them unreliable for confirming a real outcome. Developers deciding how to make Salesforce UI tests less flaky can compare approaches like this on daily.dev."}},{"@type":"Question","name":"How can failing CI tests be automatically triaged and routed to the right developer?","acceptedAnswer":{"@type":"Answer","text":"A pipeline can send the raw assertion diff from a failed test back to an AI agent, which classifies the failure type (configuration drift, missing data, an unreached page, or a known defect), proposes one concrete fix, and resolves the developer who built the story from ticket history, then posts the result as an adaptive card to Teams or Slack before any human reads the log. Engineers building automated CI failure triage can follow real implementations like this on daily.dev."}}]} ```