{"resourceId":"okd-5-lightspeed-update-assessment-tech-preview-llm-data","versions":[{"version":"external-c5f41e41c815cd9510a1be5db7c16d8d7e829a8b230e1bde1e49c1ff28b1674e","resource":{"id":"okd-5-lightspeed-update-assessment-tech-preview-llm-data","title":"OKD 5 documentation: OpenShift Lightspeed cluster update assessments are Technology Preview, advisory only, and send cluster state to the configured LLM provider","organization":"OKD community project (Red Hat-sponsored upstream distribution of OpenShift)","sector":"Open source platform documentation","geography":"Global","publishedAt":"Undated \"latest\" documentation page, retrieved 2026-11-09","publicationDate":null,"eventDate":null,"sourceName":"OKD documentation","sourceLabel":"Project documentation (vendor-affiliated)","sourceUrl":"https://docs.okd.io/latest/updating/updating_a_cluster/update-ai.html","evidenceClass":"vendor-claim","outcomeClass":"cautionary","topics":["infrastructure","data-security","developers-agents","governance-procurement"],"finding":"The OKD 5 documentation states that creating cluster update assessments with OpenShift Lightspeed is a Technology Preview feature Red Hat does not recommend for production. The tool runs an AgenticRun custom resource in a read-only sandbox, uses a user-provided LLM to precheck cluster health, node status, operator compatibility, conditional update risks and deprecated APIs, and returns an AI risk score and recommendation; it does not trigger updates. All cluster state data is processed by the configured LLM provider. Prerequisites include cluster-admin privileges, OpenShift Lightspeed Service configured with an LLM, and the Lightspeed Agentic Operator. A product-lifecycle skill recommends updating operators with under four months of remaining support.","sledRelevance":"Gives SLED security and change teams concrete control facts: assessments are advisory, require cluster-admin to generate, and send cluster state to whichever LLM is configured, which matters for CJIS, HIPAA and FERPA-adjacent clusters.","evidence":"Opened OKD docs (latest). The page carries the Technology Preview notice and describes the workflow and skills. Contradiction: Virtualization Review reports Red Hat calling update risk analysis GA in OpenShift 5, while this OKD page labels the AI update assessment Technology Preview; support status may differ by distribution or feature naming.","architectureImplications":"The LLM endpoint choice decides where cluster telemetry goes; disconnected or sovereign clusters need a locally hosted model. AgenticRun and AnalysisResult resources leave an auditable artifact trail.","governanceImplications":"AI risk scores should be advisory inputs to change approval, never the sole criterion; Technology Preview status rules out production reliance under most agency policies.","securityPrivacyImplications":"Cluster state (configuration, alerts, node conditions) leaves the cluster for the LLM provider, so it needs data-classification review and contractual terms if a hosted model is used. The read-only sandbox reduces but does not remove risk.","caveats":"Community OKD documentation, not the OpenShift Container Platform product docs (not opened this run). Page is undated. Support statements may differ for the OpenShift 5 product.","streamIds":["red-hat"],"roles":{"sales":"Sales framing: lead with control and transparency. This documentation shows Lightspeed update assessments are advisory, run in a read-only sandbox and never trigger updates, which answers public-sector worries about autonomous change. Be candid that the feature is Technology Preview in OKD and that cluster state goes to the configured LLM provider. Offer a self-hosted model option for sensitive estates; do not claim production support or fewer failed upgrades (interpretation).","engineering":"Engineering framing: the LLM endpoint is the data boundary. Before testing, decide which model receives cluster state, and use a locally hosted endpoint for regulated clusters. Generating assessments requires cluster-admin, so limit who can trigger them. Validate the AI risk score against known upgrade blockers on a test cluster, and confirm support status for the OpenShift 5 product versus OKD (interpretation).","delivery":"Delivery framing: make AI assessments a reviewed artifact, not a gate. Store AnalysisResult outputs with change records, require human review, and track how often AI recommendations matched actual upgrade outcomes. Keep usage in non-production until the feature is supported for production in the customer's product version, and record the data-classification decision for cluster telemetry (interpretation)."},"roleDetails":{"sales":{"customerProblem":"Agencies want safer cluster upgrades but cannot send sensitive cluster data to unapproved AI services or rely on unsupported features.","stakeholders":["Platform lead","Security / privacy officer","Change advisory board"],"discoveryQuestions":["Which LLM endpoint would receive cluster state?","Is Technology Preview acceptable on non-production clusters?","Who holds cluster-admin today?"],"valueHypothesis":"Bounded: advisory AI prechecks may surface upgrade blockers earlier in planning.","potentialEngagement":"A non-production evaluation of update assessments using a self-hosted model.","unsupportedClaims":["Production support","Fewer failed upgrades","Safe use with any hosted LLM without review"]},"engineering":{"fit":"Reasonable lab fit; not production-ready per this documentation.","architectureIntegration":"Lightspeed Service plus the Agentic Operator run AgenticRun resources in a read-only sandbox using a configured LLM.","prerequisites":["cluster-admin access","OpenShift Lightspeed Service with an LLM","Lightspeed Agentic Operator"],"constraints":["Technology Preview with no production SLA","Cluster state sent to the configured LLM provider","OKD documentation may differ from product support"],"security":"Classify cluster telemetry, prefer local inference and restrict who can trigger assessments.","proofOfValue":["Compare AI risk scores with seeded deprecated-API and operator blockers","Confirm via egress monitoring that no data reaches unapproved endpoints","Verify the tool never initiates updates"]},"delivery":{"work":"Evaluate Lightspeed update assessments in a lab with a local model.","dependencies":["Local model endpoint","Agentic Operator installation","Egress monitoring"],"ownership":"Platform engineering team with security review.","skillsAdoption":"Admins need guidance on interpreting AI risk scores.","governanceCheckpoints":["Data-classification approval for cluster telemetry","Pilot review before any production use"],"acceptanceCriteria":["Proposed: assessment flags all seeded blockers on the test cluster","Proposed: zero egress to unapproved endpoints during the pilot","Proposed: every assessment archived with its change record"],"risks":["Sensitive data exposure to the LLM provider","Over-trust of the AI risk score","Feature status changes"]}},"retrievedAt":"2026-11-09T22:03:56-06:00","enrichedAt":"2026-11-09T22:20:00-06:00","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Advisory assessments may help less experienced admins plan updates, but staff must still interpret AI risk scores.","procurementImplications":"If a hosted LLM is used, contracts must cover handling of cluster telemetry; self-hosting shifts cost to inference capacity.","operatingModelImplications":"Update planning gains an AI-generated artifact; change boards should define how it is reviewed and retained.","sourceVerification":{"openedUrl":"https://docs.okd.io/latest/updating/updating_a_cluster/update-ai.html","referenceExcerpt":"All cluster state data is processed only by the LLM provider you configured OpenShift Lightspeed Service (OLS) to use.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}