{ "policy": { "version": 5, "patterns": { "version": 1, "method": "CURATED_PRACTICE_TOPIC", "notice": "Pattern topics identify design choices to practice. Read the ticket's acceptance criteria and justify the simplest suitable approach. Tags are not capability or ownership evidence; an untagged ticket has no curated pattern topic assigned." }, "fieldMix": { "version": 1, "method": "CURATED_ESTIMATE", "notice": "Field percentages are editorial estimates of the ticket's engineering focus. They total 100%; they are not measured time, proficiency scores, or ownership evidence." }, "contentStatus": "PRACTICE_BRIEF", "assessmentStatus": "NOT_QUALIFIED", "evidenceUse": "NONE", "aiPolicy": "AI tools are welcome during implementation. Record assumptions, review the result, and verify its behavior.", "notice": "Fictional engineering practice briefs. Starter repositories, fixtures, automated grading, and verified ownership are not included.", "outcomeEvidence": "Tests, patches, and runbooks are requested deliverables. They become Outcome Evidence only through a qualified Mission and immutable Evidence IDs.", "ownershipEvidence": "Independent adaptation must be observed under a declared verification policy and cite immutable Evidence IDs. Completing a planning ticket establishes no Ownership Evidence." }, "patternTopics": [ { "id": "factory-method", "label": "Factory Method", "group": "Creational" }, { "id": "abstract-factory", "label": "Abstract Factory", "group": "Creational" }, { "id": "builder", "label": "Builder", "group": "Creational" }, { "id": "prototype", "label": "Prototype", "group": "Creational" }, { "id": "singleton", "label": "Singleton", "group": "Creational" }, { "id": "adapter", "label": "Adapter", "group": "Structural" }, { "id": "bridge", "label": "Bridge", "group": "Structural" }, { "id": "composite", "label": "Composite", "group": "Structural" }, { "id": "decorator", "label": "Decorator", "group": "Structural" }, { "id": "facade", "label": "Facade", "group": "Structural" }, { "id": "flyweight", "label": "Flyweight", "group": "Structural" }, { "id": "proxy", "label": "Proxy", "group": "Structural" }, { "id": "chain-of-responsibility", "label": "Chain of Responsibility", "group": "Behavioral" }, { "id": "command", "label": "Command", "group": "Behavioral" }, { "id": "interpreter", "label": "Interpreter", "group": "Behavioral" }, { "id": "iterator", "label": "Iterator", "group": "Behavioral" }, { "id": "mediator", "label": "Mediator", "group": "Behavioral" }, { "id": "memento", "label": "Memento", "group": "Behavioral" }, { "id": "observer", "label": "Observer", "group": "Behavioral" }, { "id": "state", "label": "State", "group": "Behavioral" }, { "id": "strategy", "label": "Strategy", "group": "Behavioral" }, { "id": "template-method", "label": "Template Method", "group": "Behavioral" }, { "id": "visitor", "label": "Visitor", "group": "Behavioral" }, { "id": "ports-and-adapters", "label": "Ports and Adapters", "group": "Architectural" }, { "id": "cqrs", "label": "CQRS", "group": "Architectural" }, { "id": "strangler-fig", "label": "Strangler Fig", "group": "Architectural" }, { "id": "saga", "label": "Saga", "group": "Distributed and reliability" }, { "id": "transactional-outbox", "label": "Transactional Outbox", "group": "Distributed and reliability" }, { "id": "circuit-breaker", "label": "Circuit Breaker", "group": "Distributed and reliability" }, { "id": "bulkhead", "label": "Bulkhead", "group": "Distributed and reliability" } ], "projects": [ { "id": "e19da797-4e34-424a-8bea-e1bd111f2f21", "key": "BSLO", "title": "Checkout service-level objectives", "field": "Site reliability", "summary": "Define customer-facing reliability indicators and actionable budget policies.", "context": "A fictional checkout service reports process uptime while customers experience failed orders and slow confirmations.", "stack": [ "TypeScript", "Prometheus", "HTTP" ], "prerequisites": [ "Create synthetic request and order-event traces plus a local query or metrics fixture; no production telemetry required." ], "developerValue": "Practice SLI semantics, alert evaluation, and reliability tradeoffs.", "companyValue": "Align reliability discussions with customer outcomes and explicit measurement limits.", "delivery": "Deliver executable indicator queries, alert fixtures, and an SLO decision record.", "phases": [ { "id": "define", "title": "Define indicators", "goal": "Specify measurable user outcomes and valid denominators." }, { "id": "measure", "title": "Compute and alert", "goal": "Handle missing data and evaluate budget burn." }, { "id": "operate", "title": "Use the objective", "goal": "Connect reliability policy to reviewable operational decisions." } ], "tickets": [ { "id": "82ab987d-c26d-404b-b5f2-9b94ef2e1ddc", "key": "BSLO-101", "title": "Define eligible checkout attempts and successful completion", "type": "TASK", "priority": "MEDIUM", "difficulty": "FOUNDATIONAL", "estimateMinutes": 60, "phaseId": "define", "dependsOn": [], "scenario": "Availability reports count health checks as customer success.", "acceptanceCriteria": [ "Define eligible attempts and completion deadlines.", "Exclude synthetic probes from customer denominators.", "Document validation failures and abandoned checkouts separately." ], "implementationNotes": [ "Do not exclude service failures to improve the ratio." ], "verification": [ "Classify representative success and failure traces.", "Reject a denominator that includes only completed orders." ], "deliverables": [ "SLI event contract." ], "rollout": "Review event semantics before publishing an objective.", "skills": [ "SLI design" ], "fieldMix": [ { "field": "Site reliability", "percentage": 100 } ], "patterns": [] }, { "id": "1dee3a71-bf26-4dfd-b903-57721a6a48e7", "key": "BSLO-102", "title": "Deduplicate retried checkout attempts in indicator calculations", "type": "BUG", "priority": "HIGH", "difficulty": "INTERMEDIATE", "estimateMinutes": 150, "phaseId": "define", "dependsOn": [ "BSLO-101" ], "scenario": "Client retries inflate both request volume and apparent success.", "acceptanceCriteria": [ "Count one logical attempt under the declared identity.", "Preserve retry observations separately.", "Flag missing identities without guessing deduplication." ], "implementationNotes": [ "Avoid user-identifying metric labels." ], "verification": [ "Count a retried successful attempt once.", "Expose ambiguous records with missing attempt IDs." ], "deliverables": [ "Deduplicated indicator query." ], "rollout": "Compare old and new counts before switching dashboards.", "skills": [ "Metrics", "Idempotency" ], "fieldMix": [ { "field": "Site reliability", "percentage": 60 }, { "field": "Data engineering", "percentage": 40 } ], "patterns": [] }, { "id": "ca7a1b21-ade8-49fd-b32f-7cc555e18db0", "key": "BSLO-103", "title": "Compute completion latency from consistent event pairs", "type": "TASK", "priority": "HIGH", "difficulty": "ADVANCED", "estimateMinutes": 180, "phaseId": "measure", "dependsOn": [ "BSLO-102" ], "scenario": "Latency is measured from different start events across client versions.", "acceptanceCriteria": [ "Specify start and completion event semantics.", "Reject negative or unmatched durations.", "Track excluded samples and instrumentation version." ], "implementationNotes": [ "State clock assumptions explicitly." ], "verification": [ "Compute known synthetic durations.", "Detect clock skew and unmatched completion events." ], "deliverables": [ "Latency indicator implementation." ], "rollout": "Run both definitions during comparison; retain the prior dashboard for diagnosis.", "skills": [ "Observability", "Time handling" ], "fieldMix": [ { "field": "Site reliability", "percentage": 60 }, { "field": "Data engineering", "percentage": 40 } ], "patterns": [] }, { "id": "69dbe211-67a5-4f1e-92e7-166559ead4bc", "key": "BSLO-104", "title": "Keep missing telemetry distinct from successful service", "type": "BUG", "priority": "HIGH", "difficulty": "INTERMEDIATE", "estimateMinutes": 120, "phaseId": "measure", "dependsOn": [ "BSLO-103" ], "scenario": "A metrics outage produces an empty query that the dashboard renders as healthy.", "acceptanceCriteria": [ "Represent no data separately from zero failures.", "Display data freshness and coverage.", "Alert on measurement failure independently." ], "implementationNotes": [ "Unknown reliability cannot consume zero budget by default." ], "verification": [ "Show healthy complete telemetry.", "Drop a source stream and display unknown coverage." ], "deliverables": [ "Missing-data handling." ], "rollout": "Enable measurement alerts before relying on budget policy.", "skills": [ "Monitoring" ], "fieldMix": [ { "field": "Site reliability", "percentage": 80 }, { "field": "Frontend", "percentage": 20 } ], "patterns": [] }, { "id": "8337d4a2-93ee-44fb-94f9-8d4bee7fe1ab", "key": "BSLO-105", "title": "Implement multi-window error-budget burn calculations", "type": "TASK", "priority": "HIGH", "difficulty": "ADVANCED", "estimateMinutes": 210, "phaseId": "measure", "dependsOn": [ "BSLO-102", "BSLO-104" ], "scenario": "A brief spike pages the team while a slower sustained incident passes unnoticed.", "acceptanceCriteria": [ "Calculate burn against the declared objective.", "Require aligned short and long windows for the chosen alert.", "Handle window edges and low sample counts explicitly." ], "implementationNotes": [ "Thresholds are scenario assumptions, not universal defaults." ], "verification": [ "Trigger on sustained synthetic burn.", "Avoid paging for an isolated low-volume failure under the documented policy." ], "deliverables": [ "Burn-rate queries and fixtures." ], "rollout": "Run alerts without notifications locally before operational adoption.", "skills": [ "Alerting", "Time-series analysis" ], "fieldMix": [ { "field": "Site reliability", "percentage": 70 }, { "field": "Data engineering", "percentage": 30 } ], "patterns": [] }, { "id": "dddd7323-f403-4b5c-bd9b-f847880985f6", "key": "BSLO-106", "title": "Separate dependency failure from the customer-facing objective", "type": "TASK", "priority": "MEDIUM", "difficulty": "ADVANCED", "estimateMinutes": 180, "phaseId": "measure", "dependsOn": [ "BSLO-105" ], "scenario": "The team wants to exclude payment-provider outages from checkout reliability.", "acceptanceCriteria": [ "Keep customer outcome accounting intact.", "Add dependency attribution as a separate diagnostic dimension.", "Expose uncertain attribution without changing the denominator." ], "implementationNotes": [ "Do not transfer responsibility by redefining failed outcomes away." ], "verification": [ "Count a dependency-caused customer failure.", "Show attribution missing while retaining the failure." ], "deliverables": [ "Attribution dashboard contract." ], "rollout": "Add diagnostics alongside the objective; preserve historical customer outcomes.", "skills": [ "Reliability analysis" ], "fieldMix": [ { "field": "Site reliability", "percentage": 80 }, { "field": "System design", "percentage": 20 } ], "patterns": [] }, { "id": "d52c9403-e3c7-49e8-b57a-eff445ab21a6", "key": "BSLO-107", "title": "Define release actions for exhausted error budget", "type": "TASK", "priority": "HIGH", "difficulty": "EXPERT", "estimateMinutes": 300, "phaseId": "operate", "dependsOn": [ "BSLO-105", "BSLO-106" ], "scenario": "An exhausted budget triggers a blanket release freeze, including urgent reliability fixes.", "acceptanceCriteria": [ "Distinguish feature, risk-reduction, and emergency changes.", "Define reviewed exception authority and expiry.", "Compare business urgency against measured reliability risk." ], "implementationNotes": [ "Policy provides decision support, not automatic business authority." ], "verification": [ "Apply policy to a normal feature release.", "Document an emergency exception with unresolved risks." ], "deliverables": [ "Error-budget policy decision record." ], "rollout": "Trial the policy in a tabletop; preserve human release accountability.", "skills": [ "Operational policy", "Tradeoff analysis" ], "fieldMix": [ { "field": "Site reliability", "percentage": 80 }, { "field": "System design", "percentage": 20 } ], "patterns": [] }, { "id": "78da471b-f9d4-4c81-8565-9502f011614a", "key": "BSLO-108", "title": "Build an SLO dashboard with bounded diagnostic dimensions", "type": "STORY", "priority": "MEDIUM", "difficulty": "INTERMEDIATE", "estimateMinutes": 150, "phaseId": "operate", "dependsOn": [ "BSLO-106" ], "scenario": "Engineers cannot relate budget burn to endpoint versions without exposing user data.", "acceptanceCriteria": [ "Show objective, burn, eligible volume, and coverage.", "Allow only bounded endpoint/version dimensions.", "Keep customer identifiers out of labels and URLs." ], "implementationNotes": [ "Dashboard totals must reconcile with source fixtures." ], "verification": [ "Reconcile known synthetic totals.", "Reject an unbounded user-ID dimension." ], "deliverables": [ "SLO dashboard definition." ], "rollout": "Publish read-only views first; restore prior queries if totals diverge.", "skills": [ "Observability", "Privacy" ], "fieldMix": [ { "field": "Site reliability", "percentage": 50 }, { "field": "Frontend", "percentage": 30 }, { "field": "Privacy engineering", "percentage": 20 } ], "patterns": [] }, { "id": "6cfabedd-ea85-49d0-9696-9b9648f35c62", "key": "BSLO-109", "title": "Rehearse an objective change without rewriting historical results", "type": "TASK", "priority": "HIGH", "difficulty": "ADVANCED", "estimateMinutes": 180, "phaseId": "operate", "dependsOn": [ "BSLO-107", "BSLO-108" ], "scenario": "A new completion deadline would make last month's results look better if applied retrospectively.", "acceptanceCriteria": [ "Version objective and indicator definitions.", "Compute new results from an explicit effective time.", "Preserve historical values under their original definition." ], "implementationNotes": [ "Show comparison overlap without relabeling old performance." ], "verification": [ "Run old and new definitions on the same fixture.", "Verify historical records remain bound to the old version." ], "deliverables": [ "SLO revision rehearsal." ], "rollout": "Run overlapping views before changing the active objective.", "skills": [ "Versioning", "Operational integrity" ], "fieldMix": [ { "field": "Site reliability", "percentage": 70 }, { "field": "Data engineering", "percentage": 30 } ], "patterns": [] }, { "id": "6de914b1-bdbb-48e9-854c-67d5b7451e36", "key": "BSLO-110", "title": "Write an SLO interpretation guide for low-traffic periods", "type": "CHORE", "priority": "LOW", "difficulty": "FOUNDATIONAL", "estimateMinutes": 60, "phaseId": "operate", "dependsOn": [ "BSLO-109" ], "scenario": "A single failure overnight produces a dramatic percentage without explaining the sample size.", "acceptanceCriteria": [ "Display eligible event count with the ratio.", "Explain low-volume uncertainty.", "Document when to inspect individual synthetic traces." ], "implementationNotes": [ "Avoid promises of perfect reliability." ], "verification": [ "Interpret one failure in a small sample.", "Distinguish zero traffic from a healthy measured window." ], "deliverables": [ "SLO interpretation guide." ], "rollout": "Link guidance from dashboards and alert descriptions.", "skills": [ "Technical writing", "Reliability" ], "fieldMix": [ { "field": "Site reliability", "percentage": 100 } ], "patterns": [] } ] } ] }