AI operations
A 180-lesson command-line track for operating model-backed applications from first concepts through incident response.
180 lessons
12 categories
27 checkpoints
Courses
Choose your AI Ops mission path.
A 180-lesson command-line track for operating model-backed applications from first concepts through incident response.
Track progress
0/180 lessons
0/18 missions
0/11 briefings
12 courses
Recommended path
Build one layer at a time.
Follow the course order for a steady progression, or open any course when you need a focused refresher. Nothing is locked.
- 01 AI systems foundations 15 lessons
- 02 CLI and workspace hygiene 12 lessons
- 03 Models, artifacts, and runtimes 16 lessons
- 04 Inference requests and APIs 16 lessons
- 05 Prompt and configuration operations 14 lessons
- 06 Evaluations and datasets 18 lessons
- 07 Retrieval and embeddings 16 lessons
- 08 Serving, containers, and resources 17 lessons
- 09 Observability and tracing 15 lessons
- 10 Safety, privacy, and governance 15 lessons
- 11 Cost, capacity, and reliability 14 lessons
- 12 Incident response and capstones 12 lessons
0/15
AI systems foundations
Understand models, requests, components, failure boundaries, and the operator's evidence-first role.
15 short lessons · 1 checkpoint 0/12 CLI and workspace hygieneBuild careful command, path, redaction, configuration, and evidence habits for AI operations work.
12 short lessons · 3 checkpoints 0/16 Models, artifacts, and runtimesInspect model manifests, versions, artifacts, runtime compatibility, accelerators, and rollout evidence.
16 short lessons · 2 checkpoints 0/16 Inference requests and APIsInspect bounded loopback requests, response envelopes, status codes, timeouts, retries, and streaming signals.
16 short lessons · 3 checkpoints 0/14 Prompt and configuration operationsVersion prompts and configuration, compare changes, validate variables, and prepare controlled rollbacks.
14 short lessons · 2 checkpoints 0/18 Evaluations and datasetsOperate golden sets, evaluation runs, thresholds, regressions, slices, annotations, and release evidence.
18 short lessons · 3 checkpoints 0/16 Retrieval and embeddingsInspect document ingestion, chunks, embeddings, indexes, retrieval quality, freshness, and grounded evidence.
16 short lessons · 3 checkpoints 0/17 Serving, containers, and resourcesInspect services, containers, Kubernetes resources, GPU signals, health, configuration, and rollout readiness.
17 short lessons · 1 checkpoint 0/15 Observability and tracingUse logs, metrics, traces, request identifiers, latency percentiles, and error budgets to explain behavior.
15 short lessons · 2 checkpoints 0/15 Safety, privacy, and governanceReview guardrails, redaction, data boundaries, access, retention, model cards, and operational approvals.
15 short lessons · 2 checkpoints 0/14 Cost, capacity, and reliabilityInspect token cost, capacity, concurrency, caching, fallback strategy, load signals, and reliability tradeoffs.
14 short lessons · 2 checkpoints 0/12 Incident response and capstonesCombine system, model, retrieval, serving, safety, cost, and evidence habits in operator-style incidents.
12 short lessons · 3 checkpoints
Save progress
Keep learning across sessions.
Create a free account to sync completed lessons, XP, streaks, course status, and your next lesson across sessions.
Checking account status...
Progress sync is idle.
0XP
New learnerrank
0day streak
0best streak
0daily streak
0lessons
0courses
0missions
0tasks
Noverified
Progress sync stores completion IDs, scores, streaks, badges, and game settings. Terminal contents, editor snippets, lab scratch, email, and real names are never published on leaderboards or share cards.
All lessons
Short missions for terminal confidence.
01
AI systems foundations
Map an AI application
Map an AI application through a bounded evidence-first AI operations workflow in the training lab.
Beginner 02 AI systems foundations Separate model and applicationSeparate model and application through a bounded evidence-first AI operations workflow in the training lab.
Beginner 03 AI systems foundations Trace a request lifecycleTrace a request lifecycle through a bounded evidence-first AI operations workflow in the training lab.
Beginner 04 AI systems foundations Name the serving boundaryName the serving boundary through a bounded evidence-first AI operations workflow in the training lab.
Beginner 05 AI systems foundations Read an inference contractRead an inference contract through a bounded evidence-first AI operations workflow in the training lab.
Beginner 06 AI systems foundations Distinguish training and inferenceDistinguish training and inference through a bounded evidence-first AI operations workflow in the training lab.
Beginner 07 AI systems foundations Identify deterministic componentsIdentify deterministic components through a bounded evidence-first AI operations workflow in the training lab.
Beginner 08 AI systems foundations Recognize probabilistic outputRecognize probabilistic output through a bounded evidence-first AI operations workflow in the training lab.
Beginner Checkpoint 09 AI systems foundations Separate data and instructionsSeparate data and instructions through a bounded evidence-first AI operations workflow in the training lab.
Beginner 10 AI systems foundations Locate an operational failureLocate an operational failure through a bounded evidence-first AI operations workflow in the training lab.
Beginner 11 AI systems foundations Read a system dependency mapRead a system dependency map through a bounded evidence-first AI operations workflow in the training lab.
Beginner 12 AI systems foundations Define an operator signalDefine an operator signal through a bounded evidence-first AI operations workflow in the training lab.
Beginner 13 AI systems foundations Use evidence before actionUse evidence before action through a bounded evidence-first AI operations workflow in the training lab.
Beginner 14 AI systems foundations Write a system baselineWrite a system baseline through a bounded evidence-first AI operations workflow in the training lab.
Beginner 15 AI systems foundations Foundations review checkpointFoundations review checkpoint through a bounded evidence-first AI operations workflow in the training lab.
Beginner 16 CLI and workspace hygiene Orient inside the AI labOrient inside the AI lab through a bounded evidence-first AI operations workflow in the training lab.
Beginner 17 CLI and workspace hygiene Read the workspace layoutRead the workspace layout through a bounded evidence-first AI operations workflow in the training lab.
Beginner 18 CLI and workspace hygiene Inspect redacted environment dataInspect redacted environment data through a bounded evidence-first AI operations workflow in the training lab.
Beginner 19 CLI and workspace hygiene Protect local configurationProtect local configuration through a bounded evidence-first AI operations workflow in the training lab.
Beginner 20 CLI and workspace hygiene Name files predictablyName files predictably through a bounded evidence-first AI operations workflow in the training lab.
Beginner 21 CLI and workspace hygiene Compare a configuration copyCompare a configuration copy through a bounded evidence-first AI operations workflow in the training lab.
Beginner Checkpoint 22 CLI and workspace hygiene Search without exposing secretsSearch without exposing secrets through a bounded evidence-first AI operations workflow in the training lab.
Beginner 23 CLI and workspace hygiene Capture bounded command outputCapture bounded command output through a bounded evidence-first AI operations workflow in the training lab.
Beginner 24 CLI and workspace hygiene Build an evidence directoryBuild an evidence directory through a bounded evidence-first AI operations workflow in the training lab.
Beginner 25 CLI and workspace hygiene Verify a manifest checksumVerify a manifest checksum through a bounded evidence-first AI operations workflow in the training lab.
Beginner Checkpoint 26 CLI and workspace hygiene Write an operator noteWrite an operator note through a bounded evidence-first AI operations workflow in the training lab.
Beginner 27 CLI and workspace hygiene Workspace hygiene checkpointWorkspace hygiene checkpoint through a bounded evidence-first AI operations workflow in the training lab.
Beginner Checkpoint 28 Models, artifacts, and runtimes List model inventoryList model inventory through a bounded evidence-first AI operations workflow in the training lab.
Beginner 29 Models, artifacts, and runtimes Read a model manifestRead a model manifest through a bounded evidence-first AI operations workflow in the training lab.
Beginner 30 Models, artifacts, and runtimes Compare model versionsCompare model versions through a bounded evidence-first AI operations workflow in the training lab.
Beginner 31 Models, artifacts, and runtimes Inspect artifact metadataInspect artifact metadata through a bounded evidence-first AI operations workflow in the training lab.
Beginner 32 Models, artifacts, and runtimes Verify an artifact checksumVerify an artifact checksum through a bounded evidence-first AI operations workflow in the training lab.
Beginner 33 Models, artifacts, and runtimes Match model and runtimeMatch model and runtime through a bounded evidence-first AI operations workflow in the training lab.
Beginner 34 Models, artifacts, and runtimes Read context limitsRead context limits through a bounded evidence-first AI operations workflow in the training lab.
Beginner 35 Models, artifacts, and runtimes Inspect tokenizer metadataInspect tokenizer metadata through a bounded evidence-first AI operations workflow in the training lab.
Beginner Checkpoint 36 Models, artifacts, and runtimes Compare quantization profilesCompare quantization profiles through a bounded evidence-first AI operations workflow in the training lab.
Core 37 Models, artifacts, and runtimes Read memory requirementsRead memory requirements through a bounded evidence-first AI operations workflow in the training lab.
Core 38 Models, artifacts, and runtimes Inspect accelerator availabilityInspect accelerator availability through a bounded evidence-first AI operations workflow in the training lab.
Core 39 Models, artifacts, and runtimes Spot a runtime mismatchSpot a runtime mismatch through a bounded evidence-first AI operations workflow in the training lab.
Core 40 Models, artifacts, and runtimes Choose a rollback artifactChoose a rollback artifact through a bounded evidence-first AI operations workflow in the training lab.
Core 41 Models, artifacts, and runtimes Review model provenanceReview model provenance through a bounded evidence-first AI operations workflow in the training lab.
Core 42 Models, artifacts, and runtimes Build a model baselineBuild a model baseline through a bounded evidence-first AI operations workflow in the training lab.
Core 43 Models, artifacts, and runtimes Models and runtimes checkpointModels and runtimes checkpoint through a bounded evidence-first AI operations workflow in the training lab.
Core Checkpoint 44 Inference requests and APIs Check gateway healthCheck gateway health through a bounded evidence-first AI operations workflow in the training lab.
Core 45 Inference requests and APIs List served modelsList served models through a bounded evidence-first AI operations workflow in the training lab.
Core 46 Inference requests and APIs Read a request envelopeRead a request envelope through a bounded evidence-first AI operations workflow in the training lab.
Core 47 Inference requests and APIs Read a response envelopeRead a response envelope through a bounded evidence-first AI operations workflow in the training lab.
Core 48 Inference requests and APIs Inspect token usageInspect token usage through a bounded evidence-first AI operations workflow in the training lab.
Core 49 Inference requests and APIs Distinguish client and server errorsDistinguish client and server errors through a bounded evidence-first AI operations workflow in the training lab.
Core 50 Inference requests and APIs Reason about timeoutsReason about timeouts through a bounded evidence-first AI operations workflow in the training lab.
Core Checkpoint 51 Inference requests and APIs Review retry boundariesReview retry boundaries through a bounded evidence-first AI operations workflow in the training lab.
Core Checkpoint 52 Inference requests and APIs Inspect a request identifierInspect a request identifier through a bounded evidence-first AI operations workflow in the training lab.
Core 53 Inference requests and APIs Follow a trace identifierFollow a trace identifier through a bounded evidence-first AI operations workflow in the training lab.
Core 54 Inference requests and APIs Compare batch and single requestsCompare batch and single requests through a bounded evidence-first AI operations workflow in the training lab.
Core 55 Inference requests and APIs Read a streaming event shapeRead a streaming event shape through a bounded evidence-first AI operations workflow in the training lab.
Core 56 Inference requests and APIs Inspect rate-limit metadataInspect rate-limit metadata through a bounded evidence-first AI operations workflow in the training lab.
Core 57 Inference requests and APIs Review idempotency guidanceReview idempotency guidance through a bounded evidence-first AI operations workflow in the training lab.
Core 58 Inference requests and APIs Build an API evidence bundleBuild an API evidence bundle through a bounded evidence-first AI operations workflow in the training lab.
Core 59 Inference requests and APIs Inference API checkpointInference API checkpoint through a bounded evidence-first AI operations workflow in the training lab.
Core Checkpoint 60 Prompt and configuration operations List prompt versionsList prompt versions through a bounded evidence-first AI operations workflow in the training lab.
Core 61 Prompt and configuration operations Inspect a prompt manifestInspect a prompt manifest through a bounded evidence-first AI operations workflow in the training lab.
Core 62 Prompt and configuration operations Separate system and user inputSeparate system and user input through a bounded evidence-first AI operations workflow in the training lab.
Core 63 Prompt and configuration operations Validate prompt variablesValidate prompt variables through a bounded evidence-first AI operations workflow in the training lab.
Core 64 Prompt and configuration operations Compare prompt revisionsCompare prompt revisions through a bounded evidence-first AI operations workflow in the training lab.
Core 65 Prompt and configuration operations Review a prompt rolloutReview a prompt rollout through a bounded evidence-first AI operations workflow in the training lab.
Core 66 Prompt and configuration operations Locate a prompt ownerLocate a prompt owner through a bounded evidence-first AI operations workflow in the training lab.
Core Checkpoint 67 Prompt and configuration operations Inspect configuration precedenceInspect configuration precedence through a bounded evidence-first AI operations workflow in the training lab.
Core 68 Prompt and configuration operations Read a redacted environmentRead a redacted environment through a bounded evidence-first AI operations workflow in the training lab.
Core 69 Prompt and configuration operations Detect configuration driftDetect configuration drift through a bounded evidence-first AI operations workflow in the training lab.
Core 70 Prompt and configuration operations Prepare a prompt rollbackPrepare a prompt rollback through a bounded evidence-first AI operations workflow in the training lab.
Core 71 Prompt and configuration operations Write a change noteWrite a change note through a bounded evidence-first AI operations workflow in the training lab.
Core 72 Prompt and configuration operations Review prompt observabilityReview prompt observability through a bounded evidence-first AI operations workflow in the training lab.
Core 73 Prompt and configuration operations Prompt operations checkpointPrompt operations checkpoint through a bounded evidence-first AI operations workflow in the training lab.
Core Checkpoint 74 Evaluations and datasets Inspect a golden datasetInspect a golden dataset through a bounded evidence-first AI operations workflow in the training lab.
Core 75 Evaluations and datasets Read evaluation casesRead evaluation cases through a bounded evidence-first AI operations workflow in the training lab.
Core Checkpoint 76 Evaluations and datasets Validate a dataset schemaValidate a dataset schema through a bounded evidence-first AI operations workflow in the training lab.
Core 77 Evaluations and datasets Count evaluation recordsCount evaluation records through a bounded evidence-first AI operations workflow in the training lab.
Core 78 Evaluations and datasets Run a baseline evaluationRun a baseline evaluation through a bounded evidence-first AI operations workflow in the training lab.
Core 79 Evaluations and datasets Read aggregate scoresRead aggregate scores through a bounded evidence-first AI operations workflow in the training lab.
Core 80 Evaluations and datasets Inspect failed casesInspect failed cases through a bounded evidence-first AI operations workflow in the training lab.
Core 81 Evaluations and datasets Compare evaluation runsCompare evaluation runs through a bounded evidence-first AI operations workflow in the training lab.
Core 82 Evaluations and datasets Set a release thresholdSet a release threshold through a bounded evidence-first AI operations workflow in the training lab.
Core Checkpoint 83 Evaluations and datasets Review metric tradeoffsReview metric tradeoffs through a bounded evidence-first AI operations workflow in the training lab.
Core 84 Evaluations and datasets Inspect a data sliceInspect a data slice through a bounded evidence-first AI operations workflow in the training lab.
Core 85 Evaluations and datasets Find annotation disagreementFind annotation disagreement through a bounded evidence-first AI operations workflow in the training lab.
Core 86 Evaluations and datasets Detect evaluation leakageDetect evaluation leakage through a bounded evidence-first AI operations workflow in the training lab.
Admin 87 Evaluations and datasets Review dataset provenanceReview dataset provenance through a bounded evidence-first AI operations workflow in the training lab.
Admin 88 Evaluations and datasets Build a regression reportBuild a regression report through a bounded evidence-first AI operations workflow in the training lab.
Admin 89 Evaluations and datasets Make a release recommendationMake a release recommendation through a bounded evidence-first AI operations workflow in the training lab.
Admin 90 Evaluations and datasets Archive evaluation evidenceArchive evaluation evidence through a bounded evidence-first AI operations workflow in the training lab.
Admin 91 Evaluations and datasets Evaluations checkpointEvaluations checkpoint through a bounded evidence-first AI operations workflow in the training lab.
Admin Checkpoint 92 Retrieval and embeddings Map the retrieval pipelineMap the retrieval pipeline through a bounded evidence-first AI operations workflow in the training lab.
Admin 93 Retrieval and embeddings Inspect source documentsInspect source documents through a bounded evidence-first AI operations workflow in the training lab.
Admin 94 Retrieval and embeddings Review chunk boundariesReview chunk boundaries through a bounded evidence-first AI operations workflow in the training lab.
Admin 95 Retrieval and embeddings Read embedding metadataRead embedding metadata through a bounded evidence-first AI operations workflow in the training lab.
Admin 96 Retrieval and embeddings Inspect index statusInspect index status through a bounded evidence-first AI operations workflow in the training lab.
Admin 97 Retrieval and embeddings Check index freshnessCheck index freshness through a bounded evidence-first AI operations workflow in the training lab.
Admin 98 Retrieval and embeddings Review retrieval resultsReview retrieval results through a bounded evidence-first AI operations workflow in the training lab.
Admin 99 Retrieval and embeddings Compare similarity scoresCompare similarity scores through a bounded evidence-first AI operations workflow in the training lab.
Admin Checkpoint 100 Retrieval and embeddings Spot a missing citationSpot a missing citation through a bounded evidence-first AI operations workflow in the training lab.
Admin Checkpoint 101 Retrieval and embeddings Diagnose empty retrievalDiagnose empty retrieval through a bounded evidence-first AI operations workflow in the training lab.
Admin 102 Retrieval and embeddings Inspect duplicate chunksInspect duplicate chunks through a bounded evidence-first AI operations workflow in the training lab.
Admin 103 Retrieval and embeddings Review metadata filtersReview metadata filters through a bounded evidence-first AI operations workflow in the training lab.
Admin 104 Retrieval and embeddings Compare retrieval configurationsCompare retrieval configurations through a bounded evidence-first AI operations workflow in the training lab.
Admin 105 Retrieval and embeddings Prepare an index rebuild planPrepare an index rebuild plan through a bounded evidence-first AI operations workflow in the training lab.
Admin 106 Retrieval and embeddings Build retrieval evidenceBuild retrieval evidence through a bounded evidence-first AI operations workflow in the training lab.
Admin 107 Retrieval and embeddings Retrieval checkpointRetrieval checkpoint through a bounded evidence-first AI operations workflow in the training lab.
Admin Checkpoint 108 Serving, containers, and resources Inspect the serving serviceInspect the serving service through a bounded evidence-first AI operations workflow in the training lab.
Admin 109 Serving, containers, and resources Read gateway logsRead gateway logs through a bounded evidence-first AI operations workflow in the training lab.
Admin 110 Serving, containers, and resources List training containersList training containers through a bounded evidence-first AI operations workflow in the training lab.
Admin 111 Serving, containers, and resources Inspect a containerInspect a container through a bounded evidence-first AI operations workflow in the training lab.
Admin 112 Serving, containers, and resources Read container resource useRead container resource use through a bounded evidence-first AI operations workflow in the training lab.
Admin 113 Serving, containers, and resources Validate compose configurationValidate compose configuration through a bounded evidence-first AI operations workflow in the training lab.
Admin 114 Serving, containers, and resources List Kubernetes workloadsList Kubernetes workloads through a bounded evidence-first AI operations workflow in the training lab.
Admin 115 Serving, containers, and resources Describe a serving podDescribe a serving pod through a bounded evidence-first AI operations workflow in the training lab.
Admin 116 Serving, containers, and resources Read pod logsRead pod logs through a bounded evidence-first AI operations workflow in the training lab.
Admin Checkpoint 117 Serving, containers, and resources Inspect pod resourcesInspect pod resources through a bounded evidence-first AI operations workflow in the training lab.
Admin 118 Serving, containers, and resources Review a deployment diffReview a deployment diff through a bounded evidence-first AI operations workflow in the training lab.
Admin 119 Serving, containers, and resources Inspect GPU availabilityInspect GPU availability through a bounded evidence-first AI operations workflow in the training lab.
Admin 120 Serving, containers, and resources Match model memory to GPUMatch model memory to GPU through a bounded evidence-first AI operations workflow in the training lab.
Admin 121 Serving, containers, and resources Read readiness evidenceRead readiness evidence through a bounded evidence-first AI operations workflow in the training lab.
Admin 122 Serving, containers, and resources Inspect service dependenciesInspect service dependencies through a bounded evidence-first AI operations workflow in the training lab.
Admin 123 Serving, containers, and resources Prepare a rollout reviewPrepare a rollout review through a bounded evidence-first AI operations workflow in the training lab.
Admin 124 Serving, containers, and resources Serving and resources checkpointServing and resources checkpoint through a bounded evidence-first AI operations workflow in the training lab.
Admin 125 Observability and tracing Read an observability mapRead an observability map through a bounded evidence-first AI operations workflow in the training lab.
Admin Checkpoint 126 Observability and tracing Inspect gateway metricsInspect gateway metrics through a bounded evidence-first AI operations workflow in the training lab.
Admin 127 Observability and tracing Read latency percentilesRead latency percentiles through a bounded evidence-first AI operations workflow in the training lab.
Admin 128 Observability and tracing Compare throughput signalsCompare throughput signals through a bounded evidence-first AI operations workflow in the training lab.
Admin 129 Observability and tracing Inspect error-rate evidenceInspect error-rate evidence through a bounded evidence-first AI operations workflow in the training lab.
Admin 130 Observability and tracing Follow a request traceFollow a request trace through a bounded evidence-first AI operations workflow in the training lab.
Admin 131 Observability and tracing Find a slow spanFind a slow span through a bounded evidence-first AI operations workflow in the training lab.
Admin 132 Observability and tracing Connect logs and tracesConnect logs and traces through a bounded evidence-first AI operations workflow in the training lab.
Admin Checkpoint 133 Observability and tracing Inspect token metricsInspect token metrics through a bounded evidence-first AI operations workflow in the training lab.
Admin 134 Observability and tracing Review model saturationReview model saturation through a bounded evidence-first AI operations workflow in the training lab.
Admin 135 Observability and tracing Read an SLO windowRead an SLO window through a bounded evidence-first AI operations workflow in the training lab.
Admin 136 Observability and tracing Calculate error-budget postureCalculate error-budget posture through a bounded evidence-first AI operations workflow in the training lab.
Advanced 137 Observability and tracing Build an incident timelineBuild an incident timeline through a bounded evidence-first AI operations workflow in the training lab.
Advanced 138 Observability and tracing Prepare an observability summaryPrepare an observability summary through a bounded evidence-first AI operations workflow in the training lab.
Advanced 139 Observability and tracing Observability checkpointObservability checkpoint through a bounded evidence-first AI operations workflow in the training lab.
Advanced 140 Safety, privacy, and governance Inspect guardrail policyInspect guardrail policy through a bounded evidence-first AI operations workflow in the training lab.
Advanced 141 Safety, privacy, and governance Review input redactionReview input redaction through a bounded evidence-first AI operations workflow in the training lab.
Advanced 142 Safety, privacy, and governance Review output redactionReview output redaction through a bounded evidence-first AI operations workflow in the training lab.
Advanced 143 Safety, privacy, and governance Locate sensitive fieldsLocate sensitive fields through a bounded evidence-first AI operations workflow in the training lab.
Advanced 144 Safety, privacy, and governance Check data retentionCheck data retention through a bounded evidence-first AI operations workflow in the training lab.
Advanced 145 Safety, privacy, and governance Inspect access boundariesInspect access boundaries through a bounded evidence-first AI operations workflow in the training lab.
Advanced 146 Safety, privacy, and governance Read a model cardRead a model card through a bounded evidence-first AI operations workflow in the training lab.
Advanced 147 Safety, privacy, and governance Review approved useReview approved use through a bounded evidence-first AI operations workflow in the training lab.
Advanced Checkpoint 148 Safety, privacy, and governance Inspect refusal evidenceInspect refusal evidence through a bounded evidence-first AI operations workflow in the training lab.
Advanced 149 Safety, privacy, and governance Review human escalationReview human escalation through a bounded evidence-first AI operations workflow in the training lab.
Advanced 150 Safety, privacy, and governance Check audit metadataCheck audit metadata through a bounded evidence-first AI operations workflow in the training lab.
Advanced Checkpoint 151 Safety, privacy, and governance Separate safety and qualitySeparate safety and quality through a bounded evidence-first AI operations workflow in the training lab.
Advanced 152 Safety, privacy, and governance Prepare a governance reviewPrepare a governance review through a bounded evidence-first AI operations workflow in the training lab.
Advanced 153 Safety, privacy, and governance Write a risk summaryWrite a risk summary through a bounded evidence-first AI operations workflow in the training lab.
Advanced 154 Safety, privacy, and governance Safety and governance checkpointSafety and governance checkpoint through a bounded evidence-first AI operations workflow in the training lab.
Advanced 155 Cost, capacity, and reliability Read token cost inputsRead token cost inputs through a bounded evidence-first AI operations workflow in the training lab.
Advanced 156 Cost, capacity, and reliability Estimate request costEstimate request cost through a bounded evidence-first AI operations workflow in the training lab.
Advanced 157 Cost, capacity, and reliability Compare model cost profilesCompare model cost profiles through a bounded evidence-first AI operations workflow in the training lab.
Advanced 158 Cost, capacity, and reliability Inspect cache effectivenessInspect cache effectiveness through a bounded evidence-first AI operations workflow in the training lab.
Advanced 159 Cost, capacity, and reliability Read concurrency limitsRead concurrency limits through a bounded evidence-first AI operations workflow in the training lab.
Advanced 160 Cost, capacity, and reliability Estimate capacity headroomEstimate capacity headroom through a bounded evidence-first AI operations workflow in the training lab.
Advanced 161 Cost, capacity, and reliability Inspect queue depthInspect queue depth through a bounded evidence-first AI operations workflow in the training lab.
Advanced Checkpoint 162 Cost, capacity, and reliability Compare latency and costCompare latency and cost through a bounded evidence-first AI operations workflow in the training lab.
Advanced 163 Cost, capacity, and reliability Review fallback routingReview fallback routing through a bounded evidence-first AI operations workflow in the training lab.
Advanced 164 Cost, capacity, and reliability Plan graceful degradationPlan graceful degradation through a bounded evidence-first AI operations workflow in the training lab.
Advanced 165 Cost, capacity, and reliability Read reliability targetsRead reliability targets through a bounded evidence-first AI operations workflow in the training lab.
Advanced 166 Cost, capacity, and reliability Prepare a capacity notePrepare a capacity note through a bounded evidence-first AI operations workflow in the training lab.
Advanced 167 Cost, capacity, and reliability Review cost anomaliesReview cost anomalies through a bounded evidence-first AI operations workflow in the training lab.
Advanced 168 Cost, capacity, and reliability Cost and reliability checkpointCost and reliability checkpoint through a bounded evidence-first AI operations workflow in the training lab.
Advanced Checkpoint 169 Incident response and capstones Triage elevated latencyTriage elevated latency through a bounded evidence-first AI operations workflow in the training lab.
Capstone 170 Incident response and capstones Investigate inference errorsInvestigate inference errors through a bounded evidence-first AI operations workflow in the training lab.
Capstone 171 Incident response and capstones Diagnose retrieval regressionDiagnose retrieval regression through a bounded evidence-first AI operations workflow in the training lab.
Capstone 172 Incident response and capstones Review a prompt rollout incidentReview a prompt rollout incident through a bounded evidence-first AI operations workflow in the training lab.
Capstone 173 Incident response and capstones Investigate GPU pressureInvestigate GPU pressure through a bounded evidence-first AI operations workflow in the training lab.
Capstone 174 Incident response and capstones Trace a cost spikeTrace a cost spike through a bounded evidence-first AI operations workflow in the training lab.
Capstone Checkpoint 175 Incident response and capstones Review a guardrail regressionReview a guardrail regression through a bounded evidence-first AI operations workflow in the training lab.
Capstone Checkpoint 176 Incident response and capstones Handle a stale indexHandle a stale index through a bounded evidence-first AI operations workflow in the training lab.
Capstone 177 Incident response and capstones Prepare a model rollbackPrepare a model rollback through a bounded evidence-first AI operations workflow in the training lab.
Capstone 178 Incident response and capstones Build a complete evidence bundleBuild a complete evidence bundle through a bounded evidence-first AI operations workflow in the training lab.
Capstone 179 Incident response and capstones Write an incident reviewWrite an incident review through a bounded evidence-first AI operations workflow in the training lab.
Capstone 180 Incident response and capstones AI operations final capstoneAI operations final capstone through a bounded evidence-first AI operations workflow in the training lab.
Capstone Checkpoint