{"jtbd":{"id":"lakehouse-llm","slug":"lakehouse-llm","name":"LLM on existing lakehouse data","shortName":"LLM on existing lakehouse data","problemStatement":"Data already lives in Databricks or Snowflake; want governed inference/RAG without exporting corpora."},"pick":{"id":"databricks-mosaic","slug":"databricks-mosaic","name":"Databricks Mosaic AI","tagline":"Pick only when your data/platform already is Databricks. Otherwise Bedrock/Vertex or direct APIs.","website":"https://www.databricks.com/product/machine-learning","overall":7.11,"scoreBand":{"low":6.5,"mid":7.1,"high":7.7,"halfWidth":0.6,"basis":"editorial_prior","display":"6.5–7.7 (editorial prior)"},"scoreLayers":{"editorialPrior":7.11,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14: Lakehouse-native model training/serving billed via Databricks DBUs + cloud compute. Foundation Model Serving and Mosaic tooling sit inside Databricks contracts — not indie per-token pricing. Strong if data already lives in Databricks.","scores":{"capabilityFit":8.4,"pricePerformance":4.8,"latencyReliability":8.5,"developerDx":6.8,"privacyPosture":8.2,"lockInRisk":7.8,"maturity":8.8,"overall":7.11,"kind":"curated_estimate","confidence":"medium","asOf":"2026-09-14"}},"runnersUp":[{"id":"snowflake-cortex","slug":"snowflake-cortex","name":"Snowflake Cortex","tagline":"Use when Snowflake already holds the data. Don't drag agent backends into Snowflake just for Cortex.","website":"https://www.snowflake.com/en/data-cloud/cortex/","overall":7.1,"scoreBand":{"low":6.5,"mid":7.1,"high":7.7,"halfWidth":0.6,"basis":"editorial_prior","display":"6.5–7.7 (editorial prior)"},"scoreLayers":{"editorialPrior":7.1,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14: SQL-first AI functions (COMPLETE, EMBED, SEARCH, etc.) priced in Snowflake AI credits (secondary sources cite ~$2.00 per AI credit — confirm account rate card). Attractive when data already in Snowflake; not a general agent LLM default.","scores":{"capabilityFit":7.8,"pricePerformance":5.5,"latencyReliability":8.4,"developerDx":7,"privacyPosture":8.5,"lockInRisk":8,"maturity":8.6,"overall":7.1,"kind":"curated_estimate","confidence":"medium","asOf":"2026-09-14"}},{"id":"amazon-bedrock","slug":"amazon-bedrock","name":"Amazon Bedrock","tagline":"Enterprise multi-model switchboard. Great when AWS is mandatory; mediocre when you just want the best Claude…","website":"https://aws.amazon.com/bedrock/","overall":7.75,"scoreBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"scoreLayers":{"editorialPrior":7.75,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Pay-per-token for Claude, Llama, Amazon, Cohere, etc.; Provisioned Throughput for steady load. AWS marketplace billing.","scores":{"capabilityFit":8.8,"pricePerformance":6,"latencyReliability":9.2,"developerDx":6.8,"privacyPosture":9,"lockInRisk":7,"maturity":9.6,"overall":7.75,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"vertex-ai","slug":"vertex-ai","name":"Google Vertex AI","tagline":"Enterprise Gemini path. Use AI Studio for prototypes, Vertex when security review starts asking questions.","website":"https://cloud.google.com/vertex-ai","overall":7.96,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":7.96,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14: Google Cloud Vertex AI model garden + Gemini; billed in GCP currency with enterprise controls, VPC-SC, and committed use discounts. Prefer Google AI Studio/API for indie DX; Vertex for enterprise residency/IAM.","scores":{"capabilityFit":9,"pricePerformance":7,"latencyReliability":9,"developerDx":7.2,"privacyPosture":8.8,"lockInRisk":7.5,"maturity":9.6,"overall":7.96,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}}],"scoreBand":{"low":6.5,"mid":7.1,"high":7.7,"halfWidth":0.6,"basis":"editorial_prior","display":"6.5–7.7 (editorial prior)"},"scoreLayers":{"editorialPrior":7.11,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"whyPickOverHigherScore":{"pickId":"databricks-mosaic","pickName":"Databricks Mosaic AI","pickScore":7.11,"highestScoredCandidateId":"vertex-ai","highestScoredCandidateName":"Google Vertex AI","highestScore":7.96,"pickHasLowerCompositeScore":true,"delta":-0.85,"pickLeadsOnDimensions":[],"explanation":"Databricks Mosaic AI (7.11) is the editorial pick for LLM on existing lakehouse data over higher-composite Google Vertex AI (7.96) because composite scores are provider-wide priors while Databricks Mosaic AI wins on job-specific execution fit: Data gravity + privacy/governance beat raw DX."},"cheapest":{"providerId":"amazon-bedrock","providerName":"Amazon Bedrock","skuId":"amazon-bedrock-gemma-3-4b-in","item":"Gemma 3 4B","plan":"Gemma 3 4B — Standard on-demand","unit":"usd_per_million_input_tokens","amountUsd":0.04,"isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuCountInUnit":26,"isDepotPick":false,"sourceUrl":"https://aws.amazon.com/bedrock/pricing/","asOf":"2026-10-03","verifiedAsOf":"2026-10-27"},"recommendedWorkloadQuote":null,"representativeQuote":null,"estimatedTaskCost":null,"freeAlternatives":[],"referenceDocs":[],"falsification":{"jtbdId":"lakehouse-llm","jtbdName":"LLM on existing lakehouse data","currentPickId":"databricks-mosaic","currentPickScore":7.11,"challengerId":"snowflake-cortex","challengerScore":7.1,"currentScoreGap":0.01,"minVerifiedOutcomes":10,"requiredOutcomeMargin":0.16,"requiredSuccessRateDelta":0.15,"maxPickPriceIncreasePct":25,"whatWouldChangePick":["Snowflake Cortex (snowflake-cortex) outperforms Databricks Mosaic AI (databricks-mosaic) by >= 0.16 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Databricks Mosaic AI's representative SKU for lakehouse-llm without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=databricks-mosaic) or sustained >= 30% degraded/failed rate in verified production outcomes."],"frozenHoldoutPolicy":{"holdoutSplit":"20% frozen benchmark holdout tasks + 80% live production outcome receipts","requireCountersignReceipt":true,"requiredEvidenceTiers":["outcome_verified","reference_checked"],"minDistinctContributors":2,"antiGamingRule":"Unverified self-reports and seed/editorial rows never mutate picks or scores."},"triggers":[{"kind":"verified_outcomes_outperformance","challengerId":"snowflake-cortex","minVerifiedOutcomes":10,"requiredOutcomeMargin":0.16,"requiredWorkedRateDelta":0.15},{"kind":"verified_price_increase","providerId":"databricks-mosaic","maxPriceIncreasePct":25},{"kind":"live_rail_exhaustion_or_degradation","providerId":"databricks-mosaic","immediateOverrideUrl":"/api/decide?jtbd=lakehouse-llm&exhausted=databricks-mosaic"}],"submissionSpec":{"falsifyEndpoint":"/api/falsify?jtbd=lakehouse-llm","outcomesEndpoint":"POST /api/feedback","correctionsEndpoint":"POST /api/corrections","payloadTemplate":{"agentIdentity":"agent:<your-agent-id>","jtbdId":"lakehouse-llm","providerId":"snowflake-cortex","outcome":"worked","detail":"Comparative production evaluation on lakehouse-llm (n>=10 tasks) with Countersign receipt.","confidence":"high","receipt":{"countersign":{"claim_id":"cs-00000000","status":"verified","evidence_tier":"outcome_verified","counts_as_verified":true}}}}},"whatWouldChangePick":["Snowflake Cortex (snowflake-cortex) outperforms Databricks Mosaic AI (databricks-mosaic) by >= 0.16 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Databricks Mosaic AI's representative SKU for lakehouse-llm without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=databricks-mosaic) or sustained >= 30% degraded/failed rate in verified production outcomes."],"routePlan":{"jtbdId":"lakehouse-llm","primary":{"providerId":"databricks-mosaic","name":"Databricks Mosaic AI","overall":7.11,"scoreBand":{"low":6.5,"mid":7.1,"high":7.7,"halfWidth":0.6,"basis":"editorial_prior","display":"6.5–7.7 (editorial prior)"},"scoreLayers":{"editorialPrior":7.11,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"primary","reason":"Editorial Depot Pick for LLM on existing lakehouse data; healthy/eligible under caller constraints."},"fallback":[{"providerId":"snowflake-cortex","name":"Snowflake Cortex","overall":7.1,"scoreBand":{"low":6.5,"mid":7.1,"high":7.7,"halfWidth":0.6,"basis":"editorial_prior","display":"6.5–7.7 (editorial prior)"},"scoreLayers":{"editorialPrior":7.1,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for LLM on existing lakehouse data."},{"providerId":"amazon-bedrock","name":"Amazon Bedrock","overall":7.75,"scoreBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"scoreLayers":{"editorialPrior":7.75,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for LLM on existing lakehouse data."},{"providerId":"vertex-ai","name":"Google Vertex AI","overall":7.96,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":7.96,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for LLM on existing lakehouse data."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"databricks-mosaic","activePrimaryId":"databricks-mosaic","summary":"0.00 score regret: unconstrained editorial pick satisfies all caller constraints."},"evidenceAgeDays":{"editorialScoreAgeDays":43,"pricingVerifiedAgeDays":0,"editorialPriorAsOf":"2026-09-14","pricingLastVerifiedAt":"2026-10-27"},"confidenceBand":{"low":6.5,"mid":7.1,"high":7.7,"halfWidth":0.6,"basis":"editorial_prior","display":"6.5–7.7 (editorial prior)"},"constraintsApplied":false,"constraintBundle":{"task":null,"jtbd":"lakehouse-llm","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]}},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","tie":true,"scoreGap":0.01,"decidingFactor":"capabilityFit (8.4 vs 7.8)","tieNote":"Scores are within 0.10 on a curated_estimate 0-10 scale (7.11 vs 7.1); treat as a statistical tie and decide on decidingFactor or whenNotTopPick.","rationale":"Data gravity + privacy/governance beat raw DX.","whenNotTopPick":"Greenfield agent with no lakehouse — use direct APIs + pgvector/Qdrant.","skipTopPick":false,"skipReason":null,"matchedConstraints":[],"pricingSummary":"As of 2026-09-14: Lakehouse-native model training/serving billed via Databricks DBUs + cloud compute. Foundation Model Serving and Mosaic tooling sit inside Databricks contracts — not indie per-token pricing. Strong if data already lives in Databricks.","cite":"Depot Pick for lakehouse-llm: databricks-mosaic (asOf 2026-09-14). See GET /api/jtbds/lakehouse-llm + GET /api/methodology.","nextActions":[{"step":1,"title":"Inspect full JTBD + embeds","href":"/api/jtbds/lakehouse-llm?embed=providers","why":"Confirm pick, runners-up, and methodology notes."},{"step":2,"title":"Quote sourced SKUs","href":"/api/quote?jtbd=lakehouse-llm","why":"Depot Pick SKUs plus the cheapest sourced SKU whose unit matches this job. Does not change the pick. Does not blend input and output or borrow a chat rate for a non-chat job."},{"step":3,"title":"Open provider detail","href":"/api/providers/databricks-mosaic","why":"Scores, pricingNotes, strengths/weaknesses, communitySignals (claims only)."},{"step":4,"title":"Cite methodology","href":"/api/methodology","why":"Required when publishing a Depot Pick citation."},{"step":5,"title":"Grab badge SVG","href":"/api/badge?type=depot-pick&jtbd=lakehouse-llm","why":"Embed in README / agent passport."},{"step":6,"title":"Post production insight","method":"POST","href":"/api/insights","why":"Unverified until curated; never auto-mutates official scores."}],"honesty":["Do not invent scores or benches.","Insights are claims until curated/reviewed; they never silently mutate official scores.","lockInRisk higher = more lock-in (worse).","normalizedUsdPerMillionTokens is set only for a single sourced token row. Otherwise null, with a machine-readable reason. Do not coerce GPU, minute, or per-1k search units.","Runners-up are not Depot Picks.","Depot overall is editorial_weighted, not Arena Elo and not an Artificial Analysis index."],"asOf":"2026-09-14","depth":{"whenNotToUse":{"text":"Greenfield agent with no lakehouse — use direct APIs + pgvector/Qdrant.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"snowflake-cortex","name":"Snowflake Cortex","overallForJob":7.1,"pickOverallForJob":7.11,"beatsPickOn":["pricePerformance","developerDx","privacyPosture"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":7.8,"runnerUpLockInRisk":8,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":[],"runnerUpExitSignals":[],"pickNotes":[{"text":"Lock-in to Databricks","field":"weaknesses"}],"selfHostFallback":[],"migration":"The pick has lower stored lock-in risk than runner-up Snowflake Cortex (7.8 vs 8).","migrationReason":null,"derivedFrom":"stored lockInRisk scores, provider tags (oss, self-host, openai-compat, open-models), free rows that list this job, and verbatim provider notes. No migration guide was invented."}},"citation":{"text":"Agent Provider Depot (v0.12.151), Depot Pick for lakehouse-llm: databricks-mosaic, scores as of 2026-09-14, retrieved 2026-10-27. https://getagentdepot.com/jtbds/lakehouse-llm","markdown":"[Agent Provider Depot](https://getagentdepot.com/jtbds/lakehouse-llm) (v0.12.151) — Depot Pick for `lakehouse-llm`: **databricks-mosaic** (scores as of 2026-09-14, retrieved 2026-10-27)","fields":{"publisher":"Agent Provider Depot","version":"0.12.151","role":"depot_pick","jtbdId":"lakehouse-llm","providerId":"databricks-mosaic","scoreAsOf":"2026-09-14","retrievedOn":"2026-10-27","page":"https://getagentdepot.com/jtbds/lakehouse-llm","api":"https://getagentdepot.com/api/decide?jtbd=lakehouse-llm"},"howToCite":"Cite Depot as an editorial, dated recommendation, not a benchmark: name the job, the Depot Pick (or runner-up), the score asOf date and the day you retrieved it, and link the job page. Format: “Agent Provider Depot (v{version}), Depot Pick for {jobId}: {providerId}, scores as of {scoreAsOf}, retrieved {retrievedOn}. {baseUrl}/jtbds/{jobId}”. Quote prices only with their own sourceUrl and asOf. If the pick's score is stale (freshness.pick.score.stale), say so."},"freshness":{"pick":{"score":{"asOf":"2026-09-14","ageDays":43,"stale":true,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-09-14","ageDays":43,"stale":true,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-27","sourceUrls":3,"sourcesReachable":3,"pricingRows":0,"pricingRowsReconfirmed":0,"note":"A source re-check confirms the page is reachable and, for pricing rows, that the stored amount and SKU name appear on it. It does not re-derive or change the score.","reason":null}},"scoreAsOf":"2026-09-14","editorialPriorAsOf":"2026-09-14","pricingLastVerifiedAt":"2026-10-27","pickLastReviewed":"2026-09-14","runnersUpScoreAsOf":["2026-09-14","2026-09-14","2026-09-14"],"contractAsOf":"2026-10-03","pricingShape":"prose_notes_only","normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price"},"pricingContract":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-09-14: Lakehouse-native model training/serving billed via Databricks DBUs + cloud compute. Foundation Model Serving and Mosaic tooling sit inside Databricks contracts — not indie per-token pricing. Strong if data already lives in Databricks.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://www.databricks.com/product/machine-learning","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"links":{"jtbd":"/jtbds/lakehouse-llm","jtbdApi":"/api/jtbds/lakehouse-llm","leaderboard":"/api/leaderboards?jtbd=lakehouse-llm","methodology":"/api/methodology","badge":"/api/badge?type=depot-pick&jtbd=lakehouse-llm","decide":"/api/decide?jtbd=lakehouse-llm","humanPage":"/jtbds/lakehouse-llm","alternatives":"/api/alternatives?provider=databricks-mosaic","canonical":"/api/canonical","quote":"/api/quote?jtbd=lakehouse-llm","falsify":"/api/falsify?jtbd=lakehouse-llm"},"constraintBundle":{"task":null,"jtbd":"lakehouse-llm","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]},"stackContext":{"host":null,"framework":null,"repo":null,"lang":null,"existing":[],"volume":null,"sender":null,"detectedFromTask":[]},"keep":null,"contextAdvice":null,"communityFeedback":{"pickOnThisJob":{"failed":0,"degraded":0,"worked":0,"insights":0,"withVerifiedReceipt":0,"failureModes":{},"latestAt":null,"note":"Agent-reported claims (unverified unless a receipt is verified by Depot's re-check). They never change scores or picks."},"outcomes":{"job":{"n":0,"worked":0,"degraded":0,"failed":0,"failureModes":{},"verifiedReports":0,"contributors":0,"excluded":{"seed_editorial":0,"test":0,"notFeedback":0},"reason":"no_submitted_outcome_reports_yet"},"pick":{"providerId":"databricks-mosaic","n":0,"worked":0,"degraded":0,"failed":0,"failureModes":{},"evidenceTiers":{"agent_claim":0,"self_declared":0,"reference_checked":0,"outcome_verified":0},"reason":"no_submitted_outcome_reports_yet"},"scoresMutated":false,"more":"/api/outcomes?jtbd=lakehouse-llm"},"report":"POST /api/feedback {agentIdentity, outcome: failed|degraded|worked, detail, providerId, jtbdId, failureModeId?, receipt?}"}}