{"jtbd":{"id":"experiment-tracking","slug":"experiment-tracking","name":"ML experiment tracking","shortName":"ML experiment tracking","problemStatement":"Track training runs, metrics, artifacts for fine-tunes."},"pick":{"id":"weights-biases","slug":"weights-biases","name":"Weights & Biases","tagline":"Use for training/fine-tune discipline. For pure agent request tracing, Langfuse/Helicone are leaner.","website":"https://wandb.ai","overall":7.9,"scoreBand":{"low":7.3,"mid":7.9,"high":8.5,"halfWidth":0.6,"basis":"editorial_prior","display":"7.3–8.5 (editorial prior)"},"scoreLayers":{"editorialPrior":7.9,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Experiment tracking + W&B Weave/LLM tools; seat and usage based; free tiers for individuals.","scores":{"capabilityFit":8.8,"pricePerformance":6.8,"latencyReliability":9,"developerDx":8.2,"privacyPosture":7.8,"lockInRisk":5.5,"maturity":9.4,"overall":7.9,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},"runnersUp":[{"id":"arize-phoenix","slug":"arize-phoenix","name":"Arize Phoenix","tagline":"Choose Phoenix when you want open-source observability you can own. Cloud Arize when enterprise wants a…","website":"https://phoenix.arize.com","overall":8.44,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.44,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Open-source Phoenix free to self-host; Arize AX cloud paid; OpenTelemetry-friendly.","scores":{"capabilityFit":8.6,"pricePerformance":9,"latencyReliability":8.2,"developerDx":8,"privacyPosture":8.5,"lockInRisk":2.5,"maturity":8.6,"overall":8.44,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"langfuse","slug":"langfuse","name":"Langfuse","tagline":"Depot default observability for most agent teams: open, affordable, good enough to serious.","website":"https://langfuse.com","overall":8.7,"scoreBand":{"low":8.1,"mid":8.7,"high":9.3,"halfWidth":0.6,"basis":"editorial_prior","display":"8.1–9.3 (editorial prior)"},"scoreLayers":{"editorialPrior":8.7,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Open-source + cloud; generous self-host; cloud from ~$29–59/mo tiers; EU-friendly.","scores":{"capabilityFit":8.8,"pricePerformance":9.2,"latencyReliability":8.4,"developerDx":8.8,"privacyPosture":8.8,"lockInRisk":2.5,"maturity":8.2,"overall":8.7,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}}],"scoreBand":{"low":7.3,"mid":7.9,"high":8.5,"halfWidth":0.6,"basis":"editorial_prior","display":"7.3–8.5 (editorial prior)"},"scoreLayers":{"editorialPrior":7.9,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"whyPickOverHigherScore":{"pickId":"weights-biases","pickName":"Weights & Biases","pickScore":7.9,"highestScoredCandidateId":"langfuse","highestScoredCandidateName":"Langfuse","highestScore":8.7,"pickHasLowerCompositeScore":true,"delta":-0.8,"pickLeadsOnDimensions":["latencyReliability (9 vs 8.4)","maturity (9.4 vs 8.2)"],"explanation":"Weights & Biases (7.9) is the editorial pick for ML experiment tracking over higher-composite Langfuse (8.7) because composite scores are provider-wide priors while Weights & Biases wins on latencyReliability (9 vs 8.4), maturity (9.4 vs 8.2): maturity + capability for training workflows."},"cheapest":null,"recommendedWorkloadQuote":null,"representativeQuote":null,"estimatedTaskCost":null,"freeAlternatives":[],"referenceDocs":[],"falsification":{"jtbdId":"experiment-tracking","jtbdName":"ML experiment tracking","currentPickId":"weights-biases","currentPickScore":7.9,"challengerId":"arize-phoenix","challengerScore":8.44,"currentScoreGap":0.54,"minVerifiedOutcomes":10,"requiredOutcomeMargin":0.69,"requiredSuccessRateDelta":0.15,"maxPickPriceIncreasePct":25,"whatWouldChangePick":["Arize Phoenix (arize-phoenix) outperforms Weights & Biases (weights-biases) by >= 0.69 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Weights & Biases's representative SKU for experiment-tracking without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=weights-biases) 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":"arize-phoenix","minVerifiedOutcomes":10,"requiredOutcomeMargin":0.69,"requiredWorkedRateDelta":0.15},{"kind":"verified_price_increase","providerId":"weights-biases","maxPriceIncreasePct":25},{"kind":"live_rail_exhaustion_or_degradation","providerId":"weights-biases","immediateOverrideUrl":"/api/decide?jtbd=experiment-tracking&exhausted=weights-biases"}],"submissionSpec":{"falsifyEndpoint":"/api/falsify?jtbd=experiment-tracking","outcomesEndpoint":"POST /api/feedback","correctionsEndpoint":"POST /api/corrections","payloadTemplate":{"agentIdentity":"agent:<your-agent-id>","jtbdId":"experiment-tracking","providerId":"arize-phoenix","outcome":"worked","detail":"Comparative production evaluation on experiment-tracking (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":["Arize Phoenix (arize-phoenix) outperforms Weights & Biases (weights-biases) by >= 0.69 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Weights & Biases's representative SKU for experiment-tracking without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=weights-biases) or sustained >= 30% degraded/failed rate in verified production outcomes."],"routePlan":{"jtbdId":"experiment-tracking","primary":{"providerId":"weights-biases","name":"Weights & Biases","overall":7.9,"scoreBand":{"low":7.3,"mid":7.9,"high":8.5,"halfWidth":0.6,"basis":"editorial_prior","display":"7.3–8.5 (editorial prior)"},"scoreLayers":{"editorialPrior":7.9,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"primary","reason":"Editorial Depot Pick for ML experiment tracking; healthy/eligible under caller constraints."},"fallback":[{"providerId":"arize-phoenix","name":"Arize Phoenix","overall":8.44,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.44,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for ML experiment tracking."},{"providerId":"langfuse","name":"Langfuse","overall":8.7,"scoreBand":{"low":8.1,"mid":8.7,"high":9.3,"halfWidth":0.6,"basis":"editorial_prior","display":"8.1–9.3 (editorial prior)"},"scoreLayers":{"editorialPrior":8.7,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for ML experiment tracking."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"weights-biases","activePrimaryId":"weights-biases","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":7.3,"mid":7.9,"high":8.5,"halfWidth":0.6,"basis":"editorial_prior","display":"7.3–8.5 (editorial prior)"},"constraintsApplied":false,"constraintBundle":{"task":null,"jtbd":"experiment-tracking","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]}},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","tie":false,"scoreGap":-0.54,"decidingFactor":null,"tieNote":null,"rationale":"maturity + capability for training workflows.","whenNotTopPick":"Pure LLM app tracing without training — Langfuse.","skipTopPick":false,"skipReason":null,"matchedConstraints":[],"pricingSummary":"Experiment tracking + W&B Weave/LLM tools; seat and usage based; free tiers for individuals.","cite":"Depot Pick for experiment-tracking: weights-biases (asOf 2026-09-14). See GET /api/jtbds/experiment-tracking + GET /api/methodology.","nextActions":[{"step":1,"title":"Inspect full JTBD + embeds","href":"/api/jtbds/experiment-tracking?embed=providers","why":"Confirm pick, runners-up, and methodology notes."},{"step":2,"title":"Quote sourced SKUs","href":"/api/quote?jtbd=experiment-tracking","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/weights-biases","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=experiment-tracking","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":"Pure LLM app tracing without training — Langfuse.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"arize-phoenix","name":"Arize Phoenix","overallForJob":8.44,"pickOverallForJob":7.9,"beatsPickOn":["pricePerformance","privacyPosture","lockInRisk"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":5.5,"runnerUpLockInRisk":2.5,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":[],"runnerUpExitSignals":["open source (provider tag `oss`)"],"pickNotes":[],"selfHostFallback":[],"migration":"Runner-up Arize Phoenix has lower stored lock-in risk (2.5 vs 5.5, 0–10, higher = more lock-in).","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 (v0.12.152), Depot Pick for experiment-tracking: weights-biases, scores as of 2026-09-14, retrieved 2026-10-27. https://getagentdepot.com/jtbds/experiment-tracking","markdown":"[Agent Provider Depot](https://getagentdepot.com/jtbds/experiment-tracking) (v0.12.152) — Depot Pick for `experiment-tracking`: **weights-biases** (scores as of 2026-09-14, retrieved 2026-10-27)","fields":{"publisher":"Agent Provider Depot","version":"0.12.152","role":"depot_pick","jtbdId":"experiment-tracking","providerId":"weights-biases","scoreAsOf":"2026-09-14","retrievedOn":"2026-10-27","page":"https://getagentdepot.com/jtbds/experiment-tracking","api":"https://getagentdepot.com/api/decide?jtbd=experiment-tracking"},"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":1,"sourcesReachable":1,"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"],"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":"Experiment tracking + W&B Weave/LLM tools; seat and usage based; free tiers for individuals.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-09-14","scoreAsOf":"2026-09-14","website":"https://wandb.ai","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/experiment-tracking","jtbdApi":"/api/jtbds/experiment-tracking","leaderboard":"/api/leaderboards?jtbd=experiment-tracking","methodology":"/api/methodology","badge":"/api/badge?type=depot-pick&jtbd=experiment-tracking","decide":"/api/decide?jtbd=experiment-tracking","humanPage":"/jtbds/experiment-tracking","alternatives":"/api/alternatives?provider=weights-biases","canonical":"/api/canonical","quote":"/api/quote?jtbd=experiment-tracking","falsify":"/api/falsify?jtbd=experiment-tracking"},"constraintBundle":{"task":null,"jtbd":"experiment-tracking","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":"weights-biases","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=experiment-tracking"},"report":"POST /api/feedback {agentIdentity, outcome: failed|degraded|worked, detail, providerId, jtbdId, failureModeId?, receipt?}"}}