{ "format": "bayeto-decision-record", "formatVersion": 3, "formatNote": "v3 adds decisionHash. Additive: v2 records remain valid and re-derivable — no v2 field changed meaning, moved, or was removed.", "record": { "action": "Route Meeting Summaries's gpt-4-turbo traffic to claude-sonnet", "applicationId": "meeting-summaries", "beforeAfter": { "addedEdges": [], "addedNodes": [], "after": "Meeting Summaries: Route Meeting Summaries's gpt-4-turbo traffic to claude-sonnet", "before": "Meeting Summaries: all traffic on the current premium model", "changedEdges": [ "model:openai/gpt-4-turbo" ] }, "benchmark": null, "businessValueEur": 40939.72, "complexity": "Low", "confidence": 0.7217, "contextCompleteness": { "absent": [ "Codebase", "Quality evaluation" ], "present": [ "Telemetry", "Provider bill", "Per-app criticality", "Prior experiments" ], "presentCount": 4, "totalDims": 6 }, "costModelBasis": { "agentRunAllowanceEur": 20, "byHand": { "effortCostEur": 1600, "effortDays": 2, "engineeringDayRateEur": 800 }, "effortCostEur": 220, "rateBasis": "prior", "reviewHourRateEur": 100, "reviewHours": 2, "reviewHoursBasis": "prior", "version": "agent-assisted-v1-2026-08" }, "criticalReview": { "alternativeExplanations": [ "The app may have been deliberately exempted from the rollout (a known dependency on the prior family) — confirm with the owning team." ], "assumptions": [ "Assumes Meeting Summaries's workload is comparable to the 6 migrated siblings — the evidence is on siblings, not this app." ], "failureConditions": [ "Wrong if intentionally exempted; wrong if its prompt mix differs materially from the migrated fleet.", "Wrong if this workload's real quality bar is higher than assumed and the change degrades answers." ], "missingEvidence": [ "No per-app quality evaluation on this surface; sibling history is the (strong) proxy.", "No independent quality evaluation — the quality impact is unmeasured." ] }, "demoted": null, "effort": "Low", "evidenceIds": [ "ev:meeting-summaries:migration_laggard" ], "expectedImpact": { "annualSavingsEur": 40939.72, "costDeltaPct": -0.7852, "latencyDeltaPct": 0, "qualityDeltaPct": null, "qualityRisk": "low" }, "id": "rec:meeting-summaries:migration_laggard", "inferenceId": "inf:meeting-summaries:migration_laggard", "latencyValueEur": 0, "memoryNote": "No prior implementations yet — confidence derived from evidence only.", "objectiveKey": "lowest_cost", "observationIds": [ "obs:tenant:measured_win:model_switch", "obs:meeting-summaries:monthly_spend_usd" ], "pareto": true, "paybackDays": 2, "priceBasis": "scenario", "priorityScore": 41146.03, "qualityOfEvidence": "High", "roi": { "affectedRequestsMonthly": 30000, "annualSavingsEur": 40939.72, "effortDays": 2, "monthlySavingsEur": 3411.64, "paybackDays": 2, "verified": false }, "ruleId": "migration_laggard", "sampleSize": 276000, "targetNodeId": "model:openai/gpt-4-turbo", "title": "Finish the gpt-4-turbo → claude-sonnet migration: Meeting Summaries missed the rollout", "whyNot": [ { "costDeltaPct": -0.5, "latencyDeltaPct": 0, "option": "Drop two tiers instead", "paretoOptimal": false, "qualityDeltaPct": null, "qualityRisk": "medium", "reason": "A deeper cut, but NOT what was validated — the measured evidence covers gpt-4-turbo → claude-sonnet, nothing further." }, { "costDeltaPct": 0, "latencyDeltaPct": 0, "option": "Keep gpt-4-turbo here", "paretoOptimal": false, "qualityDeltaPct": 0, "qualityRisk": "none", "reason": "Forgoes a saving your own fleet already validated. Only right if this app was deliberately exempted from the rollout — confirm with the owning team." }, { "costDeltaPct": -0.3926, "latencyDeltaPct": 0, "option": "Migrate per-request instead of the whole segment", "paretoOptimal": false, "qualityDeltaPct": null, "qualityRisk": "low", "reason": "A partial switch splits the per-model prompt cache — every call re-writes the prefix instead of reading it. Whole-segment is the clean move (and what the siblings did)." } ] }, "decisionHash": "sha256:7e1794d4f496ec5374cf4de6bcfb80d013001bb3c613138d5fa75205a29d4e96", "narrative": { "note": "Phrased by the AI Fabric from deterministic drafts. Not part of the decision; changing it cannot change any number above. `provenance` records which provider source control approved, whether it served, and why not — source:\"draft\" means you are reading the engine's own deterministic wording.", "business": "You already made this exact move fleet-wide and Bayeto measured it since 2026-06-06 (24 days of post-switch data, medium confidence). Meeting Summaries still runs 100% of its spend on gpt-4-turbo. Completing the migration you already validated captures ≈ €40,940/yr — the quality risk is bounded by your own post-switch history, not an assumption. Estimated €40,940/yr at the current run-rate, payback 2 days, confidence 72%.", "technical": "Switch the whole segment at once (per-model caches — a partial switch thrashes the prefix cache). Reuse the acceptance signals from the migrated siblings; the rollback path is already known from the fleet migration. Affects ~30,000 req/mo; expected cost -78.5%, latency +0%, quality unmeasured (low risk).", "phrasedBy": "mock", "provenance": { "narrativeProvenanceVersion": 1, "attempted": "mock", "policyVersion": "fabric-v1-2026-08", "source": "provider", "degraded": false } }, "ledgerState": "lead", "ledgerVersion": "22c35e346df765c3", "overlapGroup": { "applicationId": "meeting-summaries", "memberIds": [ "rec:meeting-summaries:migration_laggard", "rec:meeting-summaries:overpowered_model", "rec:meeting-summaries:prompt_compression" ], "leadId": "rec:meeting-summaries:migration_laggard" }, "simulation": { "formulaVersion": "sim-v1", "formula": "realization = 0.7 + 0.3 × confidence (scenario assumption)", "inputs": { "baseAnnualSavingsEur": 40939.72, "confidence": 0.7217 }, "intermediates": { "realization": 0.917 }, "outputs": { "annualSavingsEur": 37521.66, "downsideAnnualSavingsEur": 28657.8, "upsideAnnualSavingsEur": 40939.72 } }, "measured": null, "run": { "engineVersion": "0.1.0", "workspaceSourceKind": "demo", "stateVersion": "none|none|0|0:none", "datasetHash": "c8030438f36955eebab44a8b2fe9a468df7d9592992ba71e8145de0a9965ce23", "pricing": { "catalogVersion": "thornbury-scenario-v0", "unresolved": null, "rows": [ { "family": "gpt-4-turbo", "rates": { "inputPer1M": 10, "outputPer1M": 30, "cacheReadPer1M": 10, "cacheWritePer1M": 0 }, "provenance": { "source": "bayeto-scenario", "capturedAt": "2026-07-21", "quality": "scenario" } } ] }, "windowDays": 24, "windowStart": "2026-06-06T00:00:00.000Z", "windowEnd": "2026-06-29T23:58:51.723Z", "coverage": { "rows": 124800, "activeDays": 24, "unattributedRows": 0 }, "fxRates": { "USD_EUR": 0.92, "GBP_EUR": 1.17, "effectiveDate": "2026-07-06", "basis": "fixed reference rates (determinism; never live FX)" }, "implementationCostModel": { "version": "agent-assisted-v1-2026-08", "reviewHourRateEur": 100, "agentRunAllowanceEur": 20, "basis": "agent-assisted priors (review hours × rate + agent-run allowance); byHand comparison at the blended day rate" }, "engineeringDayRateEur": 800, "evidenceTaxonomyVersion": "evtax-v1", "formulaVersions": { "accuracy": "pvm-v1", "simulation": "sim-v1" }, "generatedAt": "2026-08-28T17:39:31.460Z" } }