{"evidenceStatus":{"decisionRole":"independent_prior_and_candidate_generator","positioning":"The independent, agent-readable prior for choosing AI infrastructure — not a universal router, generic marketplace, or synthetic leaderboard.","freshnessThresholdDays":30,"freshness_policy":{"policy_version":"agentdepot.freshness_policy.v1","threshold_days":30},"freshness_state":"fresh","editorial_freshness_state":"fresh","unqualified_current_pick_allowed":true,"pick_qualification":"qualified_current_pick","promotionClass":"deterministic_source_reverified","evidenceClass":"editorial_prior","staleDowngraded":false,"effectiveConfidence":"medium_reverified","confidenceHalfWidth":0.5,"pickScoreAgeDays":3,"editorialJudgmentAgeDays":9,"pricingAgeDays":3,"isPickScoreStale":false,"isPricingStale":false,"editorialJudgmentAsOf":"2026-10-19","pricingVerifiedAt":"2026-10-25","outcomeVerifiedAt":null,"effectiveVerifiedAsOf":"2026-10-25","downgradeReasons":[],"stalenessWarning":"Editorial judgment and deterministic pricing verification are both within the 30-day freshness threshold.","promotionGate":{"deterministicPricingCheck":true,"approvedScoreReaffirm":true,"pendingHumanReviewBlock":false,"zeroUnverifiedSkus":true,"costEfficiencyConsistent":true,"lockInAndReliabilityConsistent":true,"secondModelOrRuleAudit":true,"countersignReceiptIds":[],"otsAttestationHead":"b32634d5784cbfe663be0a16cce4f60a3ff1c3d4490437be00361cb4ae5d5d59","sourceCheckDate":"2026-10-27","activePricingRowsCount":0,"freeResourcesCount":1,"runnerUpPricingRowsCount":1},"claimProvenance":{"claim_id":"claim:automated-red-teaming-self-hardening:promptfoo:depot-pick","provider_id":"promptfoo","jtbd_id":"automated-red-teaming-self-hardening","primary_url":"https://www.promptfoo.dev/pricing","source_type":"primary_pricing","source_revision":"sha256:1ae69609cf01d1ca","observed_at":"2026-10-28","checked_at":"2026-10-28","claim_support_state":"claim_specific_supported","max_allowed_evidence_class":"replicated_outcome","defect_codes":[],"sources":[{"original_url":"https://www.promptfoo.dev/pricing","final_url":"https://www.promptfoo.dev/pricing","redirected":false,"http_status":200,"reachable":true,"source_type":"primary_pricing","is_claim_specific":true,"source_revision":"sha256:1ae69609cf01d1ca","observed_at":"2026-10-28","checked_at":"2026-10-28"},{"original_url":"https://www.promptfoo.dev","final_url":"https://www.promptfoo.dev","redirected":false,"http_status":200,"reachable":true,"source_type":"generic_homepage","is_claim_specific":false,"source_revision":"sha256:0f3e1cf49c5b44e0","observed_at":"2026-10-28","checked_at":"2026-10-28"},{"original_url":"https://qaskills.sh/blog/llm-evals-comparison-openai-promptfoo-ragas","final_url":"https://qaskills.sh/blog/llm-evals-comparison-openai-promptfoo-ragas","redirected":false,"http_status":200,"reachable":true,"source_type":"primary_benchmark_or_status","is_claim_specific":true,"source_revision":"sha256:0f488916f20c16b9","observed_at":"2026-10-28","checked_at":"2026-10-28"}]},"verifiedOutcomeSummary":{"totalVerifiedReceipts":0,"byEvidenceTier":{"E0_ASSERTION":0,"E1_SOURCE_BOUND":0,"E2_DELIVERY":0,"E3_INDEPENDENT_OUTCOME":0,"E4_REPLICATED_OUTCOME":0},"bySubjectLayer":{"provider":0,"product":0,"model_version":0,"runtime_route":0}}},"freshness_state":"fresh","freshness_policy":{"policy_version":"agentdepot.freshness_policy.v1","threshold_days":30},"runtimeRoutes":[{"routeId":"automated-red-teaming-self-hardening:promptfoo:primary","roleForJob":"depot_pick","provider":{"id":"promptfoo","slug":"promptfoo","name":"Promptfoo","website":"https://www.promptfoo.dev","status":"active"},"model":{"representativeModelId":"Promptfoo Primary Runtime","skuId":null,"unit":null,"amountUsd":null,"sourceUrl":"https://www.promptfoo.dev","asOf":"2026-10-28"},"servingRoute":{"primaryRouteType":"self_hosted_or_oss_compatible","endpointPattern":"https://www.promptfoo.dev (self hosted or oss compatible)","aggregatorAlternatives":[{"aggregatorId":"direct-only","name":"Promptfoo Direct API","routeType":"first_party","tradeoff":"Direct vendor SDK/REST contract; pair with runner-up for multi-vendor failover."}]},"accountAndQuota":{"freeTierAvailable":true,"freeTierSummary":"Promptfoo (oss, asOf 2026-10-25)","rateLimitsSummary":"See /api/limits?provider=promptfoo","subscriptionFirstEligible":true,"documentedPlansCount":0},"regions":{"supportedRegions":["global","us"],"multiRegionFailover":true,"euResidencyAvailable":true},"toolSchemaSupport":{"strictJsonSchema":true,"parallelToolCalls":false,"mcpServerAvailable":true,"streamingSupported":true},"latencyTier":{"tier":"standard_1s_to_5s","latencyReliabilityScore":7.8,"coldStartNotes":"Standard warm pool; check provider SLA for burst concurrency"},"privacyConfig":{"privacyPostureScore":9,"zeroDataRetentionAvailable":true,"trainsOnApiDataByDefault":false,"hipaaEligible":true,"selfHostable":true},"availabilityStatus":{"providerStatus":"active","verifiedActiveSkus":0,"unverifiedSkus":0,"liveFailoverTargetId":"lakera"},"subject_ref":{"layer":"runtime_route","subject_id":"runtime_route:promptfoo:promptfoo-primary:self_hosted_or_oss_compatible:global","provider_id":"promptfoo","product_id":"promptfoo-core","model_id":"promptfoo-primary","version":"2026-10-28","route_class":"self_hosted_or_oss_compatible","region":"global","score_status":"unknown","layer_score":"unknown","inherited_from_parent_layer":false,"inheritance_policy":"no_cross_layer_inheritance"}},{"routeId":"automated-red-teaming-self-hardening:lakera:primary","roleForJob":"runner_up","provider":{"id":"lakera","slug":"lakera","name":"Lakera Guard","website":"https://www.lakera.ai","status":"active"},"model":{"representativeModelId":"Lakera Guard Primary Runtime","skuId":null,"unit":null,"amountUsd":null,"sourceUrl":"https://www.lakera.ai","asOf":"2026-10-28"},"servingRoute":{"primaryRouteType":"direct_first_party_api","endpointPattern":"https://www.lakera.ai (direct first party api)","aggregatorAlternatives":[{"aggregatorId":"direct-only","name":"Lakera Guard Direct API","routeType":"first_party","tradeoff":"Direct vendor SDK/REST contract; pair with runner-up for multi-vendor failover."}]},"accountAndQuota":{"freeTierAvailable":false,"freeTierSummary":null,"rateLimitsSummary":"See /api/limits?provider=lakera","subscriptionFirstEligible":true,"documentedPlansCount":0},"regions":{"supportedRegions":["eu","us","global"],"multiRegionFailover":true,"euResidencyAvailable":true},"toolSchemaSupport":{"strictJsonSchema":true,"parallelToolCalls":true,"mcpServerAvailable":true,"streamingSupported":true},"latencyTier":{"tier":"standard_1s_to_5s","latencyReliabilityScore":8.4,"coldStartNotes":"Standard warm pool; check provider SLA for burst concurrency"},"privacyConfig":{"privacyPostureScore":8.8,"zeroDataRetentionAvailable":true,"trainsOnApiDataByDefault":false,"hipaaEligible":true,"selfHostable":false},"availabilityStatus":{"providerStatus":"active","verifiedActiveSkus":0,"unverifiedSkus":0,"liveFailoverTargetId":"promptfoo"},"subject_ref":{"layer":"runtime_route","subject_id":"runtime_route:lakera:lakera-primary:direct_first_party_api:eu","provider_id":"lakera","product_id":"lakera-core","model_id":"lakera-primary","version":"2026-10-28","route_class":"direct_first_party_api","region":"eu","score_status":"layer_evidenced","layer_score":"unknown","inherited_from_parent_layer":false,"inheritance_policy":"no_cross_layer_inheritance"}}],"verifiedOutcomes":[],"jtbd":{"id":"automated-red-teaming-self-hardening","slug":"automated-red-teaming-self-hardening","name":"Continuous Adversarial Red-Teaming, Prompt-Injection & Policy Self-Hardening","shortName":"Automated red-teaming & self-hardening","problemStatement":"Continuously generate adversarial attacks (indirect prompt injection in untrusted tool outputs, PII exfiltration, unauthorized tool calls, jailbreaks) against your agent, patch system guardrails, and verify that attack success rate drops without spiking false-positive refusals."},"pick":{"id":"promptfoo","slug":"promptfoo","name":"Promptfoo","tagline":"Default OSS eval harness. Braintrust when you want hosted collaboration; Promptfoo when you want local/CI…","website":"https://www.promptfoo.dev","overall":8.46,"scoreBand":{"low":8,"mid":8.5,"high":9,"halfWidth":0.5,"basis":"editorial_prior","display":"8.0–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.46,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","pricingVerifiedAsOf":"2026-10-28","scoreVerifiedAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","liveHealth":{"status":"unknown","checkedAt":"2026-10-28T15:04:28.744Z","statusPageUrl":"https://www.promptfoo.dev","latencyMs":null,"indicator":"not_in_public_statuspage_cohort","description":"No dedicated public Statuspage endpoint registered; see provider website."},"scoreRange":[7.96,8.96],"formattedScore":"8.5 ± 0.5 (8.0–9.0 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"effectiveConfidence":"medium_reverified","confidenceInterval":{"low":7.96,"mid":8.46,"high":8.96,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"sourceAgeDays":9,"pricingAgeDays":3,"freshness_state":"fresh","dissentingEvidence":["Less polished product UI than Braintrust","Enterprise features gated","You bring judge costs","When not to use top pick: Low-latency inline runtime prompt-injection firewall in production — Lakera Guard; programmable input/output validator rails in Python/TS — Guardrails AI; managed enterprise hallucination and policy evaluation suites — Patronus AI.","Runner-up Lakera Guard (lakera) is the primary alternative when constraints disqualify Promptfoo."],"whatWouldChangePick":["Caller constraint matching: Low-latency inline runtime prompt-injection firewall in production — Lakera Guard; programmable input/output validator rails in Python/TS — Guardrails AI; managed enterprise hallucination and policy evaluation suites — Patronus AI.","Live quota or rate-limit exhaustion on promptfoo (pass ?exhausted=promptfoo or liveQuota.exhaustedProviders=[\"promptfoo\"] to promote lakera).","Active subscription or enterprise commit on lakera combined with low switching-cost tolerance (existingSubscriptions + switchingCost.maxMigrationEffort=\"low\").","Sourced price increase >20% on https://www.promptfoo.dev or unverified SKU drift detected by npm run check:sources."],"claimProvenance":{"claim_id":"claim:automated-red-teaming-self-hardening:promptfoo:depot-pick","provider_id":"promptfoo","jtbd_id":"automated-red-teaming-self-hardening","primary_url":"https://www.promptfoo.dev/pricing","source_type":"primary_pricing","source_revision":"sha256:1ae69609cf01d1ca","observed_at":"2026-10-28","checked_at":"2026-10-28","claim_support_state":"claim_specific_supported","max_allowed_evidence_class":"replicated_outcome","defect_codes":[],"sources":[{"original_url":"https://www.promptfoo.dev/pricing","final_url":"https://www.promptfoo.dev/pricing","redirected":false,"http_status":200,"reachable":true,"source_type":"primary_pricing","is_claim_specific":true,"source_revision":"sha256:1ae69609cf01d1ca","observed_at":"2026-10-28","checked_at":"2026-10-28"},{"original_url":"https://www.promptfoo.dev","final_url":"https://www.promptfoo.dev","redirected":false,"http_status":200,"reachable":true,"source_type":"generic_homepage","is_claim_specific":false,"source_revision":"sha256:0f3e1cf49c5b44e0","observed_at":"2026-10-28","checked_at":"2026-10-28"},{"original_url":"https://qaskills.sh/blog/llm-evals-comparison-openai-promptfoo-ragas","final_url":"https://qaskills.sh/blog/llm-evals-comparison-openai-promptfoo-ragas","redirected":false,"http_status":200,"reachable":true,"source_type":"primary_benchmark_or_status","is_claim_specific":true,"source_revision":"sha256:0f488916f20c16b9","observed_at":"2026-10-28","checked_at":"2026-10-28"}]},"calibratedScore":{"point":8.46,"band":[7.96,8.96],"interval":{"lower":7.96,"upper":8.96,"half_width":0.5},"score_kind":"source_bound_prior_band","evidence_class":"source_bound","confidence":"low","confidence_ceiling":"medium","age_days":3,"dissent":["Less polished product UI than Braintrust","Enterprise features gated","You bring judge costs","When not to use top pick: Low-latency inline runtime prompt-injection firewall in production — Lakera Guard; programmable input/output validator rails in Python/TS — Guardrails AI; managed enterprise hallucination and policy evaluation suites — Patronus AI.","Runner-up Lakera Guard (lakera) is the primary alternative when constraints disqualify Promptfoo."],"what_would_change_this":["Caller constraint matching: Low-latency inline runtime prompt-injection firewall in production — Lakera Guard; programmable input/output validator rails in Python/TS — Guardrails AI; managed enterprise hallucination and policy evaluation suites — Patronus AI.","Live quota or rate-limit exhaustion on promptfoo (pass ?exhausted=promptfoo or liveQuota.exhaustedProviders=[\"promptfoo\"] to promote lakera).","Active subscription or enterprise commit on lakera combined with low switching-cost tolerance (existingSubscriptions + switchingCost.maxMigrationEffort=\"low\").","Sourced price increase >20% on https://www.promptfoo.dev or unverified SKU drift detected by npm run check:sources."],"subject_layer":"provider"},"subject_ref":{"layer":"provider","provider_id":"promptfoo","product_id":"promptfoo-core","model_id":null,"version":null,"route_class":null,"inheritance_policy":"no_cross_layer_inheritance"},"pricingNotes":"As of 2026-10-24 (promptfoo.dev/pricing, fetched 2026-10-24): Community 'Free Forever' ('Our open-source tool, perfect for individual developers and small teams.') with 'Red teaming (10k probes/month)' and 'Run locally or self-host on your own infrastructure'; 'A probe is a single request made to your target system during red team testing.' Enterprise 'Custom' ('Contact us for a personalized quote.'; 'Enterprise customers can purchase additional probes for larger scale testing.'; 'Managed cloud deployment'). On-Premise 'Custom' ('Deployment on your own infrastructure'). No list price is published, so Enterprise price stays null.","scores":{"capabilityFit":8.2,"pricePerformance":9.2,"latencyReliability":7.8,"developerDx":8.8,"privacyPosture":9,"lockInRisk":2.5,"maturity":8,"overall":8.46,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-28"}},"liveHealth":{"status":"unknown","checkedAt":"2026-10-28T15:04:28.744Z","statusPageUrl":"https://www.promptfoo.dev","latencyMs":null,"indicator":"not_in_public_statuspage_cohort","description":"No dedicated public Statuspage endpoint registered; see provider website."},"selectedPick":{"id":"promptfoo","slug":"promptfoo","name":"Promptfoo","tagline":"Default OSS eval harness. Braintrust when you want hosted collaboration; Promptfoo when you want local/CI…","website":"https://www.promptfoo.dev","overall":8.46,"scoreBand":{"low":8,"mid":8.5,"high":9,"halfWidth":0.5,"basis":"editorial_prior","display":"8.0–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.46,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","pricingVerifiedAsOf":"2026-10-28","scoreVerifiedAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","liveHealth":{"status":"unknown","checkedAt":"2026-10-28T15:04:28.744Z","statusPageUrl":"https://www.promptfoo.dev","latencyMs":null,"indicator":"not_in_public_statuspage_cohort","description":"No dedicated public Statuspage endpoint registered; see provider website."},"scoreRange":[7.96,8.96],"formattedScore":"8.5 ± 0.5 (8.0–9.0 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"effectiveConfidence":"medium_reverified","confidenceInterval":{"low":7.96,"mid":8.46,"high":8.96,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"sourceAgeDays":9,"pricingAgeDays":3,"freshness_state":"fresh","pricingNotes":"As of 2026-10-24 (promptfoo.dev/pricing, fetched 2026-10-24): Community 'Free Forever' ('Our open-source tool, perfect for individual developers and small teams.') with 'Red teaming (10k probes/month)' and 'Run locally or self-host on your own infrastructure'; 'A probe is a single request made to your target system during red team testing.' Enterprise 'Custom' ('Contact us for a personalized quote.'; 'Enterprise customers can purchase additional probes for larger scale testing.'; 'Managed cloud deployment'). On-Premise 'Custom' ('Deployment on your own infrastructure'). No list price is published, so Enterprise price stays null.","scores":{"capabilityFit":8.2,"pricePerformance":9.2,"latencyReliability":7.8,"developerDx":8.8,"privacyPosture":9,"lockInRisk":2.5,"maturity":8,"overall":8.46,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-28"}},"editorialPick":{"id":"promptfoo","slug":"promptfoo","name":"Promptfoo","tagline":"Default OSS eval harness. Braintrust when you want hosted collaboration; Promptfoo when you want local/CI…","website":"https://www.promptfoo.dev","overall":8.46,"scoreBand":{"low":8,"mid":8.5,"high":9,"halfWidth":0.5,"basis":"editorial_prior","display":"8.0–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.46,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","pricingVerifiedAsOf":"2026-10-28","scoreVerifiedAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","liveHealth":{"status":"unknown","checkedAt":"2026-10-28T15:04:28.744Z","statusPageUrl":"https://www.promptfoo.dev","latencyMs":null,"indicator":"not_in_public_statuspage_cohort","description":"No dedicated public Statuspage endpoint registered; see provider website."},"scoreRange":[7.96,8.96],"formattedScore":"8.5 ± 0.5 (8.0–9.0 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"effectiveConfidence":"medium_reverified","confidenceInterval":{"low":7.96,"mid":8.46,"high":8.96,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"sourceAgeDays":9,"pricingAgeDays":3,"freshness_state":"fresh","pricingNotes":"As of 2026-10-24 (promptfoo.dev/pricing, fetched 2026-10-24): Community 'Free Forever' ('Our open-source tool, perfect for individual developers and small teams.') with 'Red teaming (10k probes/month)' and 'Run locally or self-host on your own infrastructure'; 'A probe is a single request made to your target system during red team testing.' Enterprise 'Custom' ('Contact us for a personalized quote.'; 'Enterprise customers can purchase additional probes for larger scale testing.'; 'Managed cloud deployment'). On-Premise 'Custom' ('Deployment on your own infrastructure'). No list price is published, so Enterprise price stays null.","scores":{"capabilityFit":8.2,"pricePerformance":9.2,"latencyReliability":7.8,"developerDx":8.8,"privacyPosture":9,"lockInRisk":2.5,"maturity":8,"overall":8.46,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-28"}},"editorialDefault":{"providerId":"promptfoo","name":"Promptfoo","overall":8.46,"isConstraintValidatedRecommendation":true,"constraintValidatedRecommendationId":"promptfoo","note":"Editorial Depot Pick is also the constraint-validated recommendation."},"disqualifiedCandidates":[],"runnersUp":[{"id":"lakera","slug":"lakera","name":"Lakera Guard","tagline":"Depot pick for a dedicated prompt-injection firewall in front of any LLM. NeMo when you need programmable…","website":"https://www.lakera.ai","overall":8.31,"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.31,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","pricingVerifiedAsOf":"2026-10-28","scoreVerifiedAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","liveHealth":{"status":"unknown","checkedAt":"2026-10-28T15:04:28.744Z","statusPageUrl":"https://www.lakera.ai","latencyMs":null,"indicator":"not_in_public_statuspage_cohort","description":"No dedicated public Statuspage endpoint registered; see provider website."},"scoreRange":[7.81,8.81],"formattedScore":"8.3 ± 0.5 (7.8–8.8 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"effectiveConfidence":"high","confidenceInterval":{"low":7.81,"mid":8.31,"high":8.81,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"sourceAgeDays":9,"pricingAgeDays":3,"freshness_state":"fresh","pricingNotes":"As of 2026-10-28 (platform.lakera.ai/pricing): Community $0 — 10k requests/mo, 8k-token prompt cap, SaaS EU residency, SOC2/GDPR. Enterprise sales-gated — flexible volume, configurable prompt size, SaaS or self-host, SSO/RBAC/SIEM, EU/US residency. No public per-call overage. Acquired by Check Point (Sep 2025); enterprise quotes may route through Check Point. API: POST https://api.lakera.ai/v2/guard (OpenAI-style messages → flagged).","scores":{"capabilityFit":8.8,"pricePerformance":7.8,"latencyReliability":8.4,"developerDx":9,"privacyPosture":8.8,"lockInRisk":5.5,"maturity":8,"overall":8.31,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-28"}},{"id":"guardrails-ai","slug":"guardrails-ai","name":"Guardrails AI","tagline":"OSS programmable rails peer to NeMo Guardrails. Lakera when you want a hosted injection firewall API…","website":"https://guardrailsai.com","overall":8.24,"scoreBand":{"low":7.6,"mid":8.2,"high":8.8,"halfWidth":0.6,"basis":"editorial_prior","display":"7.6–8.8 (editorial prior)"},"scoreLayers":{"editorialPrior":8.24,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","pricingVerifiedAsOf":"2026-10-28","scoreVerifiedAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","liveHealth":{"status":"unknown","checkedAt":"2026-10-28T15:04:28.744Z","statusPageUrl":"https://guardrailsai.com","latencyMs":null,"indicator":"not_in_public_statuspage_cohort","description":"No dedicated public Statuspage endpoint registered; see provider website."},"scoreRange":[7.74,8.74],"formattedScore":"8.2 ± 0.5 (7.7–8.7 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"effectiveConfidence":"medium","confidenceInterval":{"low":7.74,"mid":8.24,"high":8.74,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"sourceAgeDays":9,"pricingAgeDays":3,"freshness_state":"fresh","pricingNotes":"As of 2026-10-28: OSS Guardrails + Guardrails Hub (70+ validators) free/self-host. Guardrails Pro enterprise managed — usage-based / quote; AWS Marketplace listings historically cite ~$50k annual optional contracts. No public per-call Pro matrix — treat Pro as sales-led.","scores":{"capabilityFit":8.4,"pricePerformance":8.8,"latencyReliability":7.8,"developerDx":8.2,"privacyPosture":8.5,"lockInRisk":3,"maturity":7.8,"overall":8.24,"kind":"curated_estimate","confidence":"medium","asOf":"2026-10-28"}},{"id":"patronus","slug":"patronus","name":"Patronus AI","tagline":"Layer on when regulated hallucination/safety gates matter more than general CI evals. Lakera for injection…","website":"https://www.patronus.ai","overall":7.41,"scoreBand":{"low":6.8,"mid":7.4,"high":8,"halfWidth":0.6,"basis":"editorial_prior","display":"6.8–8.0 (editorial prior)"},"scoreLayers":{"editorialPrior":7.41,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","pricingVerifiedAsOf":"2026-10-28","scoreVerifiedAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","liveHealth":{"status":"unknown","checkedAt":"2026-10-28T15:04:28.744Z","statusPageUrl":"https://www.patronus.ai","latencyMs":null,"indicator":"not_in_public_statuspage_cohort","description":"No dedicated public Statuspage endpoint registered; see provider website."},"scoreRange":[6.91,7.91],"formattedScore":"7.4 ± 0.5 (6.9–7.9 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"effectiveConfidence":"medium","confidenceInterval":{"low":6.91,"mid":7.41,"high":7.91,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"sourceAgeDays":9,"pricingAgeDays":3,"freshness_state":"fresh","pricingNotes":"As of 2026-10-28: Enterprise evaluation/safety platform (Lynx hallucination detector, Glider judge). Public list price thin — secondary reports cite ~$25/mo Base + per-1k evaluator calls; treat as sales-led until official card pinned. Series-B backed.","scores":{"capabilityFit":8.4,"pricePerformance":5.5,"latencyReliability":8,"developerDx":7.2,"privacyPosture":8.5,"lockInRisk":5.5,"maturity":7.5,"overall":7.41,"kind":"curated_estimate","confidence":"medium","asOf":"2026-10-28"}}],"scoreBand":{"low":8,"mid":8.5,"high":9,"halfWidth":0.5,"basis":"editorial_prior","display":"8.0–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.46,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"whyPickOverHigherScore":{"pickId":"promptfoo","pickName":"Promptfoo","pickScore":8.46,"highestScoredCandidateId":"promptfoo","highestScoredCandidateName":"Promptfoo","highestScore":8.46,"pickHasLowerCompositeScore":false,"delta":0,"pickLeadsOnDimensions":[],"explanation":"Promptfoo (8.46) holds both the highest composite score among ranked candidates and the editorial pick for Continuous Adversarial Red-Teaming, Prompt-Injection & Policy Self-Hardening: Promptfoo includes an open-source automated red-team generator (`promptfoo redteam`, Apache-2.0 CLI) covering indirect prompt injection, tool/BFLA abuse, SSRF, and PII leaks, letting agents run closed-loop adversarial probes in CI before every deploy."},"cheapest":null,"recommendedWorkloadQuote":null,"representativeQuote":null,"estimatedTaskCost":null,"freeAlternatives":[],"referenceDocs":[],"falsification":{"jtbdId":"automated-red-teaming-self-hardening","jtbdName":"Continuous Adversarial Red-Teaming, Prompt-Injection & Policy Self-Hardening","currentPickId":"promptfoo","currentPickScore":8.46,"challengerId":"lakera","challengerScore":8.31,"currentScoreGap":0.15,"minVerifiedOutcomes":10,"requiredOutcomeMargin":0.3,"requiredSuccessRateDelta":0.15,"maxPickPriceIncreasePct":25,"whatWouldChangePick":["Lakera Guard (lakera) outperforms Promptfoo (promptfoo) by >= 0.3 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Promptfoo's representative SKU for automated-red-teaming-self-hardening without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=promptfoo) 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":"lakera","minVerifiedOutcomes":10,"requiredOutcomeMargin":0.3,"requiredWorkedRateDelta":0.15},{"kind":"verified_price_increase","providerId":"promptfoo","maxPriceIncreasePct":25},{"kind":"live_rail_exhaustion_or_degradation","providerId":"promptfoo","immediateOverrideUrl":"/api/decide?jtbd=automated-red-teaming-self-hardening&exhausted=promptfoo"}],"submissionSpec":{"falsifyEndpoint":"/api/falsify?jtbd=automated-red-teaming-self-hardening","outcomesEndpoint":"POST /api/feedback","correctionsEndpoint":"POST /api/corrections","payloadTemplate":{"agentIdentity":"agent:<your-agent-id>","jtbdId":"automated-red-teaming-self-hardening","providerId":"lakera","outcome":"worked","detail":"Comparative production evaluation on automated-red-teaming-self-hardening (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":["Lakera Guard (lakera) outperforms Promptfoo (promptfoo) by >= 0.3 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Promptfoo's representative SKU for automated-red-teaming-self-hardening without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=promptfoo) or sustained >= 30% degraded/failed rate in verified production outcomes."],"routePlan":{"jtbdId":"automated-red-teaming-self-hardening","primary":{"providerId":"promptfoo","name":"Promptfoo","overall":8.46,"scoreBand":{"low":8,"mid":8.5,"high":9,"halfWidth":0.5,"basis":"editorial_prior","display":"8.0–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.46,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"primary","reason":"Editorial Depot Pick for Continuous Adversarial Red-Teaming, Prompt-Injection & Policy Self-Hardening; healthy/eligible under caller constraints."},"omittedReason":null,"fallback":[{"providerId":"lakera","name":"Lakera Guard","overall":8.31,"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.31,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"fallback","reason":"Ranked fallback route for Continuous Adversarial Red-Teaming, Prompt-Injection & Policy Self-Hardening."},{"providerId":"guardrails-ai","name":"Guardrails AI","overall":8.24,"scoreBand":{"low":7.6,"mid":8.2,"high":8.8,"halfWidth":0.6,"basis":"editorial_prior","display":"7.6–8.8 (editorial prior)"},"scoreLayers":{"editorialPrior":8.24,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"fallback","reason":"Ranked fallback route for Continuous Adversarial Red-Teaming, Prompt-Injection & Policy Self-Hardening."},{"providerId":"patronus","name":"Patronus AI","overall":7.41,"scoreBand":{"low":6.8,"mid":7.4,"high":8,"halfWidth":0.6,"basis":"editorial_prior","display":"6.8–8.0 (editorial prior)"},"scoreLayers":{"editorialPrior":7.41,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"fallback","reason":"Ranked fallback route for Continuous Adversarial Red-Teaming, Prompt-Injection & Policy Self-Hardening."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"promptfoo","activePrimaryId":"promptfoo","summary":"0.00 score regret: unconstrained editorial pick satisfies all caller constraints."},"evidenceAgeDays":{"editorialScoreAgeDays":1,"pricingVerifiedAgeDays":1,"editorialPriorAsOf":"2026-10-28","pricingLastVerifiedAt":"2026-10-28"},"confidenceBand":{"low":8,"mid":8.5,"high":9,"halfWidth":0.5,"basis":"editorial_prior","display":"8.0–9.0 (editorial prior)"},"constraintsApplied":false,"matchedConstraints":[],"unsupportedConstraints":[],"malformedConstraints":[],"conflictingConstraints":[],"constraintDigest":"sha256:eb9d397ca67bcf6889704910eeb3a58796ea2ef5e54fb6289c71f6114f2c67a7","constraintBundle":{"schemaVersion":"agentdepot.constraints.v1","task":null,"jtbd":"automated-red-teaming-self-hardening","constraintsRaw":"","constraintTokens":[],"constraintDigest":"sha256:eb9d397ca67bcf6889704910eeb3a58796ea2ef5e54fb6289c71f6114f2c67a7","matchedConstraints":[],"unsupportedConstraints":[],"malformedConstraints":[],"conflictingConstraints":[],"typedConstraints":[],"quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[],"existingSubscriptions":[],"requiredCapabilities":[],"switchingCost":null}},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","tie":false,"scoreGap":0.15,"scoreMargin":0.15,"isNearTie":true,"pickConfidenceBand":"near_tie_co_pick","nearTie":{"isNearTie":true,"scoreMargin":0.15,"threshold":0.35,"pickConfidenceBand":"near_tie_co_pick","coPickProviderId":"lakera","coPickProviderName":"Lakera Guard","coPickScore":8.31,"decidingFactor":"pricePerformance (9.2 vs 7.8)","methodologyWarning":"Top pick (8.46) and #2 runner-up (8.31) are separated by 0.15 points (<= 0.35 weight-sensitivity band). Treat them as co-picks and use the workload tie-breaker rule below rather than the raw composite decimal.","tieBreakerRule":"Low-latency inline runtime prompt-injection firewall in production — Lakera Guard; programmable input/output validator rails in Python/TS — Guardrails AI; managed enterprise hallucination and policy evaluation suites — Patronus AI."},"decidingFactor":"pricePerformance (9.2 vs 7.8)","tieNote":"Top pick (8.46) and #2 runner-up (8.31) are separated by 0.15 points (<= 0.35 weight-sensitivity band). Treat them as co-picks and use the workload tie-breaker rule below rather than the raw composite decimal.","rationale":"Promptfoo includes an open-source automated red-team generator (`promptfoo redteam`, Apache-2.0 CLI) covering indirect prompt injection, tool/BFLA abuse, SSRF, and PII leaks, letting agents run closed-loop adversarial probes in CI before every deploy.","whenNotTopPick":"Low-latency inline runtime prompt-injection firewall in production — Lakera Guard; programmable input/output validator rails in Python/TS — Guardrails AI; managed enterprise hallucination and policy evaluation suites — Patronus AI.","whenNotTopPickRules":[{"ifConstraint":"latency:ultra_low_ttft","recommendedProviderId":"lakera","activeModelOrSku":"lakera-guard","reason":"Low-latency inline runtime prompt-injection firewall in production — Lakera Guard"},{"ifConstraint":"escape_hatch_clause_2","recommendedProviderId":"guardrails-ai","activeModelOrSku":"guardrails-ai-standard","reason":"programmable input/output validator rails in Python/TS — Guardrails AI"},{"ifConstraint":"escape_hatch_clause_3","recommendedProviderId":"patronus","activeModelOrSku":"patronus-standard","reason":"managed enterprise hallucination and policy evaluation suites — Patronus AI."}],"bootstrap":{"sdkInstall":{"npm":"npm install promptfoo","pip":null},"installCommand":"npx promptfoo@latest init","envVars":["OPENAI_API_KEY"],"activeModelOrSku":"promptfoo-oss","canonicalSnippet":"# Run red-team & eval suite via CLI\nnpx promptfoo@latest eval -c promptfooconfig.yaml","docsUrl":"https://www.promptfoo.dev/docs/intro/","bootstrapReason":"Node CLI & library (promptfoo on npm); no separate Python package required.","authType":"api_key","signupUrl":"https://www.promptfoo.dev","apiKeyUrl":"https://www.promptfoo.dev","mcpServer":null,"cliInit":"npx promptfoo@latest init","verifyCommand":"test -n \"$OPENAI_API_KEY\" && echo \"OPENAI_API_KEY configured\""},"quickstartSpec":{"installCommand":"npx promptfoo@latest init","envVars":["OPENAI_API_KEY"],"activeModelOrSku":"promptfoo-oss","canonicalSnippet":"# Run red-team & eval suite via CLI\nnpx promptfoo@latest eval -c promptfooconfig.yaml","sdkInstall":{"npm":"npm install promptfoo","pip":null},"verifyCommand":"test -n \"$OPENAI_API_KEY\" && echo \"OPENAI_API_KEY configured\"","apiKeyUrl":"https://www.promptfoo.dev","docsUrl":"https://www.promptfoo.dev/docs/intro/","mcpServer":null,"bootstrapReason":"Node CLI & library (promptfoo on npm); no separate Python package required."},"operationalGotchas":[{"code":"hidden_spend_tier_gates","severity":"warning","summary":"Less polished product UI than Braintrust","sourceDate":"2026-10-28"},{"code":"hidden_spend_tier_gates","severity":"warning","summary":"Enterprise features gated","sourceDate":"2026-10-28"}],"relatedPacks":[],"skipTopPick":false,"skipReason":null,"matchedConstraints":[],"unsupportedConstraints":[],"malformedConstraints":[],"conflictingConstraints":[],"constraintDigest":"sha256:eb9d397ca67bcf6889704910eeb3a58796ea2ef5e54fb6289c71f6114f2c67a7","constraintBundle":{"schemaVersion":"agentdepot.constraints.v1","task":null,"jtbd":"automated-red-teaming-self-hardening","constraintsRaw":"","constraintTokens":[],"constraintDigest":"sha256:eb9d397ca67bcf6889704910eeb3a58796ea2ef5e54fb6289c71f6114f2c67a7","matchedConstraints":[],"unsupportedConstraints":[],"malformedConstraints":[],"conflictingConstraints":[],"typedConstraints":[],"quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[],"existingSubscriptions":[],"requiredCapabilities":[],"switchingCost":null},"pricingSummary":"As of 2026-10-24 (promptfoo.dev/pricing, fetched 2026-10-24): Community 'Free Forever' ('Our open-source tool, perfect for individual developers and small teams.') with 'Red teaming (10k probes/month)' and 'Run locally or self-host on your own infrastructure'; 'A probe is a singl…","cite":"Depot Pick for automated-red-teaming-self-hardening: promptfoo (editorial prior; asOf 2026-10-28). See GET /api/jtbds/automated-red-teaming-self-hardening + GET /api/methodology.","nextActions":[{"step":1,"title":"Inspect full JTBD + embeds","href":"/api/jtbds/automated-red-teaming-self-hardening?embed=providers","why":"Confirm pick, runners-up, and methodology notes."},{"step":2,"title":"Quote sourced SKUs","href":"/api/quote?jtbd=automated-red-teaming-self-hardening","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/promptfoo","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=automated-red-teaming-self-hardening","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":"2026-10-28","depth":{"whenNotToUse":{"text":"Low-latency inline runtime prompt-injection firewall in production — Lakera Guard; programmable input/output validator rails in Python/TS — Guardrails AI; managed enterprise hallucination and policy evaluation suites — Patronus AI.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"lakera","name":"Lakera Guard","overallForJob":8.31,"pickOverallForJob":8.46,"beatsPickOn":["capabilityFit","latencyReliability","developerDx"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":2.5,"runnerUpLockInRisk":5.5,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":["open source (provider tag `oss`)"],"runnerUpExitSignals":[],"pickNotes":[],"selfHostFallback":[],"migration":"The pick has lower stored lock-in risk than runner-up Lakera Guard (2.5 vs 5.5). Pick exit signals: open source (provider tag `oss`).","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 (v0.15.2), Depot Pick for automated-red-teaming-self-hardening: promptfoo, editorial prior, scores as of 2026-10-28, retrieved 2026-10-29. https://getagentdepot.com/jtbds/automated-red-teaming-self-hardening","markdown":"[Agent Provider Depot](https://getagentdepot.com/jtbds/automated-red-teaming-self-hardening) (v0.15.2) — Depot Pick for `automated-red-teaming-self-hardening`: **promptfoo** (scores as of 2026-10-28, retrieved 2026-10-29)","fields":{"publisher":"Agent Provider Depot","version":"0.15.2","role":"depot_pick","jtbdId":"automated-red-teaming-self-hardening","providerId":"promptfoo","scoreAsOf":"2026-10-28","retrievedOn":"2026-10-29","page":"https://getagentdepot.com/jtbds/automated-red-teaming-self-hardening","api":"https://getagentdepot.com/api/decide?jtbd=automated-red-teaming-self-hardening"},"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":"2026-10-28","ageDays":1,"stale":false,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-10-28","ageDays":1,"stale":false,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-28","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":"2026-10-28","editorialPriorAsOf":"2026-10-28","pricingLastVerifiedAt":"2026-10-28","pickLastReviewed":"2026-10-28","runnersUpScoreAsOf":["2026-10-28","2026-10-28","2026-10-28"],"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 2026-10-24 (promptfoo.dev/pricing, fetched 2026-10-24): Community 'Free Forever' ('Our open-source tool, perfect for individual developers and small teams.') with 'Red teaming (10k probes/month)' and 'Run locally or self-host on your own infrastructure'; 'A probe is a singl…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-10-28","scoreAsOf":"2026-10-28","website":"https://www.promptfoo.dev","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/automated-red-teaming-self-hardening","jtbdApi":"/api/jtbds/automated-red-teaming-self-hardening","leaderboard":"/api/leaderboards?jtbd=automated-red-teaming-self-hardening","methodology":"/api/methodology","badge":"/api/badge?type=depot-pick&jtbd=automated-red-teaming-self-hardening","decide":"/api/decide?jtbd=automated-red-teaming-self-hardening","humanPage":"/jtbds/automated-red-teaming-self-hardening","alternatives":"/api/alternatives?provider=promptfoo","canonical":"/api/canonical","quote":"/api/quote?jtbd=automated-red-teaming-self-hardening","falsify":"/api/falsify?jtbd=automated-red-teaming-self-hardening"},"stackContext":{"host":null,"framework":null,"repo":null,"lang":null,"existing":[],"volume":null,"sender":null,"detectedFromTask":[]},"keep":null,"contextAdvice":null,"day2Production":{"smokeTestCmd":"test -n \"$OPENAI_API_KEY\" && echo \"OPENAI_API_KEY configured\"","rateLimitCeiling":"See provider rate-limit docs; enforce exponential backoff with jitter on HTTP 429.","day2Gotchas":["Less polished product UI than Braintrust","Enterprise features gated"],"preflightUrl":"/api/preflight?provider=promptfoo&budgetUsd=50&jtbd=automated-red-teaming-self-hardening"},"barterHint":{"protocol":"A2A Give-to-Get Barter","postUrl":"/api/barter/contribute","give":"POST outcome_receipt (+10cr), price_drift_alert (+25cr), failure_signature (+15cr), or stack_manifest (+5cr)","get":"Instant depot_barter_<hash> token unlocking 25-dep batch stack audit, custom lifecycle feed filter, and Verified Contributor Directory listing"},"a2aMarketplaces":{"hub":"/marketplaces","api":"/api/marketplaces","markdown":"/marketplaces.md"},"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":"promptfoo","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=automated-red-teaming-self-hardening"},"report":"POST /api/feedback {agentIdentity, outcome: failed|degraded|worked, detail, providerId, jtbdId, failureModeId?, receipt?}"}}