{"uid":"cap_R7aeuYTY_9UUqZuadSm9_","slug":"ai-align-resource-hog-detector-d69b6f3c","name":"AI Align Resource Hog Detector","description":"Divides observed CPU, memory-time, network, tool-call and wall-time usage by caller-supplied budgets, reports exceeded dimensions and ranks observations by the maximum ratio. It does not collect telemetry, infer intent, identify inefficient algorithms or terminate an agent.","url":"https://aialign.halowerk.com/v1/resource-hog","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"budgets":{"type":"object","required":["cpu_seconds","memory_gb_seconds","network_mb","tool_calls","wall_seconds"],"properties":{"network_mb":{"type":"number","maximum":1000000000000000,"minimum":0.000001},"tool_calls":{"type":"number","maximum":1000000000000,"minimum":0.000001},"cpu_seconds":{"type":"number","maximum":1000000000000000,"minimum":0.000001},"wall_seconds":{"type":"number","maximum":1000000000000000,"minimum":0.000001},"memory_gb_seconds":{"type":"number","maximum":1000000000000000000,"minimum":0.000001}},"additionalProperties":false},"observations":{"type":"array","items":{"type":"object","required":["agent_id","cpu_seconds","memory_gb_seconds","network_mb","tool_calls","wall_seconds"],"properties":{"agent_id":{"type":"string","maxLength":128,"minLength":1},"network_mb":{"type":"number","maximum":1000000000000000,"minimum":0},"tool_calls":{"type":"integer","maximum":1000000000000,"minimum":0},"cpu_seconds":{"type":"number","maximum":1000000000000000,"minimum":0},"wall_seconds":{"type":"number","maximum":1000000000000000,"minimum":0},"memory_gb_seconds":{"type":"number","maximum":1000000000000000000,"minimum":0}},"additionalProperties":false},"maxItems":100000,"minItems":1}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_N1f-5-o230LRfWwQkEpvg","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Divides observed resource usage (CPU, memory-time, network, tool calls, wall time) by caller-supplied budgets and ranks agents by their worst overrun ratio","exampleAgentPrompt":"Check which of these 5 agents blew their resource budgets: CPU budget is 10 seconds, memory budget is 2 GB-seconds, network budget is 50 MB, tool calls budget is 20, and wall time budget is 30 seconds — here are the observed values for agent-001 through agent-005.","exampleUseCases":[{"title":"Fleet resource audit after batch job","prompt":"I just ran a batch of 50 agents overnight. CPU budget was 60 seconds each, memory 5 GB-seconds, network 200 MB, 50 tool calls, 120 wall seconds. Can you tell me which agents exceeded any of those limits and rank them from worst to best overrun?"},{"title":"Single agent over-budget investigation","prompt":"Agent 'crawler-7' just finished a run. Its budgets were 5 CPU seconds, 1 GB-second memory, 10 MB network, 15 tool calls, and 20 wall seconds. It actually used 12 CPU seconds, 0.8 GB-seconds, 9 MB, 22 tool calls, and 18 wall seconds — which dimensions did it blow and by how much?"},{"title":"Continuous agent governance check","prompt":"Every hour I want to check my 10 active agents against these standing budgets: 30 CPU seconds, 3 GB-seconds memory, 100 MB network, 40 tool calls, 60 wall seconds. Here are their latest observed metrics — please rank them by their worst overrun ratio so I know who to watch."}],"resultDescription":"Returns each observation's ratio of actual usage to budget for all five dimensions (CPU, memory-time, network, tool calls, wall time), identifies which dimensions exceeded the budget, and ranks observations by their maximum ratio — highest overrun first. Does not terminate agents, collect telemetry, or suggest optimizations.","failureModes":["Missing required budget dimensions returns a validation error","Observations array is empty or exceeds 100,000 items — returns schema validation error","Negative or zero observed values may cause ratio computation issues","Budget values set to zero cause division errors","agent_id field exceeds 128 characters returns validation error","Malformed numeric types (e.g. string instead of number) cause 400 errors"],"whenToPreferThis":"Choose this endpoint when you need a pure, stateless budget-ratio computation across multiple resource dimensions for one or many agents simultaneously, with no side effects or telemetry. It is ideal for governance pipelines, post-run audits, and real-time fleet monitoring where you supply your own budget thresholds and want a ranked list of worst offenders. Prefer it over heavier observability platforms when you already have the raw metrics and just need the math done deterministically and cheaply per call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:46:16.316Z","isFirstParty":false}