How to Publish a GPU Ready Rate That Readers Can Check

{"category":"","description":"","inputSchema":{"type":"object"},"schemaVersion":1,"steps":[{"expectedOutputs":[],"id":"9A7X","instructions":"A reliability number is only useful if readers can see what it counts. Here is the checklist we follow on our public Capacity Index, so your team can copy it. A playbook for teams that publish performance figures. Company-prepared, not independent reporting.","resourceHints":[],"title":"Start here"},{"expectedOutputs":[],"id":"7W7M","instructions":"Ours: a launch whose machine passed a health check at least once, either a healthy provider check or a healthy in-machine agent report. Acceptance by the underlying infrastructure alone does not count.","resourceHints":[],"title":"Define \"ready\" before you show a number"},{"expectedOutputs":[],"id":"ICMM","instructions":"\"No machine started\" means the order could not be placed. \"Machine did not become ready\" means a machine started but never passed its check. They have different causes and different fixes. As of Oct. 19, 2026, 17:49 UTC, we show 679 launches: 446 ready, 103 no machine started, 130 machine did not become ready.","resourceHints":[],"title":"Split the two kinds of failure"},{"expectedOutputs":[],"id":"II1Y","instructions":"We label launches as internal (490), sponsored (181) and outside (8). Most launches in our data are our own tests, and the page says so.","resourceHints":[],"title":"Say who ran the traffic"},{"expectedOutputs":[],"id":"19QQ","instructions":"A \"Normal routing\" view (230 launches) keeps forced test runs from blending into the headline.","resourceHints":[],"title":"Show routine traffic separately"},{"expectedOutputs":[],"id":"SZ4I","instructions":"Any GPU type with fewer than 20 launches shows \"Not enough data yet\" instead of a rate.","resourceHints":[],"title":"Set a minimum sample size"},{"expectedOutputs":[],"id":"7LST","instructions":"Each figure carries an as-of time. Our counts start on Sep. 21, 2026, and the page notes that 32 earlier launches are excluded.","resourceHints":[],"title":"Timestamp every number and state its scope"},{"expectedOutputs":[],"id":"GD1V","instructions":"Our reports include a section on exactly that: small samples, detection times longer than our target, and the fact that we prepared the reports ourselves. When a run was invalid because of a defect in our own test script, we marked it \"Not a test result\" and said why.","resourceHints":[],"title":"Publish what the results do not show"},{"expectedOutputs":[],"id":"69R5","instructions":"We published Outside Tester Report 1: nine findings, nine changes.","resourceHints":[],"title":"Let outsiders check your work, and show what changed"},{"expectedOutputs":[],"id":"NBEM","instructions":"These figures come from our own job records. They are not a customer success rate and have not been independently verified. Live figures and definitions: https://www.kilawattcloud.dev/capacity-index?utm_source=epismo&utm_medium=playbook&utm_campaign=ready-rate-checklist Our published reports, including the misses: https://www.kilawattcloud.dev/super-intelligence?utm_source=epismo&utm_medium=playbook&utm_campaign=ready-rate-checklist Kilawatt Cloud is a trade name of Right Recruit LLC. This is not an offer and contains no forecast.","resourceHints":[],"title":"What this does not claim, and sources"}],"title":"How to Publish a GPU Ready Rate That Readers Can Check"}