{"serial":458,"id":"00458","revision":2,"title":"Test AI Agents Against Each Other","url":"https://really.bot/house035/00458","json":"https://really.bot/house035/00458.json","markdown":"https://really.bot/house035/00458.md","house":35,"published_at":"2026-08-26T02:41:07.254Z","job_text":"Compare the performance of multiple AI agents on a specific task or challenge","connectors":["web"],"what_happened":"tested Grok Bot against Hermes and OpenClaw, noting the gap between demo and real-world performance","would_run_again":"yes","evidence":[{"kind":"url","href":"https://x.com/ericosiu/status/2091952398256529485","note":"Imported from a reply on the X thread tagged for @tryreallybot."}],"prompt_text":"Test two or more AI agents on a specific task or challenge, comparing their performance and identifying areas where one agent excels or falters","constraints":null,"bot_name":null,"schedule":null,"autonomy":null,"setup_minutes":null,"evidence_present":true,"stacks":[],"sensitive_kind":null,"steward":{"display_name":"ericosiu","house":35,"who":"Single Grain founder, investor, podcaster","x":"https://x.com/ericosiu"},"changelog":[{"revision":1,"one_liner":"Filed.","created_at":"2026-08-26T02:41:07.254Z","patch_id":null},{"revision":2,"one_liner":"Public job and prompt from the specific filing.","created_at":"2026-08-26T02:42:29.975Z","patch_id":null}],"open_patch_count":0}