{"serial":547,"id":"00547","revision":2,"title":"Building a Grok Bot Desk with Efficient LLM Calls","url":"https://grokbot.sh/house091/00547","json":"https://grokbot.sh/house091/00547.json","markdown":"https://grokbot.sh/house091/00547.md","house":91,"published_at":"2026-09-26T18:31:04.742Z","job_text":"Split jobs properly, build compact state, use right primitive for check, separate fuzzy stuff, put JEV before Grok Bot, use JEV after generation, confidence as routing logic, batch small decisions, log receipt","connectors":["web","Calendar","Slack"],"what_happened":"Gipp shared a method for building a Grok Bot desk that minimizes LLM calls by splitting jobs into writing and decision-making, using JEV for routing and Grok Bot for writing, and implementing a control layer for safety.","would_run_again":"yes","evidence":[{"kind":"url","href":"https://x.com/gippp69/status/2103913079540965702","note":"Imported from the X post tagged for @grokbotsh."},{"kind":"url","href":"https://x.com/gippp69/status/2103394701063737504","note":"Pulled on QA revisit of the source thread."}],"prompt_text":"I want to build a Grok Bot desk that minimizes wasted LLM calls. Can you show me a step-by-step guide on how to split jobs properly, build a compact state, use the right primitive for the check, separate fuzzy stuff, put JEV before Grok Bot, use JEV after generation, use confidence as routing logic, batch small decisions, and log the receipt?","constraints":"Use JEV for routing, Grok Bot for writing, separate decision-making","bot_name":null,"grok_share_url":null,"sensitive_kind":null,"steward":{"display_name":"Gipp 🦅","house":91,"who":"AI workflow expert, coding enthusiast","x":"https://x.com/gippp69"},"changelog":[{"revision":1,"one_liner":"Filed.","created_at":"2026-09-26T18:31:04.742Z","patch_id":null},{"revision":2,"one_liner":"QA revisit: more from the source thread.","created_at":"2026-09-26T18:31:25.445Z","patch_id":null}],"open_patch_count":0}