You do not watch someone else work. Each mission ends with something you made and can use the next morning.
40
prompts to copy
13
hands-on tasks
7
hours of practice
13
weak and strong prompt duels
39
quiz questions
Passport interviewPassport (template to edit)Passport stress testBlind side-by-side testBlind judgeRoute my task to the right modelStructured task promptFew-shot style lockPrompt improverCritique stepClaim extractorSkeptic reviewerMemo from verified sourcesBrand look sheetMoodboard frame builderFive-second shotCharacter anchor blockRules file for the agentPlan-first promptExecute one stepVerify and reviewDebug without guessingHardware advisorLocal assistant system promptGrounding system promptTest sheet generatorDigest step: strict JSON summaryTelegram message templateAgent brief: competitor researchReport templateTranscript to checked task listClean transcript for sharingVoice consent noteHarden my system promptSafety test cases for my botPre-launch safety reviewSystem inventory auditRouter promptWeekly system reviewOne-page case study
Passport interviewPassport (template to edit)Passport stress testBlind side-by-side testBlind judgeRoute my task to the right modelStructured task promptFew-shot style lockPrompt improverCritique stepClaim extractorSkeptic reviewerMemo from verified sourcesBrand look sheetMoodboard frame builderFive-second shotCharacter anchor blockRules file for the agentPlan-first promptExecute one stepVerify and reviewDebug without guessingHardware advisorLocal assistant system promptGrounding system promptTest sheet generatorDigest step: strict JSON summaryTelegram message templateAgent brief: competitor researchReport templateTranscript to checked task listClean transcript for sharingVoice consent noteHarden my system promptSafety test cases for my botPre-launch safety reviewSystem inventory auditRouter promptWeekly system reviewOne-page case study
Your AI PassportYour model stackYour prompt library v1Verified research memoBrand moodboard + one 5-second shotA landing page you can open and shipA private chat running on your machineYour document chatInbox-to-Telegram digestCompetitor research agentYour voice-note-to-tasks pipelineYour bot's safety test packYour AI operating panelYour AI PassportYour model stackYour prompt library v1Verified research memoBrand moodboard + one 5-second shotA landing page you can open and shipA private chat running on your machineYour document chatInbox-to-Telegram digestCompetitor research agentYour voice-note-to-tasks pipelineYour bot's safety test packYour AI operating panel
Your AI PassportYour model stackYour prompt library v1Verified research memoBrand moodboard + one 5-second shotA landing page you can open and shipA private chat running on your machineYour document chatInbox-to-Telegram digestCompetitor research agentYour voice-note-to-tasks pipelineYour bot's safety test packYour AI operating panelYour AI PassportYour model stackYour prompt library v1Verified research memoBrand moodboard + one 5-second shotA landing page you can open and shipA private chat running on your machineYour document chatInbox-to-Telegram digestCompetitor research agentYour voice-note-to-tasks pipelineYour bot's safety test packYour AI operating panel
Claude, ChatGPT, Gemini and the rest
The map: who is good at what. Facts checked on official pages; the date is under the table.
ProductCurrent modelStrong atPrice
ClaudeAnthropicFable 5.2 · Opus 5.5Long agent sessions, deep research, finished documents and code$8 / $40 · Opus $4 / $20 ↗
ChatGPTOpenAIGPT-6 AstraComplex reasoning and coding; the widest consumer app$10 / $50 ↗
GeminiGoogleGemini 4 CarbonFirst on the LMArena text board on 11 Nov 2026 (preliminary)$2 / $10 to 30 Nov, then $4 / $20 ↗
GrokxAIGrok 4.7Long prompts: up to 500k tokens of context$2 / $6 ↗
DeepSeekDeepSeek · Open weights: yesV4-ProLow price, 1M-token context, weights on Hugging Face$0.66 / $1.98 off-peak ↗
MistralMistral AI · Open weights: yesMistral Large 4Open-weight multimodal model from a European labLe Chat Pro $14.99 / month ↗
Meta AIMetaMuse Spark 1.1Muse replaced the Llama line; Muse Wonder ranks third on LMArena text— ↗
Open since 17 November 2026. No hype and no invented numbers. Model facts carry the date they were checked, GitHub stars were read on 16 November 2026, and every install command comes from the project's own README.