Hands-on prompt engineering and LLM evaluation. Built around a diagnose-then-ship loop: forensic transcript critique ▎ that names the exact failure mode, paired with a fixer that produces complete, deployment-ready rewrites — not ▎ vague advice.
一次對話幫你建好完整客製的行銷部 AI 大腦：訪談你的產業/團隊/頻道，配出剛好的 AI 角色團隊，生成 Obsidian vault、CLAUDE.md、內容系統、SOP、說明書與自動化藍圖。給想要結構化 AI 行銷庫、又不想從零自建的創辦人與行銷團隊。 In one session, get a complete custom marketing-dept AI brain: it interviews you, right-sizes an AI team (5–17 roles), then generates an Obsidian vault, CLAUDE.md, content system, SOPs, a manual, and an automation roadmap — for founders and teams who want it without building from scratch.
Your agent or chatbot keeps getting document content wrong, citing passages that don't exist, or saying "I can't find it" about things plainly in the docs. This reframes it as a retrieval failure, not a prompt bug: corpus profile, chunking, embedding and vector-DB index choice, retrieval strategy (top-k, hybrid BM25 + dense, rerank, query rewrite), context assembly with citations, and a golden Q&A set scored on recall@k / MRR / faithfulness.
Your robots.txt may be blocking AI engines right now without you knowing. Blocking ClaudeBot does not block Claude-SearchBot — each needs its own directive. Enter a URL. Get a per-engine access table showing which crawlers can reach your page, plus the citability signals engines use: structured data, attribution, dates, headings. Not a ranking promise. A reachability check.
I've spent months building my AI agent infrastructure with cost-efficient models (DeepSeek + Qwen), using them daily for content creation, strategy, and automation. I built SplitBrain after hitting the same wall every solo brainstorm: by round 3, a single AI just parrots you. Two complementary models, 10 minutes max, signal over noise. No corporate team. No committee. Just a self-taught creator who optimized the brainstorming loop and wants you to stop burning tokens on diminishing returns.
Get better results from AI with well-crafted prompts. Describe what you need in one sentence, and Prompt Expert builds a complete, structured prompt (role, context, task, guidelines, format), ready to paste into Claude, ChatGPT or Gemini. It can also improve the prompts you already use. Works for any field: studies, careers, business, marketing, social media, coding. No technical skills needed.
Un cycle Brainstorm → Spec validée → Plan à cases à cocher → TDD strict → Review de conformité, conçu pour les devs qui construisent des SaaS pilotés par IA (générateurs, agents, outils no-code) en HTML/CSS/JS vanilla ou Node/Express, avec intégrations multi-fournisseurs (Anthropic, OpenAI, Gemini, Mistral). Exemples d'usage : "ajoute une fonctionnalité X à mon générateur", "intègre un nouveau fournisseur IA", "refonds ce module"
I design AI prompts professionally and have analyzed thousands of prompts across ChatGPT, Claude, and Gemini. I distilled the 5 essential elements that separate effective prompts from weak ones into this instant diagnostic tool. Rule-based scoring ensures consistent, deterministic results every time.
120 structured, copy-paste prompts across marketing, business writing, development, and data analysis. Every prompt uses role → context → output format → constraints — fill in the {variables} and it works on ChatGPT, Claude, or Gemini. Includes a customization guide.