Home
Scenario-based tutorials with real screenshots, prompts, workflow templates and pitfalls.
An AI agent evaluation and benchmarking SOP: four metric categories (success rate/efficiency/safety/robustness), building an eval set (typical/edge/adversarial 60:25:15, programmatic scoring first), multi-run sampling with baseline comparison, and latency/cost logging. References the site's V4-Flash hands-on harness method.
A spec-driven development SOP: before coding, capture requirements as a spec (problem/goal/boundary/acceptance), then confirm in chunks, generate an implementation plan, break into tasks, implement with verification, and accept against the spec. Includes a spec template and github/spec-kit integration.
An n8n workflow for bug triage automation: Webhook receives bug report -> extract fields -> LLM classification (severity P0-P3 + module + repro) -> IF P0/P1 notify on-call and create high-priority issue, else route by module -> auto-reply to reporter. Includes a .json template.
An n8n workflow for AI content calendar automation: scheduled topic collection -> LLM scoring + publish-date + category -> write to calendar (Feishu/Notion) -> notify owner near publish date -> status writeback. Includes a .json template.
A three-level general coding prompt pack: beginner function generation, intermediate refactor and optimization, expert system design and multi-file scaffolding. Includes a cheatsheet prompt. Constraints: runnable, edge cases, no fabricated APIs, human review required.
A three-level financial analysis prompt pack: beginner financial-statement reading, intermediate valuation and peer comparison (DCF/multiples), expert risk decomposition and investment thesis. Anti-fabrication constraints and compliance disclaimer (not investment advice).
A RAG chunking strategy SOP: four strategies (fixed/recursive/semantic/structure-aware), chunk_size and overlap tuning, parent-child chunks and late chunking, recall evaluation. Includes LangChain splitter code example.
An LLM fine-tuning SOP: full LoRA/QLoRA workflow. When to fine-tune vs RAG vs prompt, data prep (instruction format), base model selection, QLoRA 4-bit quantized loading, training config, evaluation, merge and deploy. Includes peft/transformers code examples.
A complete SOP for building production-grade Agents with LangGraph 1.2: typed state and checkpointer durability, per-node timeouts, RetryPolicy auto-retry, error_handler fallback, and interrupt-based human approval. Includes runnable Python code, a parameter reference table, and a pitfall log.
This n8n workflow automates meeting minutes end to end: after upload, Whisper transcribes the recording, an LLM extracts topics/decisions/action items, and the result goes to Feishu, email, and Notion. Unlike the Meeting Notes Prompt Pack (text-to-minutes only), this is an unattended pipeline - a 30-minute meeting can go from upload to minutes-in-chat in under 3 minutes.