alecor.net.
  • AI
  • Home
  • About
  • Contact
  • Projects
  • Tags
  • Categories
  • Archives
🇬🇧 🇦🇷 🇧🇷 🇵🇱 🇷🇺
  • 2026-09-16

    Idempotency, Retries and Durable Execution Cheatsheet for AI Agent Backends

    A practical cheatsheet on making AI agents safe to retry and resume: why agents are distributed systems, idempotency keys and how to implement them, retries with exponential backoff and jitter,...

    AI · cheatsheets AI agents idempotency retries durable execution distributed systems backend reliability English
  • 2026-08-12

    LLM Cost Optimization Cheatsheet: Prompt Caching, Batching and Model Routing

    A practical cheatsheet for cutting LLM API costs without cutting quality: where the money actually goes (input vs. output vs. cached tokens), prompt caching and how to structure prompts for cache...

    AI · cheatsheets AI LLMs cost optimization prompt caching model routing FinOps English
  • 2026-06-10

    Fine-tuning vs Prompting vs RAG: LoRA and QLoRA Cheatsheet

    A practical cheatsheet for choosing between prompting, retrieval and fine-tuning, and for doing parameter-efficient fine-tuning well when you need it: how LoRA and QLoRA work, the hyperparameters...

    AI · cheatsheets AI LLMs fine-tuning LoRA QLoRA RAG prompting English
  • 2026-05-13

    Structured Outputs Cheatsheet: JSON Schema, Pydantic, Constrained Decoding

    A practical cheatsheet for getting reliable JSON out of LLMs: JSON mode vs. structured outputs vs. strict tool use, the JSON Schema subset providers accept, Pydantic patterns, how constrained...

    AI · cheatsheets AI LLMs structured outputs JSON Schema Pydantic constrained decoding Python English
  • 2025-12-17

    Agent Skills Cheatsheet: Packaging Know-how for AI Agents

    A practical cheatsheet on Anthropic's Agent Skills: what a skill is, the SKILL.md format and its frontmatter rules, progressive disclosure, bundled scripts and resources, where skills run (Claude...

    AI · cheatsheets AI agents Agent Skills Claude Code Anthropic English
Page 1 of 3 Next →

Nothing you read here should be considered advice or recommendation. Everything is purely for informational purposes.

Atom Feed