Most Popular
3,528 documents
📎ComfyUI-CrewAI
Integrates CrewAI's multi-agent framework into ComfyUI to automate and refine prompt creation for image generation workflows.
DSGVO/GDPR Compliance Guide
Defines a DSGVO/GDPR breach response procedure with notification timelines, documentation templates, and regulatory contacts for German federal states.
Contents
Serves as the homepage for a curated list of text-to-image generation papers, organised by year, conference, and research direction.
Chapter 37 — Agents & Tool Use
Explains the agent loop, function calling, MCP, coding and computer use agents, ReAct pattern, multi-agent systems, and common challenges.
Evaluation and Testing LLM Systems
Lays out a four-layer evaluation stack for LLM systems, from automated assertions through human review, with concrete testing practices.
Product Requirements Document: B2B SaaS Landing Page
Defines 12 page sections, a visual style guide, and technical requirements for a B2B SaaS landing page.
PROMPTS.md — Writing LLM Prompt Templates
Documents five Jinja2 prompt templates for three-pass LLM analysis of interview transcripts, with output schemas and editorial guidance.
Neovim Setup for Initrd/Netboot Development on Kali Linux
Defines a Neovim configuration for debugging and editing initrd, netboot, and systemd files in terminal-only environments like serial consoles and rescue shells.
17. Evaluation Frameworks
title: 17. Evaluation Frameworks
Message Chunking for MCP stdio Transport
Explains macOS 64KB pipe write limit and provides a chunking layer for MCP stdio transport that splits and reassembles large messages transparently.
绘制对比图片 KITTI
Documents the topic remapping and data flow needed to connect Fast-LIO2 frontend with SC-PGO backend for KITTI evaluation.
AutoDoc Demo: Step-by-Step Walkthrough
Walks through setting up AutoDoc in a target repository and triggering automated documentation generation from code changes.
Kiro Base System Prompt
Defines the identity, capabilities, response style, and platform-specific commands for an AI coding assistant named Kiro.
llm-hallucination-survey
Curates a structured bibliography of 100+ papers on LLM hallucination, organised by evaluation, source, and mitigation.
Aruba AP IPv6 Deployment
Documents four IPv6-only network designs for Aruba AP-to-controller discovery using DHCPv6, SLAAC, and DNS.
Logging & Evals
Documents a trigger-based logging system, cost tracking, token analytics, and a separate evals dashboard for reviewing LLM interactions.
VPM Package Template
Starter for making Packages, including automation for building and publishing them.
Chaos Testing (GameDay) Guide
Structures quarterly and monthly chaos engineering exercises with defined roles, scenarios, and post-event reviews to validate system resilience and team response.
Glossary
Collects advanced deep learning terms not covered in introductory glossaries, with brief definitions and links to papers.
When "Better" Prompts Hurt: Evaluation-Driven Iteration for LLM Applications
Presents an evaluation-driven workflow (Define-Test-Diagnose-Fix) for LLM applications and demonstrates that generic prompt improvements can degrade task-specific performance.
Jasper AI: The Enterprise Content Marketing Platform Powered by AI
Introduces Jasper AI as an enterprise content marketing platform, covering its features, pricing, workflows, and comparison with alternatives.
Content Marketing Strategist
Guides founders through building a content marketing strategy with pillars, editorial calendar, distribution plan, SEO, and repurposing playbook.
🔥 FIRE — Freedom Intelligent Routing Engine
Routes customer support tickets through LLM classification, geocoding, and a cascade of business rules to assign each to the best manager.
AI Writing App - Template Engine Documentation
Documents a template engine for AI writing apps, covering 7 template types, architecture, and how to add new ones.