How LLM Training, Fine-Tuning, RAG, and Agents Differ
The cleanest way to reason about LLM options is to ask whether you are changing weights, runtime context, or external actions. This report gives a practical selection guide.
#mcp
MCP and Agent Skills for Browser E2E Testing
A practical comparison of browser E2E automation options for agents, focused on logged-in browser sessions, reproducibility, CI fit, and adoption strategy.
AI agent memory platform created with Graphiti and MCP
We will organize the design, implementation decision, and alternative services of AI agent memory infrastructure using Graphiti and MCP from a deployment perspective.
OAuth 2.1 PKCE Flow and MCP Authentication Authorization Practical Guide
OAuth 2.1 Organize the authentication and authorization flow of PKCE, OIDC, MCP server, and Claude-based clients for practical use.
AI/LLM/Ontology/Organizational Memory
We will organize LLM, symbolic grounding, Ontology, Graphiti, and MCP as materials for making decisions about the utilization of organizational knowledge.