How AI Agent Memory Works
Separate model context, task state and saved preferences. Use Python and SQLite to test consent, scoped retrieval, stale updates, expiry and deletion.
Ideas you can put to work
Articles
Explore software, AI, and the systems behind everyday applications.
Practical explanations, examples, and things to try.
1–17 of 17 articles
Newest firstBuild Your First AI Agent
Build a bounded support assistant with one read-only tool, a reviewable trace and clear handoffs. Run fixtures first, then connect an optional model.
Connect an AI Agent to an API
Build a read-only HTTP adapter with validated inputs, controlled errors and bounded retries. Test a local API without model credentials or real secrets.
Build Your First MCP Server
Build a local read-only MCP glossary server with the official Python SDK. Test discovery, valid calls, rejected inputs and subprocess shutdown.
MCP Tools, Resources, and Prompts
Expose one documentation service as a resource, search tool and reusable prompt. Run discovery and use locally, then check host support and access boundaries.
Agent Skills vs MCP vs Tools
Follow a documentation review to separate reusable instructions, MCP connectivity and executable tools, with examples that do not need all three.
API vs MCP: What's the Difference?
Compare a direct HTTP API with an MCP adapter through the same local weather lookup, including discovery, schemas, access boundaries and maintenance costs.
How to Write an Agent Skill
Build a focused setup-guide review skill, validate its files, and design positive, negative, and failure-feedback tests without granting extra permissions.
What Are Agent Skills?
Understand SKILL.md packages, staged loading, prompts, tools, and permission boundaries through a small review skill and runnable Python helper.
How AI Agents Use Tools
Build a local read-only order dispatcher to learn tool requests, argument validation, user permissions, controlled errors, and timeouts.
AI Agents vs Chatbots vs Workflows
Compare chatbots, workflows, and AI agents through the same support ticket, with control flow, costs, failure cases, and a practical decision guide.
What Is an AI Agent?
Follow an AI agent through support-ticket triage, run a bounded Python simulation, and learn when a script or workflow is the better choice.
Add MCP Servers in Codex, Claude Code, and Gemini
Learn what MCP (Model Context Protocol) is, why it’s useful, and how to add MCP servers (Notion, Sentry, Context7) in OpenAI Codex, Claude Code, and Gemini CLI.
Securing Your MCP Server: Auth, Rate Limiting, and Input Validation
Learn how to secure your MCP (Model Context Protocol) server using FastAPI. Implement authentication, rate limiting, and input validation to protect your AI workflows from misuse, abuse, or injection.
Understanding ChatGPT Models: GPT-3.5, GPT-4, GPT-4-turbo, and Beyond
Explore the different ChatGPT models offered by OpenAI, including GPT-3.5, GPT-4, GPT-4-turbo, GPT-4.1, GPT-4.5, and GPT-4o. Learn how they differ in capabilities, performance, context window, cost, and use cases.
How to Build and Register Plugins in an MCP Server (OpenAI & YouTube API Examples)
Learn how to build modular, context-aware plugins for your Model Context Protocol (MCP) server. Includes step-by-step examples for OpenAI GPT-based summarization and YouTube metadata extraction.
What is an MCP (Model Context Protocol) Server? A Complete Guide for AI Engineers
Discover the power of the Model Context Protocol (MCP) Server — an innovative way to orchestrate AI models and tools with context-awareness. Learn how it works, why it matters, and how to build your own MCP system.