There are broadly two types of people when it comes to someone like Donald Trump. Trump constantly promotes himself. He doesn't seem particularly embarrassed by self-promotion. He can say, in effect: "I'm the best. I'm successful. I'm great." Most people, at least internally, would probably have a reaction like: That sounds very arrogant. How could … Continue reading Why Some People Love the Trump Type and Others Can’t Stand It

Context degradation is real. This session started with a long summary of prior work which is useful for continuity but it also means: stale information gets treated as current, AI check memory which could be outdated. The more context I carry, the harder it is to distinguish what's verified vs what's just noted. lose track of user's question … Continue reading AI Degradation in Long Contextual Conversations

Every session starts stateless; the MCP server provides excellent tools, but the real domain expert agent needs to know how to use these tools proficiently and intelligently. Additionally, they must be conscious of token consumption, as it is not abundant and time is critical. I don't want to waste a lot of time and money … Continue reading The Approach to Build Domain Expert Agent

An artifact is a persistent, addressable object—such as a dataset, file, report, or HTML output—stored outside the LLM's conversation context and referenced by an ID. When creating agents for extensive data-heavy tasks, it quickly becomes apparent that the large amounts of data displayed in the conversation field are unwieldy and unnecessary. Users only need to … Continue reading Use Artifacts in the Agents

I have an idea to let MedGemma become the specialized local engine, MCP becomes the interface, and Claude/ChatGPT becomes the high-level reasoning/orchestration layer. The flow would be Claude Desktop sends a tool call → the MCP server builds a prompt → llama-server runs MedGemma inference on CPU → structured JSON comes back to Claude. Deploying … Continue reading Deploying MedGamma Mini Model Locally and Create an MCP Server

1. Standard OAuth 2.1 (MCP spec-compliant) Who uses it: Remote/hosted MCP servers (e.g., a server on Fly.io, Cloudflare, etc.) How: Full OAuth 2.1 flow — the MCP server is a resource server, a separate auth server (Auth0, Okta, Keycloak, etc.) issues tokens. Client discovers auth server via /.well-known/oauth-protected-resource, opens browser with PKCE, exchanges authorization code for access token. Example: An MCP … Continue reading The 4 Common OAuth/auth Patterns for MCP Servers

An AI agent can reason, write code, and call tools. But the web is where most real-world information lives. So how does an agent actually use a web page? The answer has evolved through three distinct generations, and which one your agent uses determines what it can and can't do. Generation 1: Fetch and Parse The simplest approach. The agent makes an HTTP request, … Continue reading How AI Agents Browse the Web: From Fetch to Click

Context and Memory Management are difference: Context management = per-turn. "What fits in this prompt right now?" Deals with the model's finite window this request. Memory management = cross-turn/cross-session. "What should the agent remember for later?" Deals with persistence beyond the current request. Context management keeps the prompt usable now; memory management keeps knowledge alive later; summarization is the bridge where they overlap. why … Continue reading How Coding Agents Manage Context

Coding agents primarily utilize file-based rules along with in-session compaction; however, some agents like Claude Code and Cursor also depend on embedding-based cross-session memory. Although they can occasionally feature self-editing blocks, this approach is generally excessive unless the agent operates in long-lived sessions. First, same codes of in-session approach — no persistence, no embeddings. It's what most … Continue reading How Coding Agents Manage Memory

An AI court coordinator watches your existing booking calendar (e.g., CourtReserve), compares real-time headcounts against ideal capacity for each session, and proactively messages the right group of players — organized by skill level — when a session needs more players or when a full session's waitlist could be redirected to an open slot elsewhere. It … Continue reading How an AI Coordinator Agent Can Fix Pickleball Court Utilization