The Augmented Dev · Archive

All articles

Dynamics 365, Power Platform, AI, system design, and web development — filter by theme or search across every post.

12 of 325 articles tagged ai

Jun 25, 20267 min read

Evaluating LLM Applications: Getting Past 'It Looks Good to Me'

Shipping LLM features on vibes works until a prompt tweak silently breaks ten other cases. Here is how to build evals that catch regressions before your users do.

ai llm tutorial

Jun 23, 20267 min read

Getting Structured Output From an LLM Without the Heartbreak

Asking a model to 'return JSON' and parsing the result is how you get 3 a.m. pages. Tool schemas, constrained decoding, and validation turn a probabilistic text generator into a reliable API.

ai llm tutorial

Jun 21, 20267 min read

Chunking Strategies for RAG: Where Retrieval Quality Is Won or Lost

Most RAG systems that retrieve bad context aren't failing at embeddings or reranking — they're failing at chunking. How you split documents quietly decides what your model can ever find.

ai llm tutorial

Apr 25, 202610 min read

An MCP Server for Dynamics 365 Finance and Operations: Natural-Language Access to ERP

How to expose Dynamics 365 Finance and Operations to Claude through MCP — the architecture, the data entity choices, the auth model, and the operations that should never be one prompt away.

dynamics-365 ai mcp

Apr 23, 20266 min read

Claude Code Hooks: Automating Repo Guardrails Without Pre-Commit Fatigue

Use Claude Code hooks to enforce policy at the moment actions happen — before edits, before tool calls, on session start — without relying on pre-commit hooks everyone learns to bypass.

ai claude tutorial

Apr 21, 20267 min read

Building Your First MCP Server in Python: A Hands-On Walkthrough

From zero to a working Model Context Protocol server in about 100 lines — tools, resources, a local client test, and the traps that will bite you on day one.

mcp ai claude

Apr 18, 20267 min read

Prompt Caching with Claude: What It Saves, Where It Fails, and How to Set It Up in Production

A precise look at Claude's prompt caching — how the cache hit math actually works, the 5-minute and 1-hour TTL variants, and the subtle mistakes that silently disable it.

claude ai tutorial

Apr 15, 20268 min read

Tool Use with Claude: Parallel Calls, Retries, and the Patterns That Survive Production

The tool-use features of the Claude API look straightforward in the docs. These are the production patterns that separate a demo from a system that handles real traffic — parallel tool calls, retry loops, error recovery, and tool_choice tactics.

claude ai tutorial

Apr 12, 20267 min read

Claude Agent SDK vs Direct API: When to Reach for Each

The Claude Agent SDK is the fastest path to a capable coding-style agent. The raw messages API is the fastest path to understanding what your agent is doing. Here's when each is the right tool.

claude ai tutorial

Apr 9, 20268 min read

Designing a Production-Ready RAG System: What Actually Matters

Retrieval-augmented generation demos look great. Production RAG is a different engineering problem — chunking, hybrid retrieval, reranking, evaluation, and the failure modes nobody mentions at conferences.

system-design ai llm

Apr 4, 20268 min read

Vector Databases Compared: pgvector, Qdrant, Pinecone, and When You Don't Need Any

A practical comparison of the vector databases people actually deploy in 2026 — and an honest look at when a vector database is the wrong tool for the job.

system-design ai tutorial

Mar 25, 20268 min read

Event-Driven Architecture for LLM Pipelines: Queues, Retries, and the Cost of Synchronous Chains

LLM-powered pipelines break in the same ways old monoliths did — when you stack synchronous calls. Queues, events, and the patterns that make a six-step AI pipeline survive a partial outage.

system-design ai llm

Newsletter

New posts, straight to your inbox

One email per post. No spam, no tracking pixels, unsubscribe anytime.