Articles

RAG quality starts before retrieval. A secure ingestion guide for PDFs, OCR, metadata, permissions, source freshness, deletion, malware risk, and operational ownership.

A company knowledge assistant is only safe if retrieval respects permissions. How to design RAG source boundaries, ACL filtering, document ownership, logging, stale-source handling, and refusal behavior.

AI systems usually fail in predictable ways: hallucination, stale context, sycophancy, prompt injection, unsafe tool use, schema drift, and weak fallbacks. A production failure-mode register for teams shipping real workflows.

Prompt injection is a permanent LLM security class, not a prompt-writing mistake. A production guide to threat models, data boundaries, tool permissions, regression tests, monitoring, and incident response.

Computer use and browser agents have demos that go viral. Production deployments at scale have a different shape — narrow scoping, heavy guardrails, careful UX. The patterns that work, the failures we keep seeing, and the honest economics.

Agents need memory beyond the context window. Long-term memory architecture — what to store, when to retrieve, how to forget — determines whether agents feel like they 'know' you or start fresh every conversation. The patterns and the production trade-offs.

1M-token context windows exist, but quality degrades long before that limit. Context engineering is the discipline of using context windows effectively — what to include, what to summarize, what to retrieve fresh, and the patterns that keep quality high as context grows.

The agent framework landscape in 2026 is more mature but no clearer. LangGraph, CrewAI, Pydantic AI, OpenAI Agents SDK, and direct API — each fits some teams and projects, none fits all. A honest comparison and a decision framework.

The most common production agent failure is infinite or pseudo-infinite loops — agents that retry, branch, and burn through tokens without making progress. The architectural patterns that prevent this and produce agents that finish, even on hard tasks.

LoRA fine-tuning has become accessible — you can run real fine-tunes on a laptop or rent a GPU for an hour. The patterns that work, the cases where fine-tuning beats RAG, and a practical end-to-end workflow from data prep to deployment.

Classic chunk-based RAG has limits. Graph RAG, agentic RAG, and long-context RAG each break those limits in different ways. When each is the right tool, how they actually work, and the production trade-offs that matter.

A production RAG pipeline is six stages, each with specific patterns that determine quality. The architecture, the choices at each stage, and the iterative evaluation discipline that distinguishes RAG that works from RAG that disappoints.

Most MCP tools we see are technically correct and practically useless. LLMs ignore them, misuse them, or call them in unhelpful ways. The principles for designing tools LLMs adopt naturally, with examples of common failures and their fixes.

Building a production Model Context Protocol server requires more than wiring up a few tools. The patterns for schema design, auth, error handling, streaming, observability, and the production realities that make MCP servers useful at scale.

LLM applications fail in unique ways that traditional observability misses. The patterns for tracing multi-step flows, tracking costs that vary 100x per call, monitoring quality drift, and debugging hallucinations at production scale.

Most eval suites look impressive but miss real regressions. Building evals that catch what matters requires careful dataset construction, sensitive metrics, judge calibration, and a culture of trust. The patterns from teams that get this right.

Production prompts are not 'tell the AI what you want'. They are a layered system — stable instructions, dynamic context, per-call variables — managed like code. The architecture, the patterns, and the discipline that distinguishes production from prototype.

Structured outputs and function calling are the bridge from 'LLM that generates text' to 'system that does work'. In production, the patterns that matter are about schemas, error handling, idempotency, and graceful degradation — not just JSON mode.

Using one model for everything is the rookie move. Production AI systems route different requests to different models — and save 60-90% on cost while improving quality. The patterns, the routing logic, and the trade-offs.

Browser agents and computer-use AI promise to operate your computer the way you do. The reality in 2026 is more useful and more limited than the demos suggest. A grounded guide to what works, what doesn't, and where to apply them.

An automated daily briefing or newsletter that arrives in your inbox, with content actually worth reading, is one of the highest-leverage AI builds. The architecture, the prompts, and the discipline that makes it sustainable.

Running AI locally has matured. With Ollama or LM Studio and a modern Mac, you can run capable models offline, free, and private. What works, what doesn't, and the use cases that actually benefit.

Non-developers can now build real software with AI. A practical guide to using Cursor and Claude Code as a non-engineer — what's realistic, what's not, and the discipline that separates useful tools from broken ones.

MCP is the new standard for connecting AI to your tools. You don't need to write one to benefit. A non-engineer's guide to what MCP is, which servers to install, and what becomes possible once your AI can actually act.