How to Evaluate LLM Agents: 5 Patterns That Catch Failures
Eval shortcuts fail on honesty-trained models. Five assertion patterns that survived production.
July 11, 2026 · 12 min
Latest · Post
Why Multi-Column PDFs Scramble Reading Order in RAG
Fixing two-column extraction broke academic title pages. The benchmark never noticed.
Latest — recent dispatches
View all →
RAG for AI Agents: 6 Decisions That Make or Break Retrieval
Six retrieval decisions for agent RAG, each settled by a benchmark, not a vibe. Defaults included.
July 10, 2026 · 10 min
How One Search Change Eliminated an Entire Agent Step
pdf_search went from a pivot tool to a terminal tool. The thesis still holds.
July 04, 2026 · 8 min
Most read guides — reader favorites
View archive →
How to Ship an MCP Server to Production (Authentication, Safety, and What Breaks)
MCP tutorials stop at tool integration. The real work is auth, guardrails, and untrusted data.
April 11, 2026 · 7 min
How Claude Code Actually Reads PDFs: Lessons from Building an MCP Server
Tool boundaries shape agent behavior more than prompts. What I learned shipping pdf-mcp.
April 04, 2026 · 10 min
FastMCP 3.0 Tutorial: A Real MCP Server in Python, 100 Lines
Tools, resources, prompts, SQLite persistence, in-process testing. Under 100 lines of Python.
February 22, 2026 · 9 min
AI Agents Fail With 200 OK: 5 Error Handling Patterns
Circuit breakers, validation gates, sagas, budget guards. Five patterns I use in production.
February 12, 2026 · 10 min
pdf-mcp: How to Handle Large PDFs in Claude Code with MCP
Claude's limits: 100 pages visual, 30MB per file. Hit them? pdf-mcp reads in chunks.
January 31, 2026 · 10 min
Parallel Processing in AWS Lambda with Python: What Actually Works (And What Doesn't)
What threading, multiprocessing, and async actually do inside a Lambda function. Benchmarked.
January 17, 2026 · 4 min
AI Agent API Access: Why Full Permissions Are a Security Risk
Three MCP design patterns from giving an agent full API access. And watching it go wrong.
December 24, 2025 · 4 min
How to Connect a Legacy System to AI Agents Using MCP
How to wrap a legacy Redmine API with MCP. No rewriting, no destabilizing anything.
May 27, 2025 · 6 min
More Articles
01
How to Evaluate an MCP Server With an LLM: 17 Bugs Found and Fixed
02
How AI Agents Should Read PDFs: 5 Patterns That Survived Production
03
How I Built a Serverless Newsletter on AWS for Under $1/Month
04
MCP Tool Sprawl: How I Cut 69 Tools to 43 With a Decorator
05
How to Deploy a Python MCP Server: Remote HTTP, Auth, and Docker
Highlight Editor's pick →
Section-Level RAG: Why BM25 Beat Hybrid Search in My Benchmark
Hybrid wins at page grain. BM25 wins at section grain. Granularity decides.
June 06, 2026 · 10 min
Section Chunking vs Page Chunking for AI Agents: ~6 Fewer Tool Calls Per PDF Query
Page-mode PDF search costs 2 to 6 extra tool calls per query depending on the document. Section-aware search delivers...
May 30, 2026 · 10 min
The Production AI Agent Playbook: 8 Disciplines for Reliable LLM Systems
Architecture, error handling, monitoring, security, cost control. 8 disciplines production agents need.
March 11, 2026 · 10 min
MCP Server Security: 8 Vulnerabilities I Found and Fixed
I audited my MCP server at 3,000 downloads and found 8 vulnerabilities. Every fix is here.
February 25, 2026 · 7 min
Why AI Agents Fail in Production (And How to Fix Them)
Five lessons from real failures: structured output, constraints over roles, architecture over model.
November 29, 2025 · 4 min
AWS Global to China S3 Sync: A Serverless Solution
Event-driven sync across the China boundary. No VPN, no persistent infrastructure.
April 12, 2025 · 5 min