Archive

Aerial view of a braided glacial river: independent channels merging into one flow, the way per-document rankings fuse into one cross-corpus result. Ranks survive that merge; raw BM25 scores do not.

rag· ai-agents· mcp· llm

Cross-Document Retrieval for AI Agents Without a Vector Database

BM25 scores don't compare across documents. Ranks do. Fusing 100 PDFs into one hit list.

August 15, 2026 · 12 min

Someone standing at a wall of colored sticky notes, moving one by hand: the triage board as it looks before an agent can work it.

mcp· ai-agents· llm· production-systems

Redmine MCP Server: Give AI Agents Live Project Data

An open-source MCP server for Redmine. 51 tools, OAuth2, read-only mode, and a live triage board.

August 08, 2026 · 8 min

A library wall packed with books of every size and color: a working knowledge base organized by nothing more than which shelf each volume sits on and what its spine says.

mcp· ai-agents· rag· llm

A Knowledge Base Is Just a Folder

No pipeline, no vector store. Topic folders, a warm habit, a generated catalog, honest coverage.

August 01, 2026 · 10 min

Bundled black conduit pipes fanning out from a single trunk up the side of a brick building, the infrastructure plumbing of a fetch-extract pipeline.

ai-agents· llm· blueclaw· python

AI Agent Cloudflare 403: Two Libraries That Fix It and Cut Tokens 90%

Two Python libraries fix the 403 and the 80k-token HTML at the same time.

July 25, 2026 · 9 min

A person on a bench reads a multi-column newspaper that hides their face, standing for a reader who cannot see how the column layout is being scrambled.

rag· ai-agents· llm

Why Multi-Column PDFs Scramble Reading Order in RAG

Fixing two-column extraction broke academic title pages. The benchmark never noticed.

July 18, 2026 · 8 min

Wooden Pinocchio puppet collapsed on its back, limbs splayed: the eval that fell over when it stood on fabricated history.

ai-agents· llm· observability· blueclaw

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

Empty station hall at dawn, tracks running out toward the horizon: by the time the train leaves, every switch that matters has already been set.

rag· ai-agents· llm

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

A search result returning a single focused paragraph instead of a noisy text window.

mcp· ai-agents· python· llm

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

Two people reviewing handwritten notes between two laptops: the collaborative review loop between developer and LLM evaluator.

mcp· ai-agents· production-systems· python

How to Evaluate an MCP Server With an LLM: 17 Bugs Found and Fixed

Your tools work. That doesn't mean an agent can use them. Eight rounds. Seventeen bugs.

June 27, 2026 · 12 min

A reader's finger resting on a single line of an open book, standing for an agent locating the one passage it needs instead of reading every page.

ai-agents· mcp· rag· llm

How AI Agents Should Read PDFs: 5 Patterns That Survived Production

How agents should navigate documents at production scale, from 39,000+ downloads of one MCP server.

June 24, 2026 · 11 min

aws· serverless· python

How I Built a Serverless Newsletter on AWS for Under $1/Month

Seven Lambdas, two SQS queues, one DynamoDB table. SES for sending. No per-subscriber fee.

June 20, 2026 · 10 min

A 1940s switchboard operator routing tangled cables on a wooden patch panel: too many wires to plug, too few hands to plug them.

mcp· python· ai-agents· production-systems

MCP Tool Sprawl: How I Cut 69 Tools to 43 With a Decorator

Why more MCP tools make agents worse, and the pattern that fixes the surface.

June 13, 2026 · 8 min

Latest — recent dispatches