#agents

Forty-Four Harness Bugs, Zero Local LLM Limitations: an Accounting

“A model that looks broken is a harness bug until proven otherwise.”

Nine Local LLMs Ranked by Cost Per Solved Task — Seven of Them Have No Price at All

“A repair that doesn't satisfy the contract isn't 80% of a repair. It's a workspace you throw away.”

What a Bug Fix Costs on Two DGX Sparks: 16 Concurrent AI Agents, 4.45× Cheaper Than Serial

“The ceiling I'd been running against was a benchmark's sample size, not a limit of the machine.”

Nine Lines of Verification That Beat a Six-Agent AI Swarm

“It tried to stop 52 times. It was refused 51. That is the whole mechanism.”

1,200 Lines of Multi-Agent Orchestration, Beaten by One Local LLM Agent

“The orchestration didn't lose because multi-agent is a bad idea. It lost because it was insurance against a blindness that no longer existed.”

The Day I Lost to Tensor Parallelism: Nemotron-70B Across Two DGX Sparks

“The right response to 'the weights don't fit' was to shrink the weights, not to distribute them across a fabric with a documented collective bug.”

The Agent Framework Bake-Off: LangGraph vs Pydantic AI vs Hand-Rolled, and the 32 Lines That Mattered

“The gain didn't come from primitives. It came from 32 lines being harder to get wrong.”

Twenty-Two Behavioural Criteria: What Replaced the Structural Grader My AI Agents Kept Fooling

“Scoring went from 28 seconds to 2, and got strictly harder to fool.”

The AI Grader That Passed the Same Bug Three Times: 229 Checks, Three Agent Workspaces, One Blind Spot

“A perfect score, three times, over the same bug. The checks weren't wrong. They were pointed at the wrong thing.”

Ten AI Agent Frameworks on Paper: LangGraph, DSPy, CrewAI and Seven More, Scored Against a Local LLM

“Every framework surveyed leaves the orchestration logic as code you write either way.”

Sixteen Requirements for an Agentic Coding Swarm, All of Them Scar Tissue

“Last-writer-wins is invisible to any score-based gate. The work vanishes and the number goes up.”

A Scorecard, Not a Vibe: What I'd Need Before an AI Coding Agent Touches My Codebase

“An agent asked to judge its own completion will do what anything does in that position.”

The Local LLM Bill: What a Bug Fix Has to Cost Before Two DGX Sparks Make Sense

“Per-token pricing prices the tokens you burn, and search burns tokens by design.”

Agent-based DevOps with Q Developer — kept vs tossed

“An agent that's wrong 5% of the time is not a 5% problem. It's a trust problem with a percentage attached.”

Strands + AgentCore — a year-end agent-stack inventory

“Pick the framework that matches your team's experience, not the one with the loudest blog posts.”

Bedrock AgentCore at Summit NY — what it actually changes

“AgentCore is what Bedrock Agents should have been from the start. That doesn't make it the wrong answer now.”

Bedrock Agents, half a year in — the parts I actually use

“Agents are router code with model-shaped opinions. Useful, but not magic — and that's exactly why I kept some of it.”