§ 001 / TOPIC
Agentguard
59 posts on agentguard, guides and lab notes from real runs on hardware we own. New posts land here automatically. Start anywhere, or grab the copy-paste prompts that ship with them.
- 5 min read
GPU Prices Up 48% in Two Months. I Run LLMs in My Garage.
Blackwell rental hit $4.08/hr. CoreWeave raised prices 20%. Anthropic restricted their newest model to 40 orgs. Meanwhile, consumer GPUs are sitting idle.
- 5 min read
When to Replace Your AI Agent With a Script
Will Larson says agents should be scaffolding, not permanent infrastructure. I run 12 agents overnight. Here's what I kept as agents and what I converted to code.
- 5 min read
Your AI Agent's MCP Server Is a Security Hole
1 in 35 GenAI prompts carries high risk of data leakage. MCP makes the attack surface worse. Here's what builders need to know.
- 6 min read
Anthropic's Advisor Tool Is the Cost-Split Pattern You Should Already Be Running
Anthropic shipped a pattern where a cheap model runs the loop and escalates to Opus only when it needs to. The pattern works on any two-model setup. Here is the math and the playbook.
- 7 min read
We Built Martin Fowler's Feedback Flywheel Before He Published It
Martin Fowler published a pattern for turning individual AI interactions into collective improvement. We had already built it. Here is how our 12-agent vault system maps to his four signal types.
- 7 min read
AI Agent Safety: Findings from Mythos, Apollo, and Payne
Studies show agent behaviors under specific test setups. These conditions and limits inform how teams review agent workflows without predicting production runs.
- 5 min read
Meta Token Reports: 3 Agent Budget Controls
Reports of Meta's internal token leaderboard show why usage counts need outcome checks. Three runtime controls for your own instrumented agent loops.
- 6 min read
Study Found 9 Malicious Routers in 428 Tested Proxies
An April 2026 study examined 428 LLM routers and found malicious injection. Proxies can inspect sent requests even when transport encryption protects the link.
- 3 min read
AI Chose Nukes 95% of the Time. Here's What That Means for Your Agents.
Three AI safety papers came out this week. Reading them back to back was jarring. If you run agents in production, this is worth 5 minutes.
- 8 min read
Applying Rahul Garg's Feedback Flywheel to Agent Workflows
Rahul Garg described a feedback flywheel on Martin Fowler's site. Retained failures and shared instructions can inform tested updates to an agent workflow.
- 8 min read
Stop Runaway LLM Spend: AI Agent Cost Control (Python)
One bad loop and an AI agent burned $200 in minutes. AgentGuard is a Python SDK that enforces hard cost limits at runtime, here is how to ship it.
The AI agent build notes
Real costs, real tools, no fluff. One evidence-backed note on Friday when there is something worth sharing.
Get the requested artifact now, then at most one evidence-backed Local AI Lab Note on Friday when there is something worth sharing. One-click unsubscribe. No sponsored placements. Privacy.