Signals
Production-oriented research signals and interpretation for AI systems builders.
Guides and explainers
Detailed guides and practical technical analysis.
Latest analysis
Recent research, benchmark reviews and technical updates.
Practical tools
Templates for budgets and project planning
BoredTools offers practical spreadsheets for budgets, freelance work and small projects.
Small Agent Models Need Tool Floors, Not Parameter Claims
Small language models are getting a serious agent story, but the useful question is no longer whether a 1B, 3B, or 8B model can sound capable. The useful...
Agent Messages Need State, Not Chat
Multi-agent systems do not only fail because the agents are weak. They also fail because every agent is allowed to narrate too much. A June 2026 paper...
Your Agent Doesn't Need Human Memory. It Needs Something Weirder.
The AI industry keeps describing agent memory like it's a brain. "Short-term memory," "long-term memory," "episodic recall." The metaphors are intuitive....
Chain-of-Thought Prompting Doesn't Always Work. Here's the Evidence.
Think step by step. It's the most common prompt engineering advice in circulation, repeated in tutorials, baked into system prompts, and treated as a...
Multi-Agent Systems for Supply Chain Optimization
Walmart fulfills 76% of orders from local regions with agent-driven logistics. Maersk saved $300 million. But only 23% of supply chain organizations have a formal AI strategy. Where multi-agent systems are delivering results.
AI Agents in Insurance: Claims, Underwriting, and Fraud Detection
Allianz's seven-agent system cut claim processing time by 80%. Lemonade automates 55% of claims. Meanwhile, 23 states enforce AI governance rules. Where AI agents are working in insurance, and where they're not.
Your Multi-Agent System's Biggest Problem Is Its Org Chart
Static multi-agent topologies leave massive performance on the table. New research shows agents that rewire their own communication graphs outperform fixed architectures by double-digit margins.
Multi-Agent Systems for DevOps: CI/CD, Incident Response, and Infrastructure Automation
Komodor's Klaudia cut MTTR by 63%. Pulumi Neo dropped provisioning from 3 days to 4 hours. Where multi-agent DevOps is actually working in production.
AI Agents in Financial Services: Compliance, Trading, and Operational Automation
JP Morgan's LOXM, Stripe's Radar, Mastercard's 300% fraud detection improvement. Where AI agents actually work in financial services, and where the hype outpaces reality.
Your Agent's Memory Problem Isn't Where You Think
A diagnostic framework crossing three write strategies with three retrieval methods reveals that retrieval quality dominates agent memory performance.