The NHS Bet on AI Triage Is Bigger Than Anyone Admits
A single GP surgery in Surrey cut patient waiting times by 73% in four months. Not by hiring more doctors. Not by extending hours. By letting an AI decide...
Swarm Signal - AI Research for People Who Build
Technical AI research, explained clearly for researchers, builders, and anyone trying to understand what actually matters.
AI Agents in Legal: What Works, What Fails, and What the Sanctions Data Actually Shows
In June 2023, attorneys Steven Schwartz and Peter LoDuca submitted a brief in a federal case citing six cases that did not exist. ChatGPT had invented them. When the opposing party asked for copies, the attorneys submitted fabricated pages. A judge sanctioned them $5,000 and required them to pers...
When NOT to Use an Agent: The Production Data That Should Change Your Default
Gartner predicts over 40% of agentic AI projects will be canceled by end of 2027 , not because AI doesn't work, but because escalating costs, unclear business value, and inadequate risk controls compound faster in agent architectures than in simpler ones. The vendor that profits most from selling...
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...
Anthropic's 186-Deal Experiment Shows What the Agent Economy Actually Looks Like
In December 2025, Anthropic gave 69 employees $100 each and told them to let Claude agents trade on their behalf. The agents bought and sold real items (services, digital goods, subscriptions) listed by other employees in a controlled marketplace. The experiment ran for several weeks. When it end...
Agent Memory Architecture: Long-Term, Episodic, and Semantic Memory for AI Agents
After a year of ad-hoc RAG solutions, agent memory is becoming a proper engineering discipline. Four independent research efforts outline budget tiers, shared memory banks, empirical grounding, and temporal awareness: the building blocks of a real memory architecture.
Small Language Model Agents: The 2026 Practical Guide to Sub-10B Deployments
In February 2025, using a small model as an autonomous agent felt like a compromise: you got cheaper inference but accepted meaningful capability loss on planning, tool selection, and multi-step reasoning. That trade-off calculus has flipped.
How to Build Agent Evals That Catch Real Failures
Standard LLM benchmarks miss the failures that actually hurt in production. Here's how to build an evaluation system for agents that catches cascading errors, trajectory drift, and policy violations before they reach users.
Why AI Agent Deployments Fail — And What the Survivors Do Differently
Agent deployments fail for recurring reasons: weak problem framing, brittle long-horizon performance, poor observability, and missing human-in-the-loop controls.
Multi-Agent Systems Are Booming — But Real-Work Benchmarks Still Bite
Multi-agent workflows are growing fast, but APEX-Agents, AgentRx, Databricks, and Gartner show a gap between adoption, task success, and production readiness.
External tools
Execution tooling is separate
Swarm Signal keeps the research layer. For reusable trackers and production templates, use BoredTools.