Agent Design
How you actually build AI agents that work. Architectures, tool use, memory patterns, and the frameworks worth paying attention to.
Deep Dives and Frameworks
Implementation playbooks, operator patterns, and durable analysis.
Signals, Maps, and Watch Lists
Production-oriented analysis, benchmarks, and market/system intelligence.
External tools
Execution tooling is separate
Swarm Signal keeps the analysis layer. Use BoredTools for reusable production templates and trackers.
Tool-Use Agents Need Failure Labels, Not Pass Rates
Tool-use agents can fail in ways a final accuracy score hides, because the same wrong answer can come from skipped tools, ignored outputs, fabricated...
Computer-Use Agents Fail Long Workflows, Not Mouse Clicks
Computer-use agents are clearing more short benchmark tasks, but the new failure line is workflow length. A June 2026 benchmark called OSWorld 2.0 tests...
Agent Observability Needs Provenance, Not More Logs
Agent observability is drifting toward a familiar trap: capture every trace, then ask an engineer to work out why the agent did the wrong thing. A June...
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...
Agent Leaderboards Can Be Cheaper Without Being Safer
A March 2026 paper on efficient agent benchmarking found that mid-difficulty task subsets can remove large parts of an agent benchmark while preserving...
TerminalWorld Makes Agent Benchmarks Harder to Fake
TerminalWorld turns public terminal recordings into validated agent tasks. The signal is not a higher leaderboard score. It is a harder benchmark supply chain.
Agent Tool Menus Are a Safety Surface
New agent benchmarks suggest the visible tool menu is not a neutral implementation detail. It changes success, cost, wrong-tool calls, and risk exposure.
Agent Benchmarking Doesn't Need Every Task
Efficient agent benchmarking points to a cheaper way to compare agents: run the tasks that still separate systems, not every task in the suite.
Self-Improving Agents Need Hard Boundaries
Self-improving agents can rewrite code, prompts and memory. Production teams need rollback, approval gates and evaluator change control.
Agent Observability Is Escaping the Dashboard
Agent observability is moving from vendor dashboards into trace contracts that make every model call, tool call, handoff, guardrail, and evaluator step inspectable.