Tag
#agents
Reports tagged agents.
Reports
10 reportsOct 2026
10-17 prompt-optimization Can Tests Teach a Prompt to Improve? Automatic prompt optimization searches for instructions—and sometimes examples—that work better when executed. Its value depends on what the search changes, how it uses results, and what happens on cases kept outside the search. 10-14 decision-models When is an agent's fast decision good enough? Additional reasoning is worth buying when a specific intervention can improve a consequential choice enough to justify its full cost. Confidence can help find those opportunities; it cannot price them by itself. 10-12 multi-agent-systems How AI agents turn separate efforts into an accepted result See how useful AI teams connect responsibilities, evidence and acceptance—and judge their value by what one worker’s contribution lets another do and whether the resulting work survives the right checks. Sep 2026
09-20 agent-harness How an AI Agent Should Decide Which Decisions Deserve Credit or Blame A final score does not explain a trajectory. Reliable improvement reconstructs the decision, tests fair alternatives, measures uncertainty, and applies the smallest reversible repair. 09-20 finance What a market view must contain before a financial agent builds a position A decision-ready market view is an accepted forecast packet: one resolvable claim, bound to the information available when it was made, passed through explicit stop rules, and handed to sizing without a hidden trade instruction. 09-13 agent-harness When can an AI agent say the task is complete? Completion is a judgment about the requested result—not a synonym for stopping, passing a check, or sounding confident. 09-07 model-routing Large Model, Small Model, or Both? The choice is never about how hard the task looks. It is an estimate of how well a candidate model will do, a threshold you own, and a bill you have to measure yourself. Aug 2026
08-24 agents The Memory Was Right. The Decision Was Wrong. Long-running agents need more than accurate retrieval: they need a disciplined way to turn past events into current, scoped, independently supported inputs to action. 08-20 agents The Skill Is Real, the Ritual Is Not Yet Measured Curated skills measurably improve coding agents where they carry procedure the model lacks; the process disciplines the frameworks sell remain unmeasured — and the nearest tests lean the other way. 08-18 agents Hard, Verifiable Agent Data: Download for Code, Build for the Rest Distillation-grade agent tasks are download-ready where checkers ship with them — code, and now terminal work; everywhere else the verifier is the scarce component, and the environment is yours to build.