Find articles, news, tools and templates by subject or by the work you need to do.
91 results for “Evaluate an agent” · 13–24
Explainer · AI in production ·
The global auto mode is only part of the permission decision. Follow per-tool overrides, directory scope and restored settings through a copied-runbook exercise.
Read explainer: KoboldCpp 1.123 makes agent approvals depend on the tool and workdirNews · AI in production ·
Sparse routing reduces per-token compute, but the full 24B checkpoint, agent harness, license and representative workload still decide deployment fit.
Read news: What LFM2.5's 2.45B active parameters mean for local agentsExplainer · AI in production ·
A coding agent's tools and testing policy help determine its benchmark result. Understand what was compared before choosing a setup for your team.
Read explainer: Coding agent benchmarks: what actually won?Explainer · AI in production ·
Measure cached input against total input, locate the prefix miss boundary, and judge cache changes beside latency, task cost and correction work.
Read explainer: Long agent sessions need a prompt-cache SLIExplainer · AI in production ·
Anthropic’s October 7 credits add a Console-funded path for eligible subscribers. Subscription access remains, while scheduled agents still need task budgets spanning retries and verification.
Read explainer: Claude’s new API credits do not remove Agent SDK subscription accessNews · AI in production ·
Wikimedia’s October 5 disclosure covers unapproved edits, proxy attempts and heavy downloading. Activity windows remain unresolved; the linked WDQS outage was in May.
Read news: Wikimedia reports unapproved activity by suspected OpenAI agentsNews · AI in production ·
Bigtable joins Google’s Data Agent Kit. An illustrative rollout investigation shows why retained cell versions need an application-level evidence check.
Read news: Data Agent Kit brings Bigtable queries into coding agentsNews · AI in production ·
The desktop preview packages a configurable coding agent. Its plugins determine which model answers, which files it can read, and where commands run.
Read news: DeepSeek Harness connects a desktop agent to your models and toolsNews · Observability ·
Standard maintenance has ended for Google’s legacy agents. Migration to Ops Agent changes some metric fields, including disk labels used by existing queries.
Read news: Google ends maintenance for legacy Monitoring and Logging agentsNews · AI in production ·
CLM-8B embeds a situation and ranks supplied actions. Reusable candidate embeddings suit recurring choices, while the candidate list determines which answers are possible.
Read news: CLM-8B lets agents rank a supplied set of actionsNews · AI in production ·
SWE-Serve checks coding-agent patches through a running SGLang server. In NVIDIA’s experiment, adding live-serving checks reduced the pass rate for the same patches.
Read news: SWE-Serve tests coding agents through live inferenceNews · AI in production ·
GPT-6 Sol and Luna combine lower token rates with cache-write and cache-read pricing. A repeated prompt can cost less even though its first cached write carries a premium.
Read news: GPT-6 Sol and Luna change the agent cost calculation