Find articles, news, tools and templates by subject or by the work you need to do.
91 results for “Evaluate an agent” · 37–48
News · AI in production ·
Google's new image model rejects familiar generation settings. Follow a thumbnail job through its outgoing request, retries and delivery to evaluate the upgrade.
Read news: What Nano Banana 2.1 changes in an image-generation serviceNews · AI in production ·
Search results from Ceramic.ai, Exa and Linkup can enter an agent workflow through one gateway, while source versions and provider terms still need inspection.
Read news: Cloudflare adds web search to AI GatewayNews · AI in production ·
Google’s internal PageBreak agent proposes web vulnerabilities; separate validators test them in running applications. Reproductions can reduce the investigation work handed to developers.
Read news: Google PageBreak tests AI-found bugs before sending reportsNews · Observability ·
Kubernetes attributes connect agent calls to pods, workloads and paging routes. A processor migration can break those connections while telemetry still flows.
Read news: OpenTelemetry’s Kubernetes attributes processor reaches v1Explainer · AI in production ·
UserRepGen turns a conversation into task and behavior descriptions. Follow the intermediate artifact through a synthetic support-assistant evaluation.
Read explainer: Microsoft UserRepGen makes inputs for a simulated userGuide · AI in production ·
What a model does when you ask a question, how we got here, and how to choose between local and hosted inference without confusing fast text with useful work.
Read guide: Model inference: what happens when you ask AI a question?Explainer · AI in production ·
A host that launches codex exec must own the process, thread lease, JSONL trace, cancellation and artifact checks. Resume is a lifecycle decision, not a shell shortcut.
Read explainer: Running Codex CLI as a supervised worker processNews · AI in production ·
Mistral's October 6 launch offers a hosted trial for security investigations. Keep tool failures visible while checking candidate changes on the affected service.
Read news: Mistral Large 4 opens a preview for security investigationsNews · AI in production ·
The public preview connects Copilot to desktop applications on macOS and Windows, with application permissions and record-level verification doing different jobs.
Read news: GitHub Copilot gains computer use for desktop workflowsGuide · Observability ·
Tail sampling selects recorded traces by error, latency and other evidence. A checkout timeout shows how routing, waiting time and memory affect the trace a responder can retrieve.
Read guide: OpenTelemetry tail sampling through a checkout failureExplainer · AI in production ·
Jev answers supplied questions with choices, scores and probabilities. A token-rotation ticket shows how those structured outputs can fit a support router.
Read explainer: Jev returns typed answers for routing and scoring tasksGuide · AI in production ·
CodeRabbit brings AI feedback into pull requests, editors and the CLI. A retry loop that exceeds its caller’s deadline shows the kind of finding that can repay review time.
Read guide: CodeRabbit: how to use AI code review