Results for “non-intentional-action”

Use `analysis-agent` when engineering intent lacks desired behavior, boundaries, constraints, or completion signals. Skip requests with an accepted Engineering Brief and no-repo direct-answer work.

Detect and defend against prompt injection hidden in documents, web pages, and images consumed by an agent.

Use with analysis-agent or task-agent for task-local transaction, isolation, and conflict decisions. Do not use without a transaction decision or as task owner.

Designs or reviews Agentforce agent actions, covering Flow, Apex invocable, and prompt-template actions, including naming, input/output contracts, confirmation, and error behavior.

Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.

Agent validation v4.3.0 — Make agents act effectively by disabling harmful actions, lowering gates, and injecting cross-run learning

Guardian Angel gives AI agents a moral conscience rooted in Thomistic virtue ethics. Rather than relying solely on rule lists, it cultivates stable virtuous dispositions— prudence, justice, fortitude, temperance—that guide every interaction. The foundation is caritas: willing the good of the person you serve. From this flow the cardinal virtues as practical habits of right action and sound judgment. v3.0 introduced virtue-based disposition as the primary evaluation layer, providing deeper coherence than checklists alone. The agent's character becomes the safeguard. v3.1 adds: Plugin enforcement layer with before_tool_call hooks, approval workflows for ambiguous cases, and protections for sensitive infrastructure actions.

Append structured execution traces across operational, cognitive, and contextual surfaces with minimal overhead. Load when inspecting agent runs, logging tool calls and observations, enabling post-run debugging, or pairing with structured-planning step IDs. Also triggers on "trace this run", "log execution", "agent observability", "run log", or when fault-localize needs evidence. Default-on during multi-step plans. Traces live at .agent-loom/traces/ — git-ignored by default.

Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures, and performance regressions.

`analysis-agent`/`task-agent`/`review-agent`: use when symptoms, logs, metrics, regressions, or incidents need cause analysis; skip when no diagnosis decision exists.

Turn a "when X happens, do Y" idea into a precise build prompt for an automation platform (n8n, Make, Zapier, and others). Trigger on "build an automation", "n8n prompt", "Make scenario", "Zapier prompt", "automate this workflow", "when X happens do Y", or any request to wire up a no-code or low-code workflow.

Use `analysis-agent` to analyze permissions, secrets, sensitive data, trust boundaries, and injection; `task-agent` to implement controls; and `review-agent` to assess evidence. Skip self-review and no-trust-impact work.

Invoke after the agent has stopped, whether the user interrupted it or it paused on its own, to have it resume and stop asking for permission it doesn't need for the rest of the conversation.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.