Results for “traces”

Downloads, exports, and inspects existing Arize traces and spans to understand what an LLM app is doing or debug runtime issues. Covers exporting traces by ID, spans by ID, sessions by ID, and root-cause investigation using the ax CLI. Use when the user wants to look at existing trace data, see what their LLM app is doing, export traces, download spans, investigate errors, or analyze behavior regressions.

Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.

Run a PDCA quality audit on LLM/AI features: traces, prompts, costs, evals, grounding, hallucination. Use for "audit LLM quality", "check Langfuse", "audit prompts", "check AI quality", "audit AI costs", "check traces". Jailbreak/OWASP LLM → audit-llm-security. Token caps → plan-llm-cost-guardrails.

Debug LangChain and LangGraph agents by fetching execution traces from LangSmith. Analyze agent behavior, investigate errors, and review tool calls and performance metrics.

Use when the user asks Codex to inspect Aient telemetry, search logs, explain traces, create/list Aient API keys, or use the Aient MCP server.

`analysis-agent`/`task-agent`/`review-agent`: primary-Skill-selected for logs, metrics, traces, alerts, SLI/SLO, or diagnostics; never task owner; skip without signal impact.

`analysis-agent`: use when actors, goals, preconditions, triggers, paths, guarantees, postconditions, or acceptance traces need modeling; skip when no use-case decision exists.

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.

Capture a full DevTools-protocol trace of any browser automation, bisect the stream into per-page searchable buckets, and attach a trace to an in-progress session for debugging.

Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, and use the GraphQL API. Use whenever the user is analyzing traces or spans, investigating LLM/agent failures, deciding what to do after instrumenting an app, building failure taxonomies, choosing what evals to write, or asking "what's going wrong", "what kinds of mistakes", or "where do I focus" — even without naming a technique.

Debug agent execution by querying trace and metric tables, analyzing tool calls, durations, errors, and performance trends.

Debug LLM applications using the Phoenix CLI: fetch traces, analyze errors, structure trace review with open and axial coding, inspect datasets, review experiments, and query the GraphQL API.

Instrument LLM applications with OpenInference tracing for Phoenix AI observability, covering setup, custom spans, and production deployment.

You are an expert in LLM observability and evaluation. You think in terms of traces, spans, and metrics. You know that LLM applications need monitoring just like traditional software - but with different dimensions (cost, quality, latency).

Find the earliest decisive failure in an agent run trace and propose an evidence-backed targeted repair. Load when a run failed, results are wrong, or the user asks what went wrong in an agent session. Also triggers on "localize the fault", "first incorrect step", "debug this run", "trace attribution", "why did the agent fail", or after run-trace captures errors. Pairs with debug-and-fix for code defects and dynamic-routing for plan faults.

Diagnose Sentry issues without copy-pasting stack traces. Uses the Composio CLI to pull issue details, events, breadcrumbs, and suspect commits, then maps the frames to local source so the agent can propose a fix directly.

Diagnose Sentry issues without copy-pasting stack traces. Uses the Composio CLI to pull issue details, events, breadcrumbs, and suspect commits, then maps the frames to local source so the agent can propose a fix directly.

Show agent flow trace timeline and summary

Route LangSmith work into one workflow packet before touching SDK code. Use when the user needs LangSmith tracing, offline evals, annotation/review queues, prompt-registry decisions, audit/gap review, or cross-service trace propagation for an LLM app or agent workflow. Choose one packet: trace-debug, eval, review, prompt-registry, propagation, or audit. Triggers on: LangSmith, LangChain tracing, `@traceable` / `traceable`, `wrap_openai` / `wrapOpenAI`, datasets, experiments, annotation queues, feedback criteria, Prompt Hub, run trees, trace IDs, or production confidence for an AI feature. Not for generic SLO/alert design, non-LangSmith deployment orchestration, or runtime guardrails outside LangSmith.

`task-agent`: use for repository methods, query behavior, record mapping, visibility, errors, or transaction participation; skip schema, migration, DTO, and domain-rule work.

You are an expert in LLM observability and evaluation. You think in terms of traces, spans, and metrics. You know that LLM applications need monitoring just like traditional software - but with different dimensions (cost, quality, latency).

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

Diagnose Sentry issues without copy-pasting stack traces. Uses the Composio CLI to pull issue details, events, breadcrumbs, and suspect commits, then maps the frames to local source so the agent can propose a fix directly.

Design privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.

Generates deep links to the Arize UI for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs. Produces clickable URLs for sharing Arize resources with team members. Use when the user wants to link to or open a trace, span, session, dataset, evaluator, or annotation config in the Arize UI.

Supply-chain malware infection scanner. IoC-based local scan + safe eradication for npm/PyPI worm campaigns (Mini Shai-Hulud 1st/2nd, S1ngularity, lottie-player). Detects OS persistence (LaunchAgent/systemd), IDE-hook implants (.claude/.vscode/.github/workflows), lockfile-pinned malicious versions, and known C2/Session-Protocol exfil traces. Orchestrates credential rotation in the correct order so revocation does not trigger the `rm -rf ~/` retaliation payload. Don't use for static SAST (Sentinel), skill/MCP/`.claude/` supply-chain audit (Chain), Sigma/YARA rule authoring (Vigil), or incident coordination (Triage).

Enriches vague, low-detail prompts into structured, agent-optimized XML before execution. INVOKE IMMEDIATELY — before any tool use or file reads — when you detect any of these signals: prompt under 10 words with no file path or error message; vague action verbs with no object ("fix the bug", "make it better", "clean this up", "refactor this", "optimize performance", "improve the UI", "add authentication", "add payments", "add notifications", "build the feature"); CLARIFIER_ADVISORY in your context window; user says "clarify", "help me describe this", "enrich this prompt", "structure my request". Also triggers on: "make this work", "it's broken", "it looks bad", "add X" with no further detail, "implement Y" with no constraints. Do NOT trigger on: prompts ending with ?, prompts containing error messages or stack traces, prompts with specific file paths, prompts already containing acceptance criteria or success metrics.