Results for “self-observation”

Slow down interpretation from observation to action. Use when students or adults need to examine assumptions in conflict, dialogue, or inquiry.

Turn owner feedback about agent behavior into concrete system changes. Use when the owner says something is off, wants the assistant to improve how it operates, asks for a reflection, or wants a durable fix instead of a one-off apology.

Evaluates the agent's own work, catches mistakes, and improves permanently through self-reflection, self-criticism, and learning from corrections.

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.

LLM observability with Langfuse — tracing, evals, prompt management, cost tracking

Econometrics skill for panel data models. Activates when the user asks about: "panel data", "fixed effects", "random effects", "Hausman test", "within estimator", "between estimator", "two-way fixed effects", "clustered standard errors panel", "FE model", "RE model", "pooled OLS", "unobserved heterogeneity", "panel regression", "first difference estimator", "entity fixed effects", "time fixed effects", "面板数据", "固定效应", "随机效应", "豪斯曼检验", "双向固定效应", "面板回归", "个体效应", "时间效应", "一阶差分"

Review the week using accumulated session evidence — retrieval rates, hint depths, calibration accuracy, transfer and unassisted results. The learner identifies patterns and sets a strategy goal. Use weekly or after a multi-session period.

Run autonomous optimization loops that iteratively improve artifacts against evaluators using hypothesis tree refinement, without overfitting.

Run Karpathy-style autonomous ML search on a real training repo: choose the right mode (setup, program.md, bounded loop, results interpretation, or constrained-hardware adaptation), preserve the immutable prepare.py / 300-second / val_bpb contract, and route prompt/skill eval work away to LangSmith, Promptfoo, Braintrust, or skill-autoresearch.

Continuously monitors system performance, identifies improvement opportunities, and orchestrates skill discovery and creation to autonomously evolve capabilities.

Capture confidence ratings before and after a learning attempt to identify overconfidence and underconfidence patterns. Use when a student wants to understand how well they actually know something versus how well they think they know it.

`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.

Track performance across sessions and reduce scaffolding as competence grows. Makes fading visible — the learner knows when scaffolds are removed and why. Use for sustained learning engagement where independence is the goal.

Compresses conversation transcripts into prioritized notes using an LLM observer, consolidates them when they grow, and recovers any missed sessions without a database or vector store.

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.

Monitor a live model for data quality, input and prediction drift, performance decay, and fire retraining triggers.

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture for rapid experimentation and synthesis, producing papers and presentations.