https://nickmccarty.me/ 2026-06-09 monthly 1.0 https://nickmccarty.me/about.html 2026-06-09 monthly 0.9 https://nickmccarty.me/blog.html 2026-06-09 weekly 0.9 https://nickmccarty.me/contact.html 2026-06-09 yearly 0.7 https://nickmccarty.me/blog/agent-pipeline.html 2026-05-28 monthly 0.8 https://nickmccarty.me/assets/images/og/agent-pipeline.png Inside agent.py: The Three-Turn Research Pipeline https://nickmccarty.me/blog/agentic-design-patterns.html 2026-05-25 monthly 0.8 https://nickmccarty.me/assets/images/og/agentic-design-patterns.png Agentic System Design Patterns https://nickmccarty.me/blog/agentic-threat-hardening.html 2026-05-25 monthly 0.8 https://nickmccarty.me/assets/images/og/agentic-threat-hardening.png Agentic Threat Hardening: The OWASP Top 10, Applied https://nickmccarty.me/blog/alignment-fine-tuning.html 2026-05-01 monthly 0.8 https://nickmccarty.me/assets/images/og/alignment-fine-tuning.png Fine-Tuning and Alignment Deep Cuts: Synthetic Data, Poisoning, and Safety Recovery https://nickmccarty.me/blog/alt-data-pipeline.html 2026-05-18 monthly 0.8 https://nickmccarty.me/assets/images/og/alt-data-pipeline.png The Alt-Data Pipeline: From Beige Book to Paper Trading Thesis https://nickmccarty.me/blog/analytics-view.html 2026-05-20 monthly 0.8 https://nickmccarty.me/assets/images/og/analytics-view.png The Analytics View: Score Trends, Token Spend, and Run Distribution https://nickmccarty.me/blog/audio-data-flywheel.html 2026-05-23 monthly 0.8 https://nickmccarty.me/assets/images/og/audio-data-flywheel.png The Audio Data Flywheel https://nickmccarty.me/blog/autoresearch-convergence.html 2026-05-25 monthly 0.8 https://nickmccarty.me/assets/images/og/autoresearch-convergence.png When the Loop Defeats Itself: Convergence Failures in Autonomous Prompt Optimization https://nickmccarty.me/blog/autoresearch-view.html 2026-05-20 monthly 0.8 https://nickmccarty.me/assets/images/og/autoresearch-view.png The Autoresearch View: 40 Experiments, One Keep, and a 3% Signal Rate https://nickmccarty.me/blog/beige-book-rag-dpo.html 2026-05-28 monthly 0.8 https://nickmccarty.me/assets/images/og/beige-book-rag-dpo.png The Position Swap: Beige Book RAG Results and the DPO Cold-Start Problem https://nickmccarty.me/blog/circuit-extraction-notebook.html 2026-05-31 monthly 0.7 https://nickmccarty.me/assets/images/og/circuit-extraction-notebook.png Circuit Extraction Notebook https://nickmccarty.me/blog/circuit-extraction-pot-detection.html 2026-01-13 monthly 0.7 https://nickmccarty.me/blog/context-engineering.html 2026-05-22 monthly 0.8 https://nickmccarty.me/assets/images/og/context-engineering.png Context Engineering: What Reaches the Model https://nickmccarty.me/blog/convergence-detectors-shipped.html 2026-05-28 monthly 0.8 https://nickmccarty.me/assets/images/og/convergence-detectors-shipped.png Building the Detectors: What Actually Shipped After 107 Experiments https://nickmccarty.me/blog/curator.html 2026-05-24 monthly 0.8 https://nickmccarty.me/assets/images/og/curator.png Five Personas, One Veto: Consensus Filtering for Fine-Tuning Data https://nickmccarty.me/blog/debug-troubleshoot-skills.html 2026-05-31 monthly 0.8 https://nickmccarty.me/assets/images/og/debug-troubleshoot-skills.png The Diagnostic Skills: /debug and /troubleshoot https://nickmccarty.me/blog/design-build-page-skills.html 2026-05-31 monthly 0.8 https://nickmccarty.me/assets/images/og/design-build-page-skills.png The Site Generation Skills: /design and /build-page https://nickmccarty.me/blog/docker-deployment.html 2026-05-27 monthly 0.8 https://nickmccarty.me/assets/images/og/docker-deployment.png Deploying the Harness with Docker: CPU, GPU, and Compose Variants https://nickmccarty.me/blog/email-skill.html 2026-05-26 monthly 0.8 https://nickmccarty.me/assets/images/og/email-skill.png The Email Skill: Personalized Outreach Drafts from Conference Speaker CSVs https://nickmccarty.me/blog/eval-suite.html 2026-05-25 monthly 0.8 https://nickmccarty.me/assets/images/og/eval-suite.png The Regression Harness: Eval Suite, Criterion Functions, and Experimental Infrastructure https://nickmccarty.me/blog/evaluation-robustness.html 2026-04-29 monthly 0.8 https://nickmccarty.me/assets/images/og/evaluation-robustness.png Automated Evaluation Robustness: Metamorphic Testing, Scoring Bias, and Prompt Sensitivity https://nickmccarty.me/blog/evaluation-uncertainty.html 2026-04-29 monthly 0.8 https://nickmccarty.me/assets/images/og/evaluation-uncertainty.png Evaluation Uncertainty, Calibration, and Harness Reliability https://nickmccarty.me/blog/experimental-methodology.html 2026-05-23 monthly 0.8 https://nickmccarty.me/assets/images/og/experimental-methodology.png Experimental Methodology: Four Experiments, One Pipeline https://nickmccarty.me/blog/explorer-view.html 2026-05-30 monthly 0.8 https://nickmccarty.me/assets/images/og/explorer-view.png The Explorer View: Per-Run Pipeline DAG Inspector https://nickmccarty.me/blog/extracting-vision-features.html 2026-01-07 monthly 0.7 https://nickmccarty.me/blog/failure-taxonomy.html 2026-05-22 monthly 0.8 https://nickmccarty.me/assets/images/og/failure-taxonomy.png A Failure Taxonomy for Agentic Systems https://nickmccarty.me/blog/fastapi-web-app.html 2025-12-28 monthly 0.7 https://nickmccarty.me/blog/fine-tune-view.html 2026-05-21 monthly 0.8 https://nickmccarty.me/assets/images/og/fine-tune-view.png The Fine-tune View: DPO Training Runs, RL Data, and the Preference Feedback Loop https://nickmccarty.me/blog/fine-tuning-vision-models.html 2025-12-28 monthly 0.7 https://nickmccarty.me/blog/forge-plugin-skills.html 2026-06-01 monthly 0.8 https://nickmccarty.me/assets/images/og/forge-plugin-skills.png The Plugin System: /forge:plugin and /forge:list https://nickmccarty.me/blog/fred-bea-tools.html 2026-06-02 monthly 0.8 https://nickmccarty.me/assets/images/og/fred-bea-tools.png The Economic Data Tools: FRED and BEA https://nickmccarty.me/blog/fred-rag-results.html 2026-05-28 monthly 0.8 https://nickmccarty.me/assets/images/og/fred-rag-results.png Live Data Beats Narrative: FRED RAG Experiment Results https://nickmccarty.me/blog/gepa-autoresearch.html 2026-05-23 monthly 0.8 https://nickmccarty.me/assets/images/og/gepa-autoresearch.png From Hill-Climbing to Pareto: GEPA and the Autoresearch Loop https://nickmccarty.me/blog/github-skill.html 2026-05-27 monthly 0.8 https://nickmccarty.me/assets/images/og/github-skill.png The GitHub Skill: LLM-Assisted Git Operations from the Agent Loop https://nickmccarty.me/blog/github-view.html 2026-05-19 monthly 0.8 https://nickmccarty.me/assets/images/og/github-view.png The GitHub View: Repo Health at a Glance https://nickmccarty.me/blog/harness-data-model.html 2026-06-09 monthly 0.7 https://nickmccarty.me/blog/harness-roadmap.html 2026-05-24 monthly 0.7 https://nickmccarty.me/assets/images/og/harness-roadmap.png Seven Principles and a Moving Frontier: The Harness Roadmap https://nickmccarty.me/blog/harness-thesis.html 2026-05-22 monthly 0.8 https://nickmccarty.me/assets/images/og/harness-thesis.png The Harness Thesis: Why Scaffolding Beats Model Selection https://nickmccarty.me/blog/inference-patterns.html 2026-05-22 monthly 0.8 https://nickmccarty.me/assets/images/og/inference-patterns.png Inference Patterns: The Substrate Layer https://nickmccarty.me/blog/inference-shim.html 2026-05-29 monthly 0.8 https://nickmccarty.me/assets/images/og/inference-shim.png inference.py: The Unified LLM Backend Shim https://nickmccarty.me/blog/judge-benchmarks-scaling.html 2026-04-29 monthly 0.8 https://nickmccarty.me/assets/images/og/judge-benchmarks-scaling.png Judge Benchmarks and Test-Time Scaling: Where LLM Judges Succeed and Where They Don't https://nickmccarty.me/blog/judge-reliability.html 2026-04-29 monthly 0.8 https://nickmccarty.me/assets/images/og/judge-reliability.png Judging the Judges: Benchmark Contamination and LLM Evaluation Reliability https://nickmccarty.me/blog/knowledge-graphs-extraction.html 2026-05-01 monthly 0.8 https://nickmccarty.me/assets/images/og/knowledge-graphs-extraction.png Knowledge Graphs and Structured Extraction: Beyond the Vector Store https://nickmccarty.me/blog/layer4-circuit-diagram.html 2026-06-03 monthly 0.7 https://nickmccarty.me/assets/images/og/layer4-circuit-diagram.png Layer 4 Circuit Diagram https://nickmccarty.me/blog/leverage.html 2026-05-25 monthly 0.8 https://nickmccarty.me/assets/images/og/leverage.png Leverage: What the Metric Measures, What It Doesn't, and Why the Replacement Framing Gets the Math Wrong https://nickmccarty.me/blog/lit-review-skill.html 2026-05-26 monthly 0.8 https://nickmccarty.me/assets/images/og/lit-review-skill.png The Lit-Review Skill: Seven Steps from ArXiv Query to Rendered Survey https://nickmccarty.me/blog/mcp-view.html 2026-05-23 monthly 0.8 https://nickmccarty.me/assets/images/og/mcp-view.png The MCP View: Exposing the Harness as a Tool Server https://nickmccarty.me/blog/mechanistic-interpretability.html 2026-01-05 monthly 0.7 https://nickmccarty.me/blog/memory-observability.html 2026-05-28 monthly 0.8 https://nickmccarty.me/assets/images/og/memory-observability.png Memory as Infrastructure: Quality-Weighted Retrieval and the Ontology Graph https://nickmccarty.me/blog/memory-view.html 2026-05-19 monthly 0.8 https://nickmccarty.me/assets/images/og/memory-view.png The Memory View: 2,173 Observations, Quality Signals, and an Ontology Graph https://nickmccarty.me/blog/mine-knowledge.html 2026-05-26 monthly 0.8 https://nickmccarty.me/assets/images/og/mine-knowledge.png Mining a Ground-Truth Knowledge Base for the Eval Suite https://nickmccarty.me/blog/multi-objective-alignment.html 2026-05-23 monthly 0.8 https://nickmccarty.me/assets/images/og/multi-objective-alignment.png Multi-Objective Alignment: Beyond Scalar Rewards https://nickmccarty.me/blog/observability-flywheel.html 2026-05-22 monthly 0.8 https://nickmccarty.me/assets/images/og/observability-flywheel.png Observability and the Data Flywheel https://nickmccarty.me/blog/onboarding-grill-me-skills.html 2026-06-01 monthly 0.8 https://nickmccarty.me/assets/images/og/onboarding-grill-me-skills.png The Interview Skills: /grill-me and /onboarding https://nickmccarty.me/blog/op-cli.html 2026-05-24 monthly 0.8 https://nickmccarty.me/assets/images/og/op-cli.png The op CLI: A Rich REPL for the Research Harness https://nickmccarty.me/blog/orchestration-patterns.html 2026-05-22 monthly 0.8 https://nickmccarty.me/assets/images/og/orchestration-patterns.png Orchestration Patterns: Scaling to Multi-Agent Execution https://nickmccarty.me/blog/osint-enrichment.html 2026-05-28 monthly 0.8 https://nickmccarty.me/assets/images/og/osint-enrichment.png OSINT Enrichment: Nine Layers of Passive Reconnaissance https://nickmccarty.me/blog/osint-skill.html 2026-05-21 monthly 0.8 https://nickmccarty.me/assets/images/og/osint-skill.png The OSINT Skill: 11-Layer Target Enrichment for Research Tasks https://nickmccarty.me/blog/page-feedback-widget.html 2026-05-30 monthly 0.8 https://nickmccarty.me/assets/images/og/page-feedback-widget.png The Page Feedback Widget: Closing the Loop Between Browser and Agent https://nickmccarty.me/blog/panel.html 2026-06-02 monthly 0.8 https://nickmccarty.me/assets/images/og/panel.png The Wiggum Panel: Three-Persona Parallel Evaluation https://nickmccarty.me/blog/parallel-inference.html 2026-05-22 monthly 0.8 https://nickmccarty.me/assets/images/og/parallel-inference.png Parallel Inference: Hardware Substrates for LLM Workloads https://nickmccarty.me/blog/perplexity-vs-harness.html 2026-05-19 monthly 0.8 https://nickmccarty.me/assets/images/og/perplexity-vs-harness.png Harness vs. Perplexity: Eight Iterations to Parity https://nickmccarty.me/blog/pipeline-in-motion.html 2026-05-22 monthly 0.8 https://nickmccarty.me/assets/images/og/pipeline-in-motion.png The Pipeline in Motion: Tracing a Task Through All Eleven Subsystems https://nickmccarty.me/blog/pipeline-view.html 2026-05-30 monthly 0.8 https://nickmccarty.me/assets/images/og/pipeline-view.png The Pipeline View: Data Enrichment DAG https://nickmccarty.me/blog/planner.html 2026-05-28 monthly 0.8 https://nickmccarty.me/assets/images/og/planner.png The Planner: Two-Pass Pre-Research Analysis https://nickmccarty.me/blog/playwright-skill.html 2026-05-25 monthly 0.8 https://nickmccarty.me/assets/images/og/playwright-skill.png The Playwright Skill: LLM-Guided Navigation via ARIA Snapshots https://nickmccarty.me/blog/prompt-injection-security.html 2026-05-01 monthly 0.8 https://nickmccarty.me/assets/images/og/prompt-injection-security.png Prompt Injection and Agentic Security: What the Attack Literature Says https://nickmccarty.me/blog/research-history-view.html 2026-05-30 monthly 0.8 https://nickmccarty.me/assets/images/og/research-history-view.png The Research History View: A Unified Activity Log https://nickmccarty.me/blog/runs-view.html 2026-05-20 monthly 0.8 https://nickmccarty.me/assets/images/og/runs-view.png The Runs View: Pipeline Stage Visualization and Live Run Monitoring https://nickmccarty.me/blog/sam-object-detection.html 2026-01-10 monthly 0.7 https://nickmccarty.me/blog/sam-vs-fasterrcnn-comparison.html 2026-01-03 monthly 0.7 https://nickmccarty.me/blog/sbom-aibom.html 2026-05-25 monthly 0.8 https://nickmccarty.me/assets/images/og/sbom-aibom.png SBOM and AIBOM for Agentic Systems https://nickmccarty.me/blog/scratchpad-test-harness-skills.html 2026-06-01 monthly 0.8 https://nickmccarty.me/assets/images/og/scratchpad-test-harness-skills.png The Developer Utility Skills: /scratchpad and /test-harness https://nickmccarty.me/blog/search-cache.html 2026-05-28 monthly 0.8 https://nickmccarty.me/assets/images/og/search-cache.png The Search Cache: SQLite TTL Caching for DDGS Queries and Research Contexts https://nickmccarty.me/blog/security-patterns.html 2026-05-22 monthly 0.8 https://nickmccarty.me/assets/images/og/security-patterns.png Security Patterns: Constraining the Agent https://nickmccarty.me/blog/security-view.html 2026-05-23 monthly 0.8 https://nickmccarty.me/assets/images/og/security-view.png The Security View: 36 Events, 28 Blocks, and Live Injection Intercepts https://nickmccarty.me/blog/server.html 2026-05-29 monthly 0.8 https://nickmccarty.me/assets/images/og/server.png harness/api: The FastAPI Backend and Dashboard Server https://nickmccarty.me/blog/sessions-artifacts-view.html 2026-05-22 monthly 0.8 https://nickmccarty.me/assets/images/og/sessions-artifacts-view.png Sessions and Artifacts: The Harness Output Registry https://nickmccarty.me/blog/site-deck-skills.html 2026-05-31 monthly 0.8 https://nickmccarty.me/assets/images/og/site-deck-skills.png The Site Generation Skills: /site and /deck https://nickmccarty.me/blog/skillopt-gaps.html 2026-05-25 monthly 0.8 https://nickmccarty.me/assets/images/og/skillopt-gaps.png What SkillOpt Gets Right https://nickmccarty.me/blog/skillopt-shipped.html 2026-06-02 monthly 0.8 https://nickmccarty.me/assets/images/og/skillopt-shipped.png Closing the SkillOpt Gaps: What Actually Shipped https://nickmccarty.me/blog/skills-registry.html 2026-05-29 monthly 0.8 https://nickmccarty.me/assets/images/og/skills-registry.png The Skills Registry: Hook Points, Auto-Activation, and 38 Skills https://nickmccarty.me/blog/slm-efficiency.html 2026-05-08 monthly 0.8 https://nickmccarty.me/assets/images/og/slm-efficiency.png Small Language Models and the Efficiency-Accuracy Frontier https://nickmccarty.me/blog/sparse-probing-pot-detection.html 2026-01-09 monthly 0.7 https://nickmccarty.me/blog/structured-knowledge-queries.html 2026-04-29 monthly 0.8 https://nickmccarty.me/assets/images/og/structured-knowledge-queries.png Structured Knowledge Queries: Ontology, SPARQL, and Grounded Verification https://nickmccarty.me/blog/subagent-demo.html 2026-05-27 monthly 0.8 https://nickmccarty.me/assets/images/og/subagent-demo.png The Subagent Demo Suite: Orchestrating Multi-Task Research Portfolios https://nickmccarty.me/blog/submit-view.html 2026-05-21 monthly 0.8 https://nickmccarty.me/assets/images/og/submit-view.png The Submit View: Queuing Tasks and Watching the Pipeline Execute in Real Time https://nickmccarty.me/blog/suggest-reorient-skills.html 2026-05-31 monthly 0.8 https://nickmccarty.me/assets/images/og/suggest-reorient-skills.png The Navigation Skills: /suggest and /re-orient https://nickmccarty.me/blog/supervisor.html 2026-05-24 monthly 0.8 https://nickmccarty.me/assets/images/og/supervisor.png The Supervisor: Four Convergence Signals and Advisory Interventions https://nickmccarty.me/blog/system-view.html 2026-05-21 monthly 0.8 https://nickmccarty.me/assets/images/og/system-view.png The System View: Governance Docs, Active Configuration, and 38 Skills https://nickmccarty.me/blog/telemetry-router.html 2026-05-23 monthly 0.8 https://nickmccarty.me/assets/images/og/telemetry-router.png The Telemetry Router: Mining runs.jsonl for Self-Directed Improvement https://nickmccarty.me/blog/the-wiggum-loop.html 2026-05-22 monthly 0.8 https://nickmccarty.me/assets/images/og/the-wiggum-loop.png The Wiggum Loop: Cross-Model Evaluation and Dimensional Revision https://nickmccarty.me/blog/tinytroupe-tasks.html 2026-05-27 monthly 0.8 https://nickmccarty.me/assets/images/og/tinytroupe-tasks.png Synthetic Eval Task Generation with TinyTroupe Personas https://nickmccarty.me/blog/tool-use-planning.html 2026-05-01 monthly 0.8 https://nickmccarty.me/assets/images/og/tool-use-planning.png Agentic Tool Use and Planning: What the Literature Says https://nickmccarty.me/blog/trade-execution-skills.html 2026-06-01 monthly 0.8 https://nickmccarty.me/assets/images/og/trade-execution-skills.png The Trading Skills: /validate-trades and /execute-trades https://nickmccarty.me/blog/training-faster-rcnn-geospatial.html 2025-12-20 monthly 0.7 https://nickmccarty.me/blog/verification-patterns.html 2026-05-22 monthly 0.8 https://nickmccarty.me/assets/images/og/verification-patterns.png Verification Patterns: Measuring and Improving Output Quality https://nickmccarty.me/blog/voice-view.html 2026-05-23 monthly 0.8 https://nickmccarty.me/assets/images/og/voice-view.png The Voice View: Push-to-Talk Notes, Task Dictation, and the Audio Data Flywheel https://nickmccarty.me/blog/wiki-sync.html 2026-05-26 monthly 0.8 https://nickmccarty.me/assets/images/og/wiki-sync.png The Wiki Sync Skill: Deterministic Source Extraction and Gap-Targeted Code Injection https://nickmccarty.me/blog/youtube-transcribe.html 2026-05-25 monthly 0.8 https://nickmccarty.me/assets/images/og/youtube-transcribe.png YouTube and Media Transcription: Two Paths, One Research Input