Marketplace

Systematically clean a messy dataset with profiling, ordered fixes, validation, and a provenance log; use before analyzing or merging untrusted data.

Review cryptographic implementations: algorithm selection, key management, random number generation, and protocol-level flaws.

Audit cloud infrastructure for cost optimization: right-sizing, reserved capacity, storage tiers, and waste elimination.

Design chaos engineering experiments: hypothesis formation, blast radius control, steady-state metrics, and game day execution.

Design canary and progressive deployment strategies: traffic splitting, health metrics, automatic rollback, and analysis windows.

Design AI writing assistant features: tone control, suggestion timing, feedback loops, and human-in-the-loop editing.

Design AI-powered search experiences: semantic search, conversational interfaces, result ranking, and relevance tuning.

Design AI content moderation pipelines: multi-layer classification, appeal workflows, edge case handling, and trust safety.

Design AI code review systems: PR analysis, finding prioritization, false positive suppression, and developer feedback.

Design complex agentic workflows: DAG-based task graphs, conditional branching, human-in-the-loop checkpoints, and error recovery paths.

Design and implement multi-agent workflows with role assignment, task decomposition, and inter-agent communication protocols.

Design first-run experiences and onboarding flows for AI agents: capability discovery, permission grants, and initial task routing.

Implement tracing, logging, and monitoring for AI agent systems: LLM call traces, tool execution logs, latency tracking, and replay debugging.

Design persistent memory systems for AI agents: episodic, semantic, and procedural memory with retrieval strategies.

Design seamless handoff protocols between specialized agents: context transfer, state serialization, and recovery on failure.

Design self-improving agent systems: outcome tracking, reward signal extraction, prompt refinement cycles, and human preference collection.

Use when an agent workflow needs measurable quality: build task-based evals with graders, baselines, and A/B comparisons before shipping changes.

Design and run comprehensive eval suites for AI agents: task completion rates, tool call accuracy, cost tracking, and regression testing.

Manage WordPress in all popular forms: wp-cli for self-hosted, REST API for headless, Gutenberg block manipulation, plugin/theme management, and performance hardening.

Diagnose Core Web Vitals with field and lab data and produce an impact-ranked optimization plan. Use for slow pages, LCP/INP/CLS issues, or perf regressions.

Use when a feature or epic needs decomposition into a prioritized story map with user stories, acceptance criteria, and end-to-end release slices.

Synthesize user research interviews into actionable insights: affinity mapping, theme extraction, and opportunity prioritization.

Use when adding tests to existing code or after a bug fix: derives high-value cases from branches, boundaries, and bug history, then writes the suite.

Write clear technical specifications: RFC format, design alternatives, tradeoff analysis, and review-ready formatting.