The request "improve" names no product, software or platform, so I cannot tell whether you want to improve code, prompts, an AI agent, a CLAUDE.md file, a Cypher query, a search engine, or something else. Once you say what you want improved, I can recommend specific tools; several listed here (e.g., the Langfuse trace-and-evaluate platform 10 or Qdrant search-quality diagnostics 9) fit particular kinds of improvement.
A question back: What do you want to improve (for example code, an AI prompt or agent, search relevance, query performance, or a project file), and on which platform or stack?
Sources
- 9Qdrant - Vector Search Engineqdrant.tech · read 2026-10-29
- 10Langfuse: Open Source Agent Evals & Observabilitylangfuse.com · read 2026-10-29
For agents: the 10 actions behind this answer
arize-prompt-optimization · arize-prompt-optimization verified and signed
Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond bette
improve · improve verified and signed
Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs
connection-properties · connection-properties verified and signed
Specialized agent for creating and improving Connection Properties in Aspire resource and README files
prompt-optimizer · prompt-optimizer verified and signed
Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates. Use when asked to improve a prompt, optimize a system prompt, rewrite an agent prompt, tune prompt wording, make a prompt more reliable, port prompts between OpenAI, Claude, o
tilegym-improve-cutile-kernel-perf · tilegym-improve-cutile-kernel-perf verified and signed
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimiz
promptify · promptify verified and signed
Optimize prompts for clarity and effectiveness. Use when user says "improve this prompt", "optimize my prompt", "make this clearer", or provides vague/unstructured prompts. Intelligently routes to sub-agents for codebase research, clarifying questions, or web search as needed.
claude-md-improver · claude-md-improver verified and signed
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintena
neo4j-query-tuning-skill · neo4j-query-tuning-skill verified and signed
Diagnoses and fixes slow Neo4j Cypher queries by reading execution plans, identifying bad operators (AllNodesScan, CartesianProduct, Eager, NodeByLabelScan), and prescribing fixes (indexes, hints, query rewrites, runtime selection). Use when a query is slow, when EXPLAIN or PROFILE output needs inte
qdrant-search-quality · qdrant-search-quality verified and signed
Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or asks 'how to improve search quality?', 'which embedding model?', 'should I use hybrid search?', 'how
experiments · langfuse verified and signed
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.