从这里开始
使用最新发布
The release page is the second public front door, but the first-run path stays sequential:
Review artifacts in the same order each time: share-summary.md, scorecard.md, then recommendations.md.
版本化分发
发布说明应该像第二个公开入口，而不是一座更新日志坟场。
这一页由发布元数据编译而成，目的是让公开版本线保持机器可读、易于索引，并且对首次访客有用。
Apr 21, 2026
v0.3.2
AnswerLens is a CLI-first AI visibility auditor for product websites. CI for AI discoverability. ## 从这里开始 - 打开在线演示报告: https://yscjrh.github.io/ai-visibility-auditor/examples/static-good/index.html - 运行 60 秒 fixture 演示: https://github.com/YSCJRH/ai-visibility-auditor#run-the-60-secon...
Apr 21, 2026
v0.3.1
AnswerLens is a CLI-first AI visibility auditor for product websites. CI for AI discoverability. ## 从这里开始 - 打开在线演示报告: https://yscjrh.github.io/ai-visibility-auditor/examples/static-good/index.html - 运行 60 秒 fixture 演示: https://github.com/YSCJRH/ai-visibility-auditor#run-the-60-secon...
Apr 15, 2026
v0.3.0
AnswerLens is a CLI-first AI visibility auditor for product websites. CI for AI discoverability. ## 从这里开始 - 打开在线演示报告: https://yscjrh.github.io/ai-visibility-auditor/examples/static-good/index.html - 运行 60 秒 fixture 演示: https://github.com/YSCJRH/ai-visibility-auditor#run-the-60-secon...
Apr 15, 2026
v0.2.3
AnswerLens is a CLI-first AI visibility auditor for product websites. CI for AI discoverability. ## What ships - Field-level schema-text consistency and evidence density checks - Internal link context and discoverability rules for proof pages - Manual rank import with competitive position score (CPS) - Repeated-samp...
Apr 11, 2026
v0.2.0
## What ships AnswerLens `v0.2.0` is a CLI-first, report-driven AI visibility auditor for product websites. This release ships: - `audit` for deterministic AI-readiness checks against live sites or local fixtures - `eval` for prompt-pack benchmarking with OpenAI and Perplexity adapters - `manual-import` for scoring...
Apr 10, 2026
v0.1.0-alpha.1
Initial public alpha for AnswerLens. What is supported now: - CLI-first AI-readiness audit for product sites and fixtures - OpenAI-backed experimental eval with normalized citations and raw payload persistence - Markdown, JSON, and static HTML reports - Brief generation for FAQ, compare, and use-case gaps What this...