2026 · 0905

日期:2026-09-05 · 类型:版本发布(首版)· 关联版本:v1.0.0

当日摘要 · SUMMARY

一套可分行业复用的 AI Harness 规约体系首次发布——5 大域、26 个场景,每个场景给出「使用规约细节 + 可复制的提示词」。建立在 AGENTS.md + SKILL.md + MCP 三件套之上,不自造 DSL、不绑定任何厂商。

1. 发布内容

1.1 规约文档(6 篇)

文件场景数优先级
00-master-spec-ai-harness-2026-09-05.md总纲
01-spec-software-engineering-2026-09-05.mdA 软件工程域6P0
02-spec-knowledge-collaboration-2026-09-05.mdB 知识与协同域7P0
03-spec-risk-compliance-2026-09-05.mdC 风险与合规域5P1(紧迫度 P0)
04-spec-data-science-2026-09-05.mdD 数据与科学域4P1
05-spec-industry-creative-2026-09-05.mdE 产业与创意域4P2(框架版)

5 大域共 26 个场景,与规划一一对应。

1.2 调研附件(3 份)

  • research/01-competitive-landscape(竞析)—— 竞品分析与市场格局
  • research/02-user-insights(瑞思)—— 用户洞察与采纳门槛
  • research/03-market-data(数析)—— 市场规模与数据基准

1.3 工具链资产

  • specs/tooling-schemas-2026-09-05.md —— JSON Schema + MCP 清单 + Eval 集 + deny-rule + CI 集成

1.4 路线图与索引

  • roadmap-ai-harness-promotion-2026-09-05.md —— 推广路线图(2026 Q4 – 2027 Q3)
  • README.md —— 索引

2. 关键决策(v1.0 锁定)

  1. 载体三件套:AGENTS.md + SKILL.md + MCP
  2. 自主度分级:Gartner L1-L4,映射 Google SRE L0-L3
  3. HITL 按可逆性 × 影响半径插入
  4. C 域封顶 L3;E 域物理接入封顶 L3
  5. A 与 B 同批;E 域出框架版
  6. 引用纪律:回避无原文数字;说明市场规模口径层级
  7. 北极星指标 WSHR

3. 说明(Notes)

  • 5 大域共 26 个场景(与规划一一对应)
  • E 域为框架版(数据不足;下版基于真实案例库补齐)
  • 北极星指标 WSHR 已建立基线采集机制
  • 季度复审机制:下次复审 2026-12-05

4. 后续

两天后(2026-09-07)发布 v1.0.1,新增白皮书 v1.0、行业基准定价评估与利益相关者更新, 规约主体保持不变。详见版本记录 2026 · 0907

2026 · 0905

Date: 2026-09-05 · Type: version release (initial) · Related version: v1.0.0

Daily Summary

The first release of a reusable, industry-segmentable AI Harness spec system — 5 domains, 26 scenarios, each with "usage-spec detail + a copy-ready prompt." Built on the AGENTS.md + SKILL.md + MCP trio, inventing no DSL and binding to no vendor.

1. What Was Released

1.1 Spec Documents (6)

FileDomainScenariosPriority
00-master-spec-ai-harness-2026-09-05.mdMaster spec
01-spec-software-engineering-2026-09-05.mdA · Software Engineering6P0
02-spec-knowledge-collaboration-2026-09-05.mdB · Knowledge & Collaboration7P0
03-spec-risk-compliance-2026-09-05.mdC · Risk & Compliance5P1 (urgency P0)
04-spec-data-science-2026-09-05.mdD · Data & Science4P1
05-spec-industry-creative-2026-09-05.mdE · Industry & Creative4P2 (framework version)

26 scenarios across 5 domains, one-to-one with the planned coverage.

1.2 Research Attachments (3)

  • research/01-competitive-landscape (Competitive) — competitor analysis and market landscape
  • research/02-user-insights (Insights) — user insights and adoption barriers
  • research/03-market-data (Market) — market size and data benchmarks

1.3 Tooling Assets

  • specs/tooling-schemas-2026-09-05.md — JSON Schema + MCP inventory + Eval set + deny-rule + CI integration

1.4 Roadmap & Index

  • roadmap-ai-harness-promotion-2026-09-05.md — promotion roadmap (2026 Q4 – 2027 Q3)
  • README.md — index

2. Key Decisions (locked in v1.0)

  1. The carrier trio: AGENTS.md + SKILL.md + MCP
  2. Autonomy grading: Gartner L1–L4, mapped to Google SRE L0–L3
  3. HITL inserted by reversibility × impact radius, not by step number
  4. Domain C capped at L3; Domain E physical access capped at L3
  5. Domains A and B ship in the same batch; Domain E ships as a framework version
  6. Citation discipline: avoid figures without source text; always state the market-size metric layer
  7. North-Star metric: WSHR

3. Notes

  • 26 scenarios across 5 domains (one-to-one with the planned coverage)
  • Domain E is a framework version (insufficient data; to be completed from a real case library in the next version)
  • Baseline collection for the North-Star metric WSHR is in place
  • Quarterly review cycle: next review 2026-12-05

4. What's Next

Two days later (2026-09-07), v1.0.1 added the whitepaper v1.0, the benchmark pricing assessment, and the stakeholder update, with the spec body unchanged. See the version record 2026 · 0907.