feat: V4.0 — portable evidence-based competitive intelligence agent - #2
Open
diandian1001 wants to merge 4 commits into
Open
feat: V4.0 — portable evidence-based competitive intelligence agent#2diandian1001 wants to merge 4 commits into
diandian1001 wants to merge 4 commits into
Conversation
…nhanced evidence rules ### New files - evaluation/benchmark.md: 3 test tasks with 7-dimension scoring rubric (status: design complete, pending execution) - templates/output-template.md: unified 10-section result template integrating all existing templates ### README.md + README_zh.md (fully synced) - Add 30-second input→output example with sanitized business problem - Add 'When to Use / Not Suitable' section with 7 failure scenarios - Add V3.0 Key Changes comparison table to English README (was only in Chinese) - Expand repository structure to show all files - Add platform-specific usage options (ChatGPT/Claude/Hermes) - Sync scope section between English and Chinese versions ### references/evidence-rubric.md (enhanced) - Add capability boundaries: what each grade (A/B/C/D) can support - Add critical principle: conclusion certainty ≤ evidence certainty - Add source conflict resolution rules (time priority, authority, alignment, irreconcilable) - Add stale information handling table (6 info types with validity periods and downgrade rules) - Add 2 new prohibited practices (D-grade masking, forced precision)
…ading rules ### README.md + README_zh.md - Remove unverified percentages (40% return visits, 7/12/5/3 evidence counts) - Remove fabricated competitor count (4 from 10) - Replace with structural placeholders and 'structure illustrative' warning - Add⚠️ disclaimer: examples are structural illustrations, not real conclusions ### evidence-rubric.md - Add 5-dimension evaluation framework (source, claim-match, sample, timeliness, cross-validation) - Each grade now requires all 5 dimensions, not just source name - Add critical examples: official page = A for 'feature exists', D for 'feature effective' - Add: product testing can prove path, not preference; data can prove correlation, not causation - Time windows changed from fixed rules to advisory defaults - Add industry-specific and risk-adjusted guidance
### evidence-rubric.md - Fix A-grade: no longer mechanically requires sample+validation for ALL claims - Add principle: different claims have different evidence requirements - Add examples: official page = A for feature existence, NOT A for business effect - B-grade updated for consistency ### README.md - Replace Chinese disclaimer with English - Add English equivalents alongside Chinese labels (事实/Fact, 推断/Inference, 待验证/Unverified)
diandian1001
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Upgrades the repository from a competitive-analysis workflow into a portable, executable and traceable AI Competitive Intelligence Operating System.
V4.0 Goals
New Files
AGENTS.mdPORTABLE.mdtemplates/project-state.mdtemplates/evidence-ledger.mdtemplates/output-quick.mdtemplates/output-standard.mdtemplates/output-deep.mdCore Changes
/14selection with decision-specific weightingValidation
/14scoring removed from current rulesMerge
Do not merge until the V4.0 content and validation results have been independently reviewed.