Wiki source code of Workflows

Last modified by Robert Schaub on 2026/02/08 08:26

version	line-number	content
1.1	1	= Workflows =
4.2	2
1.1	3	FactHarbor workflows are simple, automated, focused on continuous improvement.
4.2	4
1.1	5	== 1. Core Principles ==
4.2	6
1.1	7	* Automated by default: AI processes everything
	8	* Publish immediately: No centralized approval (removed in V0.9.50)
	9	* Quality through monitoring: Not gatekeeping
	10	* Fix systems, not data: Errors trigger improvements
	11	* Human-in-loop: Only for edge cases and abuse
4.2	12
1.1	13	== 2. Claim Submission Workflow ==
3.1	14
	15	=== 2.1 Claim Extraction ===
	16
	17	When users submit content (text, articles, web pages), FactHarbor first extracts individual verifiable claims:
	18
	19	Input Types:
4.2	20
3.1	21	* Single claim: "The Earth is flat"
	22	* Text with multiple claims: "Climate change is accelerating. Sea levels rose 3mm in 2023. Arctic ice decreased 13% annually."
	23	* URLs: Web pages analyzed for factual claims
	24
	25	Extraction Process:
4.2	26
3.1	27	* LLM analyzes submitted content
	28	* Identifies distinct, verifiable factual claims
	29	* Separates claims from opinions, questions, or commentary
	30	* Each claim becomes independent for processing
	31
	32	Output:
4.2	33
3.1	34	* List of claims with context
	35	* Each claim assigned unique ID
	36	* Original context preserved for reference
	37
	38	This extraction ensures:
4.2	39
3.1	40	* Each claim receives focused analysis
	41	* Multiple claims in one submission are all processed
	42	* Claims are properly isolated for independent verification
	43	* Context is preserved for accurate interpretation
	44
1.1	45	```
	46	User submits → Duplicate detection → Categorization → Processing queue → User receives ID
	47	```
	48	Timeline: Seconds
	49	No approval needed
2.1	50
	51	== 2.5 Claim and Scenario Workflow ==
	52
4.12	53	{{include reference="Archive.FactHarbor 2026\.01\.20.Specification.Diagrams.Claim and Scenario Workflow.WebHome"/}}
2.1	54
1.1	55	== 3. Automated Analysis Workflow ==
4.2	56
1.1	57	```
	58	Claim from queue
	59	↓
	60	Evidence gathering (AKEL)
	61	↓
	62	Source evaluation (track record check)
	63	↓
	64	Scenario generation
	65	↓
	66	Verdict synthesis
	67	↓
	68	Risk assessment
	69	↓
	70	Quality gates (confidence > 40%? risk < 80%?)
	71	↓
	72	Publish OR Flag for improvement
	73	```
	74	Timeline: 10-30 seconds
	75	90%+ published automatically
4.2	76
1.1	77	== 3.5 Evidence and Verdict Workflow ==
4.2	78
4.13	79	{{include reference="Archive.FactHarbor 2026\.01\.20.Specification.Diagrams.Evidence and Verdict Workflow.WebHome"/}}
4.2	80
1.1	81	== 4. Publication Workflow ==
4.2	82
1.1	83	Standard (90%+): Pass quality gates → Publish immediately with confidence scores
	84	High Risk (<10%): Risk > 80% → Moderator review
	85	Low Quality: Confidence < 40% → Improvement queue → Re-process
4.2	86
1.1	87	== 5. User Contribution Workflow ==
4.2	88
1.1	89	```
	90	Contributor edits → System validates → Applied immediately → Logged → Reputation earned
	91	```
	92	No approval required (Wikipedia model)
	93	New contributors (<50 reputation): Limited to minor edits
4.2	94
2.1	95	== 5.5 Quality and Audit Workflow ==
	96
4.14	97	{{include reference="Archive.FactHarbor 2026\.01\.20.Specification.Diagrams.Quality and Audit Workflow.WebHome"/}}
2.1	98
1.1	99	== 6. Flagging Workflow ==
4.2	100
1.1	101	```
	102	User flags issue → Categorize (abuse/quality) → Automated or manual resolution
	103	```
	104	Quality issues: Add to improvement queue → System fix → Auto re-process
	105	Abuse: Moderator review → Action taken
4.2	106
1.1	107	== 7. Moderation Workflow ==
4.2	108
1.1	109	Automated pre-moderation: 95% published automatically
	110	Moderator queue: Only high-risk or flagged content
	111	Appeal process: Different moderator → Governing Team if needed
4.2	112
1.1	113	== 8. System Improvement Workflow ==
4.2	114
1.1	115	Weekly cycle:
	116	```
	117	Monday: Review error patterns
	118	Tuesday-Wednesday: Develop fixes
	119	Thursday: Test improvements
	120	Friday: Deploy & re-process
	121	Weekend: Monitor metrics
	122	```
	123	Error capture:
	124	```
	125	Error detected → Categorize → Root cause → Improvement queue → Pattern analysis
	126	```
	127	A/B Testing:
	128	```
	129	New algorithm → Split traffic (90% control, 10% test) → Run 1 week → Compare metrics → Deploy if better
	130	```
4.2	131
1.1	132	== 9. Quality Monitoring Workflow ==
4.2	133
1.1	134	Continuous: Every hour calculate metrics, detect anomalies
	135	Daily: Update source track records, aggregate error patterns
	136	Weekly: System improvement cycle, performance review
4.2	137
1.1	138	== 10. Source Track Record Workflow ==
4.2	139
1.1	140	Initial score: New source starts at 50 (neutral)
	141	Daily updates: Calculate accuracy, correction frequency, update score
	142	Continuous: All claims using source recalculated when score changes
4.2	143
1.1	144	== 11. Re-Processing Workflow ==
4.2	145
1.1	146	Triggers: System improvement deployed, source score updated, new evidence, error fixed
	147	Process: Identify affected claims → Re-run AKEL → Compare → Update if better → Log change
4.2	148
1.1	149	== 12. Related Pages ==
4.2	150
4.15	151	* [[Requirements>>Archive.FactHarbor 2026\.01\.20.Specification.Requirements.WebHome]]
4.10	152	* [[Architecture>>Archive.FactHarbor 2026\.01\.20.Specification.Architecture.WebHome]]
4.11	153	* [[Data Model>>Archive.FactHarbor 2026\.01\.20.Specification.Data Model.WebHome]]

Wiki source code of Workflows

Applications

Navigation

Need help?