System prompts
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-05.)
System prompts has 30 facts recorded in Dontopedia across 2 references, with 4 live disagreements.
Mostly:rdf:type(3), part of(2), configures(2)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (11)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
involvesInvolves(2)
- Context Management
ex:context-management - Context Management
ex:context-management
containsContains(1)
- System
ex:system
hasPartHas Part(1)
- Context Management Section
ex:context-management-section
hasSubcomponentHas Subcomponent(1)
- Context Management
ex:context-management
hasSubsectionHas Subsection(1)
- Context Management Section
ex:context-management-section
implementsInterfaceImplements Interface(1)
- Context Management Section
ex:context-management-section
managesManages(1)
- Context Management
ex:context-management
marksItemAsResolvedMarks Item As Resolved(1)
- Dominance Analysis
ex:dominance-analysis
precedesResolutionPrecedes Resolution(1)
- Custom Model Execution
ex:custom-model-execution
usesUses(1)
- Context Management
ex:context-management
Other facts (27)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Rdf:type | Concept | [1] |
| Rdf:type | Concept | [2] |
| Rdf:type | Technical Concept | [1] |
| Part of | Context Management | [2] |
| Part of | Context Management Section | [2] |
| Configures | Llm | [2] |
| Configures | Initial System State | [2] |
| Related to | Context Management | [1] |
| Similar to | System | [2] |
| Contains | Prompt | [2] |
| Provides | Agent Instructions | [2] |
| Sets | Agent Behavior | [2] |
| Component of | Context Management | [2] |
| Sets Initial Behavior of | Llm | [2] |
| Data Structure Type | text-based | [2] |
| Timing | initialization | [2] |
| Configures Initial Behavior of | Llm | [2] |
| Data Structure | text-based | [2] |
| Configuration Structure | context-management | [2] |
| During | initialization | [2] |
| Has Semantic Meaning | provides context and instructions | [2] |
| Has Level | 2 | [2] |
| Provides Instruction | Concept Llm | [2] |
| Modifies Behavior of | Sampling Section | [2] |
| Has Outline Position in Section | 2 | [2] |
| Has Word Count | 2 | [2] |
| Depth in Hierarchy | 2 | [2] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (2)
ctx:discord/blah/agents/5- full textctx:discord/blah/agents/5text/plain2 KB
doc:discord/blah/agents/5Show excerpt
[2026-02-18 10:45] lisamegawatts: teams be teams everywhere you go, i loved this back and forth between ml team and dev team (files: image.png) [2026-02-19 18:06] traves_theberge: (files: HBhXt3aW4AEz7wV.png) [2026-02-19 19:47] traves_theb…
ctx:discord/blah/agents/6- full textctx:discord/blah/agents/6text/plain1 KB
doc:discord/blah/agents/6Show excerpt
[2026-03-15 03:03] traves_theberge: The key insight: LLM + loop + tools = agent The Agent Loop The core while-loop Code: basic loop skeleton Stop conditions: end_turn, max_iterations, human approval Sampling (The Model Layer) Making API…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.