Agent
Black-box architecture generation agent. Proposes multiple approaches, elaborates functional blocks with ASCII diagrams, and guides section-by-section approval.
Agent
Black-box architecture generation agent. Proposes multiple approaches, elaborates functional blocks with ASCII diagrams, and guides section-by-section approval.
Agent
Final document composition agent. Produces Concept Document and Solution Landscape with section-by-section approval and source citations.
Agent
Research execution agent for drill-down phase. Uses tiered tool strategy with verification protocol and confidence levels. Registers sources via sourcetracker.py.
Agent
Gap identification agent for drill-down phase. Identifies unknowns per block, lists solution OPTIONS (not recommendations) with citations.
Agent
Open-ended questioning agent for spit-ball ideation sessions. Probes feasibility, expands ideas with "what if" questions, and clusters themes.
Agent
Metered questioning agent for problem definition. Adapted from problem-definition skill's 5W2H pattern but generalized for concept development. Includes scope guardrail for deferring solutions.
Agent
AI slop checker that verifies feasibility claims, solution descriptions, and technical assertions. Cross-cutting agent invoked in Phases 1, 4, and 5 to catch hallucinated capabilities, vague assessments, and ungrounded claims.
Agent
Semantic quality checker for requirements using 9 INCOSE GtWR v4 LLM-tier rules.
Agent
Research agent for Technical Performance Measures. Searches for performance benchmarks, comparable system data, and published metrics using tiered research tools. Registers sources via sourcetracker.py.