BoardroomAI is a dependency-aware, human-steerable multi-agent deliberation system. It achieves human-agent coexistence through four components: (i) a typed decision graph representing evidence, assumptions, constraints, claims, objections, alternatives, risks, decisions, semantic dependencies, and specialist responsibility; (ii) an intervention compiler that converts confirmed human actions into explicit graph updates; (iii) dependency-aware propagation that identifies affected subgraphs, preserves unaffected artifacts, and selectively reactivates relevant specialists; and (iv) an evaluation framework measuring intervention impact, repair coverage, preservation, recomputation, and decision validity. Experimental results show that propagation matched exhaustive impact computation while inspecting only 14.59% of nodes. In a 12-case exploratory pilot, selective repair recomputed 62.11% of canonical nodes, preserved all gold-unaffected nodes, and produced valid updated decisions in six cases while abstaining in the remaining six. These abstentions demonstrate that correct intervention routing may still provide insufficient context for synthesis, motivating a emph{decision-sufficient context closure} for human-steered multi-agent deliberation. All results are synthetic and prototype-level. Blogger's Review: BoardroomAI's dependency-aware and human-steerable multi-agent deliberation mechanism provides a new approach to complex decision-making problems. By treating humans as persistent participants, the system can better adapt to changing environments and needs. However, correct intervention routing and decision-sufficient context closure remain important issues that require further research.