manual_slop/conductor/tracks/saved_presets_20260308/debrief.md

Track Debrief: Saved System Prompt Presets

Outcome

Implemented foundational "System Prompt Presets" with scoped inheritance (Global/Project) and integrated model parameters (Temperature, Top-P, Max Tokens).

Conceptual Dilemma

During implementation, a conflict was identified between "Prompt Presets" and "Model Settings." Selecting a preset from a prompt dropdown currently overrides global model parameters, which is unintuitive when multiple prompts (Global, Project, MMA) contribute to a single agent turn.

Future Direction: Agent Personas

To resolve this, we will move toward a Unified Persona model.

• Consolidation: Provider, Model, Parameters, Prompts (all scopes), and Tool Presets will be grouped into a single "Persona" object.
• UI Overhaul: The "AI Settings" panel will be refactored to focus on "Active Persona" selection rather than fragmented prompt/model controls.
• MMA Integration: MMA agents will eventually be assigned specific Personas, allowing for differentiated behaviors (e.g., a "Creative Worker" vs. a "Strict QA").

Implementation Sequence

1. Track: Saved Tool Presets (Upcoming)
2. Track: Agent Tool Preference & Bias Tuning (Upcoming)
3. Track: Agent Personas: Unified Profiles & Tool Presets (Final Consolidation) - This track will consume the findings from this debrief and the components from the preceding tracks.