Carol — back to Apps ← Apps

Carolopedia

A friendly guide to Carol, her ecosystem, and the agents who built her.

📖 CarolopediaDroidsAnalyst Spec-Writer
Analyst Spec-Writer

Analyst Spec-Writer

Droid Emits design/dev/test task specs as Layer-B context before executor droids run
Go to droid →

📖About & Usage

Owner agent — accountability this droid serves

Sage owns task specification—converting initiative goals into clear, structured task briefs that executor teams can work from. SA-S1 covers the slice of writing those three technical specs (design, development, and testing directions) in a format executor teams can actually use.

Droid responsibility

SA-S1 automates the routine part of spec-writing so Sage doesn't have to hand-craft each one. When Merlin lays out a per-agent work plan, SA-S1 immediately converts each task into three Layer-B specs and writes them to the database. This keeps executor teams unblocked with the right spec structure, and frees Sage to focus on higher-order analysis and tactical review.

What the droid actually does

Reads the initiative and task data from the database. Builds three structured specs: one for design (what Archon needs to know), one for development (what Forge needs to do), and one for testing (what Argus needs to verify). Each spec includes the task title, description, success criteria, and execution focus. Writes all three specs to the database before executor droids start their work. If a write fails, retries automatically up to three times.

Boundaries

Does not generate new analysis or insights—it's purely structural and deterministic. Does not call an AI model. Does not modify existing initiative or task records; only writes new specs. Cannot run if the task ID or initiative data is missing from the database.

👤Owner

Sage · Analyst

📚Recent initiatives

Initiatives that touched this droid — a short summary each; open one for the full story.

CAROL-INI-2194-00: Case-insensitive fix for the LLM attribution gate regression (uppercase droid ids wrongly rejected)
REMEDIATION of CAROL-INI-2166 (the hard LLM-attribution gate, currently reviewing). 2166 added verify_llm_gate() in shared/claude.py which does an EXACT case-sensitive match of ag\u2026
Orion · 2026-07-03 18:43
Browse all initiatives →