violetfleming47

Answer human questions about GTM system state on demand. Use when asked about system health, pipeline status, content performance, or suggestions.

Assess and manage content autonomy levels for the validation system. Use for trust assessment, autonomy level review, or trust tracker updates.

Extract signals from sales call transcripts and detect cross-call patterns. Use for call analysis, [YOUR TRANSCRIPT PROVIDER] transcript processing, or sales signal extraction.

Find ICP-matched contacts for content distribution via [YOUR CRM] and LinkedIn. Use when finding distribution contacts or matching people to content.

Generate daily content suggestions, campaign proposals, and calendar updates. Use when suggesting content ideas, planning campaigns, or filling calendar gaps.

Create 3-stage distribution briefs: pre-publication, at-launch, and post-publication. Use when creating distribution plans or engagement briefs.

Capture engagement data from [YOUR SCHEDULING TOOL] analytics feed and LinkedIn uploads. Use when capturing engagement metrics, processing analytics data, or recording edit deltas.

Observe human edits to content, detect patterns across reviews, and propose skill adjustments. Use when learning from edits, detecting patterns, or running weekly analysis.

Freshness and decay management for the Deal Intelligence pipeline. Runs FIRST every cadence — before spotters, before the assembler, before anything analytical. Manages entity freshness transitions (active → aging → stale → archived), extends freshness for pattern-matched entities, and cleans the data layer so downstream agents work with current data. Triggered automatically before every pipeline run, or manually via 'run lifecycle', 'clean the data layer', 'check freshness'.

Reads meeting transcripts, CRM notes, and CRM emails to classify friction types, objections, competitive mentions, boosts, and unblocking events. Runs daily in parallel with other spotters. Writes to di_raw_signals and di_signal_classifications. Triggered automatically on cadence, or manually via 'run friction reader', 'scan friction for [deal]', 'what's stalling [deal]'.

Reads meeting transcripts, CRM emails, and CRM notes to classify deal progression signals — pain, commitment, authority, buying intent, language posture shifts. Runs daily in parallel with other spotters. Writes to di_raw_signals and di_signal_classifications. Triggered automatically on cadence, or manually via 'run conversation reader', 'scan conversations for [deal]', 'what signals are in [deal]'.

Forensic deep dive on a single deal from the Deal Intelligence pipeline. On-demand only. Triggered by 'deep dive on [deal]', 'prep me for the [company] call', 'analyse [deal]', 'what's happening with [company]', or any request for a single-deal analytical deep dive backed by evidence from di_* tables.

Reads CRM deal properties and property change history to detect stage transitions, deal value changes, owner reassignments, and close date shifts. The lightest spotter — reads structured fields, not unstructured text. Runs daily in parallel with other spotters. Writes to di_raw_signals and di_signal_classifications. Triggered automatically on cadence, or manually via 'run deal properties reader', 'check stage changes', 'what moved in the pipeline'.

Aggregates all available reader outputs into the five-dimension di_deal_state snapshot using SCD Type 2 versioning. Runs daily after all readers complete. No direct CRM or transcript provider access — everything comes through DI tables. Writes new di_deal_state versions only when something actually changed. Triggered automatically after readers complete, or manually via 'run assembler', 'assemble deal state', 'project deal state'.