Review — elartedevivir.ar

← overview

ventana últimos 7d vs 7d previos · tz America/Argentina/Buenos_Aires · último cambio Ninjo: 2026-07-30 20:55 (deploy config, hace 1d) · 70 untracked

127

Nuevas (7d)

prior 16

Calls booked

0.0% de link

Link sent

5.7% de activas

Revenue variable

70 msgs

Resumen — período vs período

Métrica	this 7d	prior 7d	Δ
Activas	348	61	+470.5%
Nuevas	127	16	+693.8%
Link sent	20	2	+900.0%
Calls booked	0	0	—
Booked/Link %	0.0%	0.0%	+0.0pp
Booked/Activas %	0.0%	0.0%	+0.0pp
Booked/Nuevas %	0.0%	0.0%	+0.0pp
Revenue variable	$0.00	$0.00	—

Funnel — semana actual vs anterior

Período	Activas	Nuevas	Link sent	Calls booked	Booked/Link	Booked/Activas	Booked/Nuevas
Semana actual (7d)	348	127	20	0	0.0%	0.0%	0.0%
Semana anterior (7d)	61	16	2	0	0.0%	0.0%	0.0%

Ver desglose por día

Día	Activas	Nuevas	Link sent	Booked/Link	Booked/Activas	Booked/Nuevas
07-30	32	12	0	—	0.0%	0.0%
07-29	284	108	19	0.0%	0.0%	0.0%
07-28	15	5	1	0.0%	0.0%	0.0%
07-27	3	1	0	—	0.0%	0.0%
07-26	3	1	0	—	0.0%	0.0%
07-25	3	0	0	—	0.0%	—
07-24	8	0	0	—	0.0%	—
07-23	11	4	1	0.0%	0.0%	0.0%
07-22	9	3	0	—	0.0%	0.0%
07-21	11	2	1	0.0%	0.0%	0.0%
07-20	11	3	0	—	0.0%	0.0%
07-19	3	0	0	—	0.0%	—
07-18	7	2	0	—	0.0%	0.0%
07-17	9	2	0	—	0.0%	0.0%

run 2026-07-24T14:58:26+00:00 · fuente: live DB state (daily_audit pipeline)

4/10

BP semánticos PASS

top-10 best practices

14/16

Determinísticos PASS

2 FAIL · 0 WARN

C0 · H1 · M0

Fails por severidad

critical / high / medium

—

Drift

DB vs repo local

BP semánticos (top-10 best practices)

BP-1

BP-2

BP-3

BP-4

BP-5

BP-6

BP-7

BP-8

BP-9

BP-10

BP	Sev	Estado	Detalle
BP-1	HIGH	FAIL	Template compliance system.md contains only 'test only' — a placeholder with no substantive content. The principles template requires 7 mandatory sections: Identity, Voice, Flow, Calibration, Principles, Tools, and NO_RESPONSE. None are present. evidence (2) {'file': 'system.md', 'quote': 'test only'} {'file': 'templates/principles.md', 'quote': 'Prompt structure: 7 sections in `system.md` + `examples.md` ... Identity + Mission, Voice, Flow, Calibration, Principles, Tools, NO_RESPONSE'}
BP-2	MEDIUM	PASS	Example coverage and cap (7 base scenarios + conditional, ≤20 total) examples.md contains 15 examples covering all 7 base scenarios (happy path, resource/link delivery, objection handling, disqualification, emotional/sensitive, re-engagement, off-topic) plus two conditional scenarios (keyword trigger in Example 7, price objection in Example 4). Total count is 15, within the ≤20 cap.
BP-3	HIGH	N/A	Examples align with the flow system.md is a placeholder ('test only') and contains no flow definition. Without a flow to map against, this rule cannot be evaluated. Once system.md is populated with a Flow section, this check will apply.
BP-4	CRITICAL	N/A	No internal contradictions in system.md system.md is a placeholder ('test only') with no substantive content. There are no rules to contradict. This check will apply once system.md is populated.
BP-5	CRITICAL	PASS	No cross-file contradictions Although system.md is a placeholder, examples.md, keywords.json, resources.json, program.json, objections.md, and knowledge_base.md are internally consistent. Examples demonstrate behavior (e.g., Example 1 shows presencial pricing, Example 11 shows online exterior pricing) that aligns with program.json pricing rules. Keywords in keywords.json (e.g., 'regalo', 'taller', 'parte 1') are demonstrated in examples.md (Examples 7, 2, 1 respectively). No file contradicts another under a shared precondition.
BP-6	MEDIUM	PASS	Voice consistency across examples All 15 examples use consistent voice: warm, direct, voseo (Argentine Spanish), minimal emojis (mostly 🙂, 🌿, ❤️), conversational tone, and similar message length. No jarring tonal shifts between examples.
BP-7	CRITICAL	N/A	Unguarded actions (PAT-004) system.md is a placeholder ('test only') and contains no flow steps or action instructions. Without a Flow section defining actions, this rule cannot be evaluated. Once system.md is populated, this check will apply to risky actions (sending links, qualifying, booking).
BP-8	HIGH	N/A	No stale version language in examples system.md is a placeholder with no flow definition to compare against. Examples cannot be checked for staleness without a current flow definition. This check will apply once system.md is populated.
BP-9	MEDIUM	PASS	No duplicated instructions system.md is a placeholder ('test only') with no instructions to duplicate. Knowledge files (objections.md, keywords.json, program.json, knowledge_base.md) each have a single canonical home for their instructions. No duplication detected across files.
BP-10	MEDIUM	N/A	Rule-vs-principle balance system.md is a placeholder ('test only') and contains no Principles section. This check will apply once system.md is populated with behavioral guidance (tone, flow, conversational style) vs. hard rules (facts, safety, compliance).

Checks determinísticos

Check	Sec	Estado	Notas
6a	1.8	PASS	NO_RESPONSE present (limits not checked, --no-db)
6c	3.x	PASS	2 lines
6d	1.2	PASS	15 examples
6e	1.3	N/A	no Principles section
6g	PAT-006	FAIL	keywords defined but no handling in system.md
6h	Anti-pat	PASS	no 'burbuja'
6i	Anti-pat	PASS	no HTML comments
6j	Anti-pat	PASS	no em-dashes
6k	PAT-006	PASS	no tool syntax leak
6l	Resources	PASS	no placeholder URLs
6m	Hygiene	PASS	no audit metadata in prompt files
6n	PAT-008	PASS	URL forms consistent across files
6q	PAT-001	PASS	no instruction duplication into examples.md, keywords.json, program.json, resources.json
6r	Keyword-drift	FAIL	2 in keywords.json + recent digest, never named in system.md: ['respiracion', 'sky']; (5 stale drift entr(ies) ignored — no recent digest mention)
6s	Hygiene	PASS	no expired dates in live SDK
6t	Coverage	N/A	no Principles or Flujo section found in system.md

canal — · sync 2026-07-31

293

Digests

37 en últimos 14d

Cambios pedidos / pendientes

del checklist

304

Threads

en el canal

2026-07-31

Última sync

del digest

Cosas nuevas (digests recientes)

Fecha	Tema	Tags
2026-07-30	whatsapp leads processing 30 jul	whatsapp-leads, data-processing, ledger-management
2026-07-30	active course schedule parte 1 status	course-schedule, parte-1, reference-data
2026-07-30	course schedule cleanup parte 1	course-scheduling, agent-config, parte-1, data-cleanup
2026-07-29	8 new whatsapp leads july 29	leads, whatsapp, shared-phone, automated
2026-07-28	whatsapp leads processing july 28	whatsapp-leads, deduplication, automation
2026-07-27	lucas aol agent lead volume conversion drop	conversion-issue, lead-quality, funnel-analysis, shared-phone-leads
2026-07-27	weekly funnel report elartedevivir jul 20 26	funnel-performance, conversion-metrics, content-strategy, keyword-analysis
2026-07-27	weekly performance report jul27 lucas aol	metrics, performance-report, conversion-concern
2026-07-27	whatsapp shared phone lead ingestion jul 27	lead-processing, whatsapp, automation, data-management
2026-07-27	weekly funnel report jul20 26 cortex	metrics, performance-report, conversion-analysis, content-strategy
2026-07-26	whatsapp lead grace gimenez notified	whatsapp-leads, deduplication, high-quality-lead
2026-07-25	whatsapp shared phone leads processing resume	whatsapp-leads, deduplication, automation
2026-07-24	whatsapp lead processing sql error	whatsapp-leads, sql-error, blocker
2026-07-24	new course venues and dates jul24 aug	schedule-management, venue-expansion, program-update
2026-07-24	course schedule purge and refresh jul24	schedule-management, program-update, deployment
2026-07-24	whatsapp lead processing sql error recovery	bug, sql, whatsapp-leads, deduplication
2026-07-23	whatsapp lead processing sql timeout blocking	bug, blocking, database, whatsapp-leads
2026-07-23	whatsapp lead processing sql timeout blocker	infrastructure, blocker, whatsapp-leads, database
2026-07-22	whatsapp lead processing silent run	whatsapp, leads, automation, maintenance
2026-07-22	course date cleanup july 22	course-schedule, data-cleanup, program-management

Cambios pedidos por el creador / pendientes

ID	Estado	Cambio pedido
C9	pendiente	Si existe ultimo_pendiente → no saludar, retomar desde ese paso
C10	pendiente	Si pasan 12-48h y lead responde "hola/sí/ok" → no saludar, retomar último pendiente
F2	pendiente	Si contexto_previo=true → NO ejecutar M1 (saludo). Continuar desde ultimo_pendiente
Y4	pendiente	"Hola" y "Lucas AOL" tenían link presencial viejo `1ZodB7D` / ambiguo `1yFkCfx`

sentiment del cliente → Ninjo · scoreado ahora (2026-07-31 15:37:47) · modelo claude-sonnet-4-6 · ventana 7d

Sentiment score

neutral

Bajo

Churn risk

del lado del cliente

Cambios pedidos

pendientes en checklist

Volumen cliente

agente: 127 convs

Matriz de volumen

enganchado sano

Cliente activo con tono ok — buena señal de retención.

Sentiment del cliente

📋 Sin señal de sentimiento del cliente: el único contacto atribuible al equipo (Maca Coronel) es una solicitud operativa neutra de mantenimiento de datos; todos los demás digests son output interno de Ninjo Bot/cortex sin voz del cliente. CS debe proactivamente buscar feedback dado el contexto de 0 conversiones en la semana del 21–27 jul, que es una señal de riesgo latente aunque no expresada por el cliente.

Señal	Valor	Evidencia (cita del cliente)
Enojado con la plataforma	no	—
Es queja	no	—
Queja constructiva (accionable)	no	—

Evidencia citada

Señal	Cita textual	Fecha
Única interacción del cliente identificada: solicitud operativa rutinaria de limpieza de fechas de cursos, sin carga emocional	“None”	2026-07-30

Cambios pedidos por el creador (Métrica 1)

Un creador que pide cambios concretos está enganchado (mejor señal que el silencio).

ID	Estado	Cambio pedido
C9	pendiente	Si existe ultimo_pendiente → no saludar, retomar desde ese paso
C10	pendiente	Si pasan 12-48h y lead responde "hola/sí/ok" → no saludar, retomar último pendiente
F2	pendiente	Si contexto_previo=true → NO ejecutar M1 (saludo). Continuar desde ultimo_pendiente
Y4	pendiente	"Hola" y "Lucas AOL" tenían link presencial viejo `1ZodB7D` / ambiguo `1yFkCfx`