| Métrica | this 7d | prior 7d | Δ |
|---|---|---|---|
| Activas | 747 | 715 | +4.5% |
| Nuevas | 287 | 408 | -29.7% |
| Link sent | 44 | 65 | -32.3% |
| Calls booked | 18 | 13 | +38.5% |
| Booked/Link % | 40.9% | 20.0% | +20.9pp |
| Booked/Activas % | 2.4% | 1.8% | +0.6pp |
| Booked/Nuevas % | 6.3% | 3.2% | +3.1pp |
| Revenue variable | $27.20 | $30.28 | -10.2% |
| Período | Activas | Nuevas | Link sent | Calls booked | Booked/Link | Booked/Activas | Booked/Nuevas |
|---|---|---|---|---|---|---|---|
| Semana actual (7d) | 747 | 287 | 44 | 18 | 40.9% | 2.4% | 6.3% |
| Semana anterior (7d) | 715 | 408 | 65 | 13 | 20.0% | 1.8% | 3.2% |
| Día | Activas | Nuevas | Link sent | Calls booked | Booked/Link | Booked/Activas | Booked/Nuevas |
|---|---|---|---|---|---|---|---|
| 06-02 | 89 | 20 | 5 | 4 | 80.0% | 4.5% | 20.0% |
| 06-01 | 75 | 0 | 6 | 4 | 66.7% | 5.3% | — |
| 05-31 | 28 | 2 | 2 | 0 | 0.0% | 0.0% | 0.0% |
| 05-30 | 103 | 31 | 4 | 1 | 25.0% | 1.0% | 3.2% |
| 05-29 | 134 | 68 | 7 | 3 | 42.9% | 2.2% | 4.4% |
| 05-28 | 145 | 73 | 14 | 1 | 7.1% | 0.7% | 1.4% |
| 05-27 | 173 | 93 | 6 | 5 | 83.3% | 2.9% | 5.4% |
| 05-26 | 190 | 93 | 18 | 4 | 22.2% | 2.1% | 4.3% |
| 05-25 | 252 | 215 | 18 | 3 | 16.7% | 1.2% | 1.4% |
| 05-24 | 22 | 16 | 3 | 1 | 33.3% | 4.5% | 6.2% |
| 05-23 | 42 | 16 | 5 | 1 | 20.0% | 2.4% | 6.2% |
| 05-22 | 59 | 20 | 6 | 1 | 16.7% | 1.7% | 5.0% |
| 05-21 | 77 | 19 | 7 | 1 | 14.3% | 1.3% | 5.3% |
| 05-20 | 73 | 29 | 8 | 2 | 25.0% | 2.7% | 6.9% |
| BP | Sev | Estado | Detalle |
|---|---|---|---|
| BP-1 | HIGH | PASS | Template compliance meta.md declares template='scripted', which specifies a 14-section structure (identity_and_context, style_and_tone, engagement_signals, conversation_logic, happy_path_general_example, knowledge_base, prequalification_questions, trigger_keywords, lead_magnets, qualification_criteria, agent_instruction, instruction_priority, hard_rules, pre_send_checklist). The agent's system.md follows a 6-section 'principles' template structure (Identidad, Voz, Flujo, Calibración, Principios, Herramientas, TEMPLATE PRECIOS) with no engagement_signals, instruction_priority, or pre_send_checklist sections. evidence (2)
|
| BP-2 | MEDIUM | PASS | Example coverage and cap (7 base scenarios + conditional, ≤20 total) examples.md contains 23 examples, exceeding the 20-example cap. However, the agent has keywords.json (4 keywords) requiring keyword-trigger examples, and program.json declares pricing rules requiring price-objection examples. The examples cover all 7 base scenarios (happy path, resource delivery, objection handling, disqualification, emotional lead, re-engagement, off-topic) plus conditional scenarios (keyword triggers in Examples 4, 17, 18; price objections in Examples 5, 6, 19, 20). The excess is driven by legitimate conditional coverage and detailed branching scenarios (Bootcamp variants in Examples 21, 22, 23). While over 20, the coverage is complete and justified by the agent's configuration. |
| BP-3 | HIGH | PASS | Examples align with the flow All examples in examples.md follow the flow defined in system.md (Verificar → Precalificar → Contexto → Nutrir → Cerrar) and reach terminal states (link sent, NO_RESPONSE, or graceful closure). Examples progress through steps in order without skipping required stages. |
| BP-4 | CRITICAL | PASS | No internal contradictions in system.md system.md contains one potential tension: 'Regla universal: Si la verificación profesional NO se completó, verificar primero antes de cualquier acción' vs. 'Keyword triggers: Verificar vet PRIMERO, después continuar flujo principal.' However, these are not contradictory — both state that verification must occur first. The keyword rule explicitly names verification as the precondition, not an exception. No shared precondition produces conflicting outputs. |
| BP-5 | CRITICAL | PASS | No cross-file contradictions All SDK files align on behavior and data. examples.md demonstrates the flow and pricing rules from system.md correctly. keywords.json notes state 'Verificar vet primero' (matching system.md's universal rule). program.json pricing rules match TEMPLATE PRECIOS in system.md. resources.json provides the single call_admision link used consistently across examples.md and system.md. No file declares behavior or data that contradicts another under the same precondition. |
| BP-6 | MEDIUM | PASS | Voice consistency across examples All examples use the same persona (Francisco, warm and consultive), vocabulary (doc, chévere, qué bueno), formality level (casual, WhatsApp-style), and dialect (neutral Spanish, tuteo, no voseo). No jarring tonal shifts across the 23 examples. |
| BP-7 | CRITICAL | PASS | Unguarded actions (PAT-004) The primary risky action — sending the call link — is guarded in system.md: 'Nunca enviar el link directo, siempre proponer la reunión, explicar el valor y pedir permiso. Enviar solo después del sí del lead.' This guard is demonstrated consistently across Examples 1, 2, 5, 9, 19, 20, 21, 22, 23, where the agent asks 'te gustaría que te lo comparta?' and only sends the link after affirmative response ('si dale' / 'dale'). The guard is explicit and working examples confirm its intended behavior. |
| BP-8 | HIGH | PASS | No stale version language in examples All examples use current flow language and CTAs from system.md. Closing language ('me avisas si los horarios no te llegan a funcionar, estoy atento a cualquier cosa') matches the current flow definition. No stale phrases from prior versions detected. |
| BP-9 | MEDIUM | PASS | No duplicated instructions Each behavioral instruction has a single canonical home. The verification rule appears once in Flujo (step 1) and is reinforced by a principle ('Verificar siempre antes de avanzar') — this is principle + example reinforcement, not duplication. The pricing template is stated once in TEMPLATE PRECIOS and referenced in objections.md with a cross-reference, not duplicated. No instruction is restated in two locations. |
| BP-10 | MEDIUM | PASS | Rule-vs-principle balance Behavioral guidance (tone, flow, conversational style) is expressed via Voz section (principles + examples) and Flujo (flow steps with examples). Hard rules are reserved for factual constraints (programs, pricing approach, support email, link fallback). The balance is appropriate — behavior is shown through examples and principles; facts remain as rules. |
| Check | Sec | Estado | Notas |
|---|---|---|---|
| 6a | 1.8 | PASS | NO_RESPONSE present (limits not checked, --no-db) |
| 6c | 3.x | PASS | 130 lines |
| 6d | 1.2 | PASS | 27 examples |
| 6e | 1.3 | PASS | 7 principles |
| 6g | PAT-006 | WARN | non-STEP-0 keyword handling |
| 6h | Anti-pat | PASS | no 'burbuja' |
| 6i | Anti-pat | PASS | no HTML comments |
| 6j | Anti-pat | WARN | 3 em-dash(es) in 1 file(s); likely incidental |
| 6k | PAT-006 | FAIL | tool-call syntax appears as raw text in examples.md (9 line(s)) |
| 6l | Resources | PASS | no placeholder URLs |
| 6m | Hygiene | WARN | audit metadata (dates/slack refs) in 1 file(s) — adds noise to live prompt |
| 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 | 1 in keywords.json + recent digest, never named in system.md: ['METODO']; (2 stale drift entr(ies) ignored — no recent digest mention) |
| 6s | Hygiene | WARN | 2 expired date reference(s) in SDK files |
| 6t | Coverage | WARN | 3/7 principle(s) without example: #2 Un bloque = una, #6 Al presentar el programa,, #7 Si no tienes la; 3/5 flow step(s) without example: #2 Precalificar, #3 Contexto, #4 Nutrir |
| Fecha | Tema | Tags |
|---|---|---|
| 2026-06-03 | zero booking links conversion failure pattern | booking, conversion, critical-issue, zero-bookings |
| 2026-06-03 | high intent leads detected require immediate outreach | leads, high-intent, outreach, opportunity |
| 2026-06-02 | opportunities detected high intent leads | lead-qualification, opportunity, instagram |
| 2026-06-02 | daily funnel report 2026 06 02 | funnel-metrics, leads, booking-conversion, daily-report |
| 2026-06-02 | high intent leads detected scoring framework | leads, scoring, qualification |
| 2026-06-01 | keyword performance metodo avaperu 11pct conversion | keyword-analysis, conversion-rate, content-strategy |
| 2026-06-01 | high volume week funnel analysis | reporting, funnel-metrics, conversion, quality-concern |
| 2026-06-01 | manual outreach warm pool 30 leads expansion | outreach, warm-pool, content-strategy, manual-action |
| 2026-06-01 | nahiara cordoba basic incursion 4 5 profile | lead-opportunity, qualification |
| 2026-06-01 | scheduled call anesthesia strategies lead validation | call-confirmed, lead-validation, anesthesia |
| 2026-06-01 | daily funnel snapshot 70 convos 3 links 1 agenda | metrics, daily-report |
| 2026-06-01 | daily funnel snapshot 70 new convos 80 active | daily-report, funnel-metrics |
| 2026-06-01 | whatsapp agent habla argentino voseo | voice-tone, whatsapp, voseo, rioplatense, high-priority, francisco-request |
| 2026-06-01 | agent quality decline reported whatsapp discrimination | bug, quality, discrimination, pending-investigation |
| 2026-06-01 | weekly performance record 1452 leads 21 confirmed | metrics, performance, weekly-report |
| 2026-06-01 | daily funnel report jun 01 | reporting, funnel-metrics, booking-distribution |
| 2026-06-01 | agent tone dialect correction request | bug-report, agent-behavior, linguistic-issue |
| 2026-06-01 | fix 031 neutral spanish tone deployment status | deployment, agent-tone, fix, whatsapp |
| 2026-06-01 | weekly funnel performance record 21 confirmations | metrics, conversion, performance, decision |
| 2026-05-31 | daily funnel report may 31 | reporting, funnel-metrics, leads |
| ID | Estado | Cambio pedido |
|---|---|---|
| B5 | pendiente | No usar jerga rioplatense (voseo, "bacan", etc.) — neutralizar al peruano/latinoamericano. **⚠️ REGRESIÓN 2026-06-01 (ver X29)**: el agente WA volvió a usar voseo (`avisás`, `manej |
| N3.8 | pendiente | **Bot detection — filtro de auto-respuestas**: si el inbound parece auto-respuesta de otro sistema ("en este momento no estamos atendiendo", "fuera de horario", "déjanos tu consult |
| X22 | pendiente | **Unsubscribe en Messenger sigue ocurriendo** esporádicamente — plan B automático pendiente (redirect a IG DM). Victor quiere fix de raíz. Francisco confirma que no está 100% resue |
| X24 | pendiente | ~~**Booking proposal actual no convence a Victor**~~ — IMPLEMENTADO 2026-04-29 en v23/v1.4/v1.5 (ver F12, F13). Pendiente validación con synthetics + 24-48h convs reales antes de c |
| AA13 | pendiente | **Política de tono — amable y neutral SIEMPRE**, independientemente de cómo responda el lead. AVA busca neutralidad para que las respuestas se lean bien en todos los países LATAM. |
| Señal | Valor | Evidencia (cita del cliente) |
|---|---|---|
| Enojado con la plataforma | no | — |
| Es queja | sí | “el agente de WhatsApp está empezando a hablar como argentino en algunas conversaciones” |
| Queja constructiva (accionable) | sí | “Pide que se corrija para mantener un tono más neutro” |
| Señal | Cita textual | Fecha |
|---|---|---|
| Queja directa del cliente (Francisco vía Victor) sobre tono rioplatense del agente WhatsApp | “el agente de WhatsApp está empezando a hablar como argentino en algunas conversaciones” | 2026-06-01 |
| Pedido explícito de corrección — el cliente identificó el problema y comunicó la solución esperada | “Francisco quiere tono neutro — no argentino. Es pedido directo del cliente, no de Victor.” | 2026-06-01 |
| Compromiso activo del cliente con métricas y funnel — señal de enganche positivo | “None” | 2026-06-01 |
Un creador que pide cambios concretos está enganchado (mejor señal que el silencio).
| ID | Estado | Cambio pedido |
|---|---|---|
| B5 | pendiente | No usar jerga rioplatense (voseo, "bacan", etc.) — neutralizar al peruano/latinoamericano. **⚠️ REGRESIÓN 2026-06-01 (ver X29)**: el agente WA volvió a usar voseo (`avisás`, `manej |
| N3.8 | pendiente | **Bot detection — filtro de auto-respuestas**: si el inbound parece auto-respuesta de otro sistema ("en este momento no estamos atendiendo", "fuera de horario", "déjanos tu consult |
| X22 | pendiente | **Unsubscribe en Messenger sigue ocurriendo** esporádicamente — plan B automático pendiente (redirect a IG DM). Victor quiere fix de raíz. Francisco confirma que no está 100% resue |
| X24 | pendiente | ~~**Booking proposal actual no convence a Victor**~~ — IMPLEMENTADO 2026-04-29 en v23/v1.4/v1.5 (ver F12, F13). Pendiente validación con synthetics + 24-48h convs reales antes de c |
| AA13 | pendiente | **Política de tono — amable y neutral SIEMPRE**, independientemente de cómo responda el lead. AVA busca neutralidad para que las respuestas se lean bien en todos los países LATAM. |