| Métrica | this 7d | prior 7d | Δ |
|---|---|---|---|
| Activas | 59 | 58 | +1.7% |
| Nuevas | 24 | 30 | -20.0% |
| Link sent | 2 | 2 | +0.0% |
| Calls booked | 2 | 0 | — |
| Booked/Link % | 100.0% | 0.0% | +100.0pp |
| Booked/Activas % | 3.4% | 0.0% | +3.4pp |
| Booked/Nuevas % | 8.3% | 0.0% | +8.3pp |
| Revenue variable | $4.34 | $2.56 | +69.5% |
| Período | Activas | Nuevas | Link sent | Calls booked | Booked/Link | Booked/Activas | Booked/Nuevas |
|---|---|---|---|---|---|---|---|
| Semana actual (7d) | 59 | 24 | 2 | 2 | 100.0% | 3.4% | 8.3% |
| Semana anterior (7d) | 58 | 30 | 2 | 0 | 0.0% | 0.0% | 0.0% |
| Día | Activas | Nuevas | Link sent | Calls booked | Booked/Link | Booked/Activas | Booked/Nuevas |
|---|---|---|---|---|---|---|---|
| 06-02 | 8 | 3 | 0 | 0 | — | 0.0% | 0.0% |
| 06-01 | 9 | 3 | 0 | 1 | — | 11.1% | 33.3% |
| 05-31 | 5 | 3 | 1 | 0 | 0.0% | 0.0% | 0.0% |
| 05-30 | 6 | 4 | 0 | 0 | — | 0.0% | 0.0% |
| 05-29 | 10 | 2 | 1 | 0 | 0.0% | 0.0% | 0.0% |
| 05-28 | 12 | 4 | 0 | 0 | — | 0.0% | 0.0% |
| 05-27 | 9 | 5 | 0 | 1 | — | 11.1% | 20.0% |
| 05-26 | 8 | 4 | 0 | 0 | — | 0.0% | 0.0% |
| 05-25 | 9 | 5 | 0 | 0 | — | 0.0% | 0.0% |
| 05-24 | 5 | 1 | 0 | 0 | — | 0.0% | 0.0% |
| 05-23 | 9 | 4 | 0 | 0 | — | 0.0% | 0.0% |
| 05-22 | 13 | 7 | 0 | 0 | — | 0.0% | 0.0% |
| 05-21 | 8 | 6 | 1 | 0 | 0.0% | 0.0% | 0.0% |
| 05-20 | 6 | 3 | 1 | 0 | 0.0% | 0.0% | 0.0% |
| BP | Sev | Estado | Detalle |
|---|---|---|---|
| BP-1 | HIGH | PASS | Template compliance All 7 required sections (Identity, Voice, Flow, Calibration, Principles, Tools, NO_RESPONSE) are present in system.md and match the principles template specification. Content fits the template's intent. |
| BP-2 | MEDIUM | PASS | Example coverage and cap (7 base scenarios + conditional, ≤20 total) examples.md covers all 7 base scenarios (happy path, resource/link delivery, objection handling, disqualification, emotional lead, re-engagement, off-topic) plus two conditional scenarios (keyword trigger in Example 4, price objection in Example 5). Total count is 14 examples, well under the 20-example cap. |
| BP-3 | HIGH | PASS | Examples align with the flow Every example in examples.md walks the flow steps in order (qualify → pain → context → position → close → post-booking or terminal state) and reaches a terminal state (link sent, NO_RESPONSE, or course offered). No examples skip required steps or end mid-flow. |
| BP-4 | CRITICAL | PASS | No internal contradictions in system.md system.md contains one explicit exception that resolves potential ambiguity: the Flow section states 'Solo si la respuesta es genuinamente ambigua (un "ok"/"dale" suelto, sin contexto que indique reserva), preguntá UNA vez "pudiste agendar?"' This carve-out is documented and Example 1 demonstrates it correctly. No shared precondition produces conflicting outputs. |
| BP-5 | CRITICAL | PASS | No cross-file contradictions All SDK files agree on behavior and parameters. keywords.json declares two conditions: 'resource_with_flow' (roadmap, equipo, ceo, ops, fire, foco, testing) with send_without_permission=true, and 'contextual' (guia, aceleradora, link) with send_without_permission=false. system.md's Flow step 5 states 'Si el lead pregunta por un keyword (roadmap, guia, costos), entregá el recurso primero y después arrancá la calificación.' Example 4 (roadmap) and Example 6 (guia) both demonstrate the correct behavior: roadmap is sent immediately, guia is sent only after qualification begins. The two keyword conditions apply to different preconditions (different keywords) and coexist correctly. |
| BP-6 | MEDIUM | PASS | Voice consistency across examples All examples use the same persona, vocabulary, formality level, and rioplatense dialect. Tone is consistently sharp, direct, and professional. Message length, punctuation, and emoji usage (none) are uniform across all examples. |
| BP-7 | CRITICAL | PASS | Unguarded actions (PAT-004) All risky actions in system.md's Flow are paired with inline guards. Step 4 (Posicionar) includes 'La explicación va siempre, independientemente de cómo respondió el lead' (guard: always explain). Step 5 (Cerrar) includes 'SOLO una vez que el lead aceptó la call' (guard: explicit acceptance required). Step 6 (Post-booking) includes 'Solo si la respuesta es genuinamente ambigua... preguntá UNA vez' (guard: ambiguity condition). Examples 1, 1B, 1C, 2, 4, 5, 6 all demonstrate these guards firing correctly. |
| BP-8 | HIGH | PASS | No stale version language in examples All example CTAs and closing language match the current flow definition in system.md. Post-booking messages ('bárbaro, te llega ahí el material'), link delivery format ('va [URL] cuando reserves avisame'), and NO_RESPONSE usage are all consistent with system.md's current language. |
| BP-9 | MEDIUM | PASS | No duplicated instructions Each behavioral instruction has a single canonical location. The 25-word limit is stated once in Voice. The NO_RESPONSE rule is stated once in Principles (item 7). The keyword handling rule is stated once in Flow. No instruction is restated in multiple places; cross-references are minimal and appropriate. |
| BP-10 | MEDIUM | PASS | Rule-vs-principle balance Behavioral guidance (tone, flow, conversational style) is expressed via Voice section and examples. Hard rules are reserved for factual constraints (revenue thresholds, pricing rules, eligibility) and safety boundaries (never invent data, no diagnosis, minor disengagement). The balance is appropriate for the principles template. |
| Check | Sec | Estado | Notas |
|---|---|---|---|
| 6a | 1.8 | PASS | NO_RESPONSE present (limits not checked, --no-db) |
| 6c | 3.x | PASS | 105 lines |
| 6d | 1.2 | PASS | 16 examples |
| 6e | 1.3 | FAIL | 14 principles, cognitive overload |
| 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 | 2 em-dash(es) in 2 file(s); likely incidental |
| 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 | 5 in keywords.json + recent digest, never named in system.md: ['ceo', 'ops', 'fire', 'foco', 'testing']; (1 stale drift entr(ies) ignored — no recent digest mention) |
| 6s | Hygiene | PASS | no expired dates in live SDK |
| 6t | Coverage | WARN | 10/14 principle(s) without example: #2 No des precios de, #3 Si alguien parece menor, #6 No des coaching, estrategia, #7 Respondé con la palabra, #8 Si el mensaje solo; 5/6 flow step(s) without example: #1 Calificar, #2 Dolor, #3 Contexto, #4 Posicionar, #6 Post-booking |
| Fecha | Tema | Tags |
|---|---|---|
| 2026-06-01 | bot calendar booking detection resource delivery failure | bug, calendar-integration, resource-delivery, automation |
| 2026-06-01 | weekly agent performance and lead follow up actions | reporting, metrics, lead-management, follow-up |
| 2026-06-01 | bot not reading calendar bookings resource delivery | bug, bot-behavior, calendar-integration, resources |
| 2026-05-26 | bot flow pause after followup automation issue | bug, automation, workflow, followup |
| 2026-05-25 | weekly funnel report may 18 24 | metrics, funnel, weekly-report, keywords, action-items |
| 2026-05-25 | weekly funnel report keywords and closings | metrics, reporting, keywords, sales-pipeline |
| 2026-05-22 | barbaro duplication fix post booking flow | bot-responses, follow-up-automation, prompt-adjustment |
| 2026-05-22 | clarify flow exit condition barbaro case | bot-flow-logic, clarification |
| 2026-05-22 | bot response fixes barbaro duplication prompt adjustment | bot-quality, prompt-optimization, copy-fixes |
| 2026-05-21 | bot message quality issues link duplication | bot-behavior, message-quality, bug |
| 2026-05-19 | agent alert logic removal | agent-behavior, alert-logic, bug-fix |
| 2026-05-18 | revenue threshold call cancellations | lead-qualification, revenue-filtering |
| 2026-05-18 | weekly funnel report may 11 17 volume surge | funnel-analytics, lead-recovery, keyword-analysis, conversion |
| 2026-05-18 | weekly funnel report may 11 17 | metrics, funnel, leads, action-items |
| 2026-05-18 | revenue filter implementation outcomes | qualification, revenue-filter, outcome |
| 2026-05-13 | assessment form url migration | post-booking, forms, urgent |
| 2026-05-13 | slack booking notification missing | alerts, slack, debugging |
| 2026-05-13 | post booking copy alex mention and split format | post-booking, copy, chunked-messages, custom-split-prompt, bug |
| 2026-05-13 | call booked slack alert refinement | alerts, slack, platform-feature |
| 2026-05-13 | post booking copy format fix | post-booking, copy, automation, agent-output |
Sin pendientes en el checklist ✅
| Señal | Valor | Evidencia (cita del cliente) |
|---|---|---|
| Enojado con la plataforma | sí | — |
| Es queja | sí | — |
| Queja constructiva (accionable) | sí | — |
| Señal | Cita textual | Fecha |
|---|---|---|
| Bug reportado por el cliente: bot no detecta bookings de calendario ni envía recursos | “None” | 2026-06-01 |
| Integración de calendario (desplegada en febrero) no funciona — el cliente lo identifica y escala | “None” | 2026-06-01 |
| Cliente activo en el canal, participa en decisiones operativas y propuestas de mejora (seguimiento de leads, cold open, prompt) | “None” | — |
| Alto volumen de iteraciones y propuestas abiertas sugiere que el cliente sigue invertido en hacer funcionar la plataforma | “None” | — |
Sin cambios pendientes en el checklist ✅