mirror of
https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools.git
synced 2026-06-18 15:29:36 +00:00
Locks Dealix's positioning forever and closes the operational gap between "great product" and "great customer experience": onboarding, connectors, support SLA, incidents, customer success cadence, and companies/marketers landing pages. Positioning Lock (3 docs) - POSITIONING_LOCK.md (Arabic): Saudi Revenue Execution OS category lock; one-liner; primary buyers (companies + agencies/marketers); wedge (First 10 Opportunities + Proof Pack); 5 approved claims; 5 prohibited categories; 5 modes; 5 bundles; 6 "what Dealix is NOT" rules - PROHIBITED_CLAIMS.md (Arabic): 8 categories of forbidden marketing language (guaranteed results, scraping, full automation, bypass approvals, competitor attacks, legal/financial promises, medical language, exaggerated speed) + technical enforcement (safety_eval + tone_eval + quality_review_gate + tool_action_planner + test_positioning_lock.py) - APPROVED_MARKET_MESSAGING.md (Arabic): tagline + 30-second elevator pitch + 5 headlines + competitor positioning table + 4-segment outreach templates + LinkedIn/X social posts + slogan bank Customer Ops (6 modules) - onboarding_checklist: 8-step Pilot onboarding (select_goal → select_bundle → company_intake → connect_channels → upload_or_source → risk_review → first_service_run → first_proof_pack) with progress tracking + state advancement - connector_setup_status: 11 connectors (Gmail/Calendar/Sheets/Moyasar/WhatsApp/Forms/LinkedIn-LeadForms/GBP/CRM/Meet/Instagram) each with default_mode (draft_only/manual/ingest_only/approved_execute), launch phase, and blocking flag; ready_for_first_service gate requires no blocking connectors missing AND ≥1 connected - support_ticket_router: 4-tier P0/P1/P2/P3 classification with Arabic+English keyword matching; auto-classifies "تسريب", "إرسال بدون موافقة", "بدون موافقتي", "live charge", "unauthorized" as P0; per-priority Arabic first-response templates; SLA targets per priority - sla_tracker: SLA targets per priority (P0=30min/4h, P1=2h/24h, P2=8h/72h, P3=24h/1week); record_sla_event with strict event-type validation; classify_sla_breach for individual tickets; build_sla_health_report aggregates with verdict (healthy/watch/critical based on breach_rate) - customer_success_cadence: 6 cadence types (weekly_check_in, monthly_proof_review, QBR, at_risk_alert, renewal_30/7_day); build_at_risk_alert with risk_score 0..100 from days_inactive + drafts_pending + last_proof_pack_days_ago; build_customer_success_plan with 30-day per-bundle cadences (growth_starter, executive_growth_os, partnership_growth) - incident_router: SEV1/SEV2/SEV3 with first_action_minutes + comm_cadence; auto-SEV1 on has_data_leak OR has_unauthorized_send; SEV2 on affected_customers≥5; canonical 5-step response plan (freeze live actions / notify founder / create incident channel / review Action Ledger / PDPL 72h notification) + per-severity additional steps + post-mortem template New Operator Modes (2) - self_growth_mode: re-exports targeting_os.self_growth_mode (DEALIX_ICP_FOCUSES, recommend_dealix_targets, build_self_growth_daily_brief, build_weekly_learning_report) + operator-tier reminders (no cold WhatsApp even for Dealix itself, all drafts approval-first, no scraping) - service_delivery_mode: orchestrates service_tower workflow + revenue_launch.pilot_delivery + customer_ops.sla_tracker; build_service_delivery_brief (per-service template), build_sla_status_for_delivery (breach detection on open tickets), build_post_delivery_handoff (5-step transition to Customer Success cadence) Router (1 new) — 20 endpoints - /api/v1/customer-ops/* — onboarding (checklist/update-step/demo), connectors (catalog/summary/update/demo), support (priorities/classify/route/first-response), sla (event/classify-breach/health-report/health-report-demo), incidents (triage/response-plan), cs (weekly-check-in/at-risk-alert/success-plan) Customer-facing pages (1 new, 1 already-existed-preserved) - landing/companies.html (NEW): Saudi B2B companies pitch — Approval-first, no scraping, no cold WhatsApp; 4 bundles (Growth Starter / Data to Revenue / Executive Growth OS / Full Growth Control Tower); Proof Pack section; safety + compliance section - landing/marketers.html (existed): preserved as-is — agency/marketers Agency Growth OS path Tests (2 new files, 44 tests) - test_customer_ops.py: 31 tests * 4 onboarding (8 steps, advancement, unknown step error, complete-all) * 5 connectors (critical connectors present, blocking_missing detection, ready gate, validation, write) * 8 support (P0 security, P0 unauthorized send, P1 service down, P2 connector, P3 default, empty input, route includes SLA, P0 first-response Arabic with 30 min) * 6 SLA (event validates, log appends, breach detection within/exceeded targets, health report aggregation, critical verdict) * 4 incidents (data leak SEV1, unauthorized send SEV1, ≥5 customers SEV2, single customer SEV3, SEV1 plan includes PDPL) * 4 customer success (weekly check-in talking points Arabic, at-risk high severity, at-risk low severity, success plan per bundle including growth_starter and executive_growth_os Founder Shadow Board) - test_positioning_lock.py: 13 tests * positioning_lock.md exists with category + "ليس CRM" + "ليس بوت" * prohibited_claims.md exists with "نضمن" + "scraping" * approved_market_messaging.md has Approval-first + PDPL + Saudi Tone + Proof Pack * landing pages contain NO positive forbidden claims (negative restatements like "no auto-DM" in safety sections allowed) * companies.html includes "Approval-first" + "Proof Pack" * agency-partner.html OR marketers.html exists * private-beta.html does NOT promise guarantees * REVENUE_TODAY_PLAYBOOK emphasizes Approval-first * positioning_lock lists all 5 bundles * positioning_lock lists all 5 modes (CEO + Growth Manager + Agency Partner + Self-Growth + Service Delivery) Customer Ops Docs (5 new) - ONBOARDING_RUNBOOK.md (Arabic): 8 onboarding steps + day-by-day Day1-Day5 + 11 connector states + acceptance criteria - SUPPORT_SLA.md (Arabic): 4 priority tiers + auto-classification keywords + Arabic first-response templates + weekly review process - INCIDENT_RESPONSE.md (Arabic): SEV1/SEV2/SEV3 logic + canonical response plan + per-severity additional steps + post-mortem template + Arabic communication templates + auto-actions - CUSTOMER_SUCCESS_PLAYBOOK.md (Arabic): cadence types + weekly agenda (25 min) + at-risk scoring formula + per-bundle cadence + QBR + renewal flow + health score formula - CONNECTOR_SETUP_GUIDES.md (Arabic): all 11 connectors with scopes + step-by-step + acceptance criteria + troubleshooting table Test results - 44/44 new tests pass - Full suite: 949 passed, 2 skipped (missing API keys, unrelated) - 0 existing tests broken Safety + integration - All 20 customer-ops endpoints: approval_required=True, live_send_allowed=False - support_ticket_router HARD-CLASSIFIES "تسريب", "إرسال بدون موافقة", "live charge", "unauthorized" as P0 (founder owner, 30-min first response) - incident_router auto-promotes to SEV1 on has_data_leak or has_unauthorized_send (regardless of affected_customers count) - onboarding_checklist requires WhatsApp connector (blocking) before ready_for_first_service - connector_setup_status default_mode is draft_only/manual/ingest_only — never live - Positioning Lock test_positioning_lock.py enforces: * 5 bundles must be listed in POSITIONING_LOCK.md * 5 modes must be listed * landing pages must not contain positive forbidden claims (8 phrases) * companies.html must mention Approval-first + Proof Pack - self_growth_mode reminds operator: no cold WhatsApp even for Dealix itself - service_delivery_mode integrates SLA tracker before declaring delivery success Integration with everything before - Customer Ops onboarding integrates Service Bundles (autonomous_service_operator.service_bundles) - Customer Ops connectors mirror connector_catalog risk_levels + add operational state machine - Support classifier integrates with security_curator (P0 on secret leaks) + revenue_launch.payment_manual_flow (P0 on unauthorized charge) - Customer Success metrics flow from agent_observability + revenue_launch.proof_pack_template - Service Delivery Mode wires service_tower.workflow + revenue_launch.pilot_delivery + sla_tracker into one pipeline - Self-Growth Mode wraps targeting_os.self_growth_mode with operator-tier safety reminders - Companies + Marketers pages enforce POSITIONING_LOCK headlines Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
133 lines
4.0 KiB
Python
133 lines
4.0 KiB
Python
"""SLA tracker — measure first-response, MTTR, weekly support health."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import time
|
|
from typing import Any
|
|
|
|
# Default SLA targets per priority (minutes for first_response, hours for resolution).
|
|
SLA_TARGETS: dict[str, dict[str, float]] = {
|
|
"P0": {"first_response_min": 30, "resolution_hours": 4},
|
|
"P1": {"first_response_min": 120, "resolution_hours": 24},
|
|
"P2": {"first_response_min": 480, "resolution_hours": 72},
|
|
"P3": {"first_response_min": 1440, "resolution_hours": 168},
|
|
}
|
|
|
|
|
|
def record_sla_event(
|
|
*,
|
|
ticket_id: str,
|
|
priority: str,
|
|
event: str,
|
|
log: list[dict[str, Any]] | None = None,
|
|
) -> dict[str, Any]:
|
|
"""
|
|
Record an SLA event.
|
|
|
|
`event` = "opened" | "first_response" | "resolved" | "escalated".
|
|
"""
|
|
if event not in {"opened", "first_response", "resolved", "escalated"}:
|
|
raise ValueError(f"Unknown SLA event: {event}")
|
|
entry: dict[str, Any] = {
|
|
"ticket_id": ticket_id,
|
|
"priority": priority,
|
|
"event": event,
|
|
"ts": time.time(),
|
|
}
|
|
if log is not None:
|
|
log.append(entry)
|
|
return entry
|
|
|
|
|
|
def classify_sla_breach(
|
|
*,
|
|
priority: str,
|
|
minutes_to_first_response: float | None = None,
|
|
hours_to_resolve: float | None = None,
|
|
) -> dict[str, Any]:
|
|
"""Classify whether SLA was breached for a single ticket."""
|
|
target = SLA_TARGETS.get(priority, SLA_TARGETS["P3"])
|
|
breaches: list[str] = []
|
|
|
|
if (minutes_to_first_response is not None
|
|
and minutes_to_first_response > target["first_response_min"]):
|
|
breaches.append(
|
|
f"first_response: {minutes_to_first_response:.0f} > "
|
|
f"{target['first_response_min']} min"
|
|
)
|
|
|
|
if (hours_to_resolve is not None
|
|
and hours_to_resolve > target["resolution_hours"]):
|
|
breaches.append(
|
|
f"resolution: {hours_to_resolve:.1f}h > "
|
|
f"{target['resolution_hours']}h"
|
|
)
|
|
|
|
return {
|
|
"priority": priority,
|
|
"breached": bool(breaches),
|
|
"breaches": breaches,
|
|
}
|
|
|
|
|
|
def build_sla_health_report(
|
|
*,
|
|
tickets: list[dict[str, Any]] | None = None,
|
|
) -> dict[str, Any]:
|
|
"""Build a weekly SLA health report from a list of tickets."""
|
|
tickets = tickets or []
|
|
by_priority: dict[str, dict[str, Any]] = {}
|
|
total_tickets = len(tickets)
|
|
total_breached = 0
|
|
|
|
for t in tickets:
|
|
priority = str(t.get("priority", "P3"))
|
|
bucket = by_priority.setdefault(priority, {
|
|
"count": 0, "breaches": 0,
|
|
"total_first_response_min": 0.0,
|
|
"total_resolution_hours": 0.0,
|
|
"responded_count": 0, "resolved_count": 0,
|
|
})
|
|
bucket["count"] += 1
|
|
ftr = t.get("first_response_min")
|
|
ttr = t.get("resolution_hours")
|
|
b = classify_sla_breach(
|
|
priority=priority,
|
|
minutes_to_first_response=ftr,
|
|
hours_to_resolve=ttr,
|
|
)
|
|
if b["breached"]:
|
|
bucket["breaches"] += 1
|
|
total_breached += 1
|
|
if ftr is not None:
|
|
bucket["total_first_response_min"] += float(ftr)
|
|
bucket["responded_count"] += 1
|
|
if ttr is not None:
|
|
bucket["total_resolution_hours"] += float(ttr)
|
|
bucket["resolved_count"] += 1
|
|
|
|
# Compute averages.
|
|
for p, b in by_priority.items():
|
|
if b["responded_count"]:
|
|
b["avg_first_response_min"] = round(
|
|
b["total_first_response_min"] / b["responded_count"], 1,
|
|
)
|
|
if b["resolved_count"]:
|
|
b["avg_resolution_hours"] = round(
|
|
b["total_resolution_hours"] / b["resolved_count"], 2,
|
|
)
|
|
|
|
breach_rate = round(total_breached / total_tickets, 3) if total_tickets else 0.0
|
|
|
|
return {
|
|
"total_tickets": total_tickets,
|
|
"total_breached": total_breached,
|
|
"breach_rate": breach_rate,
|
|
"by_priority": by_priority,
|
|
"verdict": (
|
|
"healthy" if breach_rate < 0.10
|
|
else "watch" if breach_rate < 0.25
|
|
else "critical"
|
|
),
|
|
}
|