mirror of
https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools.git
synced 2026-06-18 07:19:35 +00:00
bcf545c22e
Security Curator (4 modules) — جدار الحماية الأول
- secret_redactor: 11 patterns (GitHub PAT, OpenAI/Anthropic/Supabase/WhatsApp/Moyasar/Sentry/Google/AWS/private keys); never returns raw secret
- patch_firewall: blocks .env / credentials.json / RSA keys; scans added lines for secret patterns
- trace_redactor: masks phones (+966...) and emails for PII safety
- tool_output_sanitizer: cleans tool outputs before they hit ledger/Proof Pack/UI/observability
Growth Curator (5 modules) — التحسين الذاتي
- message_curator: grades Arabic messages (0..100), detects 8 risky phrases, suggests Saudi-tone skeleton
- playbook_curator: scores playbooks by outcome (accept/reply/meeting/deal); winner/promising/needs_work/archive
- mission_curator: scores completed missions; ship_it_widely/iterate/rework_or_retire
- skill_inventory: deterministic 23-skill catalog across 5 layers
- curator_report: weekly Arabic summary "ماذا تعلمنا هذا الأسبوع"
Meeting Intelligence (5 modules) — ذكاء الاجتماعات
- transcript_parser: accepts Google Meet entries OR plain "Speaker: text" format
- meeting_brief: 6-section pre-meeting brief in Arabic (objective/questions/objections/offer/next-step)
- objection_extractor: 8 categories (price/timing/authority/trust/integration/competitor/results/complexity)
- followup_builder: email + WhatsApp drafts; live_send_allowed=False always
- deal_risk: 0..100 score from objections + missing next-step + decision-maker absence + days-since-touch
Model Router (5 modules) — موجّه النماذج
- provider_registry: 7 providers (Claude Sonnet/Haiku, GPT-4-class, GPT-4o-mini, Gemini Pro, Azure OAI KSA-region, Local Qwen Arabic-tuned)
- task_router: 10 task types × routing decisions with reasons_ar
- cost_policy: bulk → low; output > 1500 tokens → high
- fallback_policy: high-sensitivity workloads prefer KSA-region/self-hosted FIRST
- usage_dashboard: deterministic demo of all task routes
Connector Catalog (3 modules) — كتالوج التكاملات
- 14 connectors (WhatsApp Cloud, Gmail, Calendar, Google Meet, Moyasar, LinkedIn Lead Forms, Google Business Profile, X API, Instagram, Sheets, CRM, Website Forms, Composio, MCP Gateway)
- Each has launch_phase (1-4), risk_level, allowed_actions, blocked_actions, Arabic risk dossier
- WhatsApp blocks cold_send_without_consent; Moyasar blocks store_card_number; MCP requires allowlist
Agent Observability (5 modules) — مراقبة الوكلاء + التقييمات
- trace_events: SHA256-hashes user/company IDs; sanitizes payload/output before logging
- safety_eval: 7 rules (guarantee, scarcity_fake, medical_claim, financial, regulatory, personal_data, urgency); 0..100 → safe/needs_review/blocked
- saudi_tone_eval: positive markers (هلا, لاحظت, يناسبك) vs negative (تحية طيبة وبعد, synergy, leverage); arabic_ratio bonus
- eval_pack: 5 curated cases with expected verdicts
- cost_tracker: per workflow/provider/task_type aggregation
Routers (6 new) — 30 endpoints
- /api/v1/security-curator/{demo, redact, inspect-diff, sanitize-output}
- /api/v1/growth-curator/{skills/inventory, messages/grade, messages/improve, messages/duplicates, missions/next, report/weekly, report/demo}
- /api/v1/meeting-intelligence/{brief, brief/demo, transcript/summarize, followup/draft, deal-risk}
- /api/v1/model-router/{providers, tasks, route, cost-class, usage/demo}
- /api/v1/connector-catalog/{catalog, summary, status, risks, {key}}
- /api/v1/agent-observability/{trace/build, safety/eval, tone/eval, evals/run}
Tests (6 new files, 76 tests)
- test_security_curator: 16 tests (PAT detect, key redact, env diff block, payload scan, trace mask)
- test_growth_curator: 16 tests (Arabic grade, risky phrases, dup detect, playbook scoring, mission recommend, weekly report)
- test_meeting_intelligence: 13 tests (transcript parse, brief sections, objection extract, followup drafts, deal risk)
- test_dealix_model_router: 11 tests (every task → ≥1 provider, KSA-region for high sensitivity, cost class, primary override)
- test_agent_observability: 12 tests (trace hashing, safety verdicts, tone scoring, eval pack)
- test_connector_catalog: 11 tests (≥12 connectors, every has risk/blocked actions, WA cold-send blocked, Moyasar card-storage blocked)
Docs (8 new + 1 updated)
- AGENT_SECURITY_CURATOR.md (Arabic)
- GROWTH_CURATOR_STRATEGY.md (Arabic)
- MEETING_INTELLIGENCE.md (Arabic)
- MODEL_PROVIDER_ROUTER.md (Arabic)
- CONNECTOR_CATALOG.md (Arabic)
- AGENT_OBSERVABILITY_EVALS.md (Arabic)
- PRIVATE_BETA_LAUNCH_TODAY.md (Arabic) — go-checklist + offer + risks
- DEMO_SCRIPT_12_MINUTES.md (Arabic) — minute-by-minute demo flow
- FIRST_20_OUTREACH_MESSAGES.md (Arabic) — 7 personas + 3 follow-ups, all under safety/tone evals
- DEALIX_100_PERCENT_LAUNCH_PLAN.md — added §34 Self-Improving Agent Platform + §35 Private Beta Launch
Landing
- landing/private-beta.html — Arabic RTL, dark theme, pricing, 11 demo endpoints, safety banner
Test results
- 76/76 new tests pass
- Full suite: 663 passed, 2 skipped (missing API keys, unrelated)
- 0 existing tests broken
Safety
- All 6 layers honor approval-first, draft-only, no-live-send
- Hash user/company IDs before any trace
- No secrets in logs/embeddings/traces (3-layer defense: redactor + sanitizer + firewall)
- Saudi tone eval rejects "تحية طيبة وبعد" + "synergy" auto-corporate language
- Safety eval blocks "ضمان 100%" + medical claims + fake urgency
- Connector Catalog: WhatsApp blocks cold-send, Moyasar blocks card storage, MCP requires allowlist
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
99 lines
3.7 KiB
Markdown
99 lines
3.7 KiB
Markdown
# Growth Curator Strategy — مدير التحسين الذاتي للنمو
|
||
|
||
> **الفكرة (مستلهمة من Hermes Curator):** كل أسبوع، Dealix يراجع ما كتبه ونفذه، يدمج المتشابه، يأرشف الضعيف، ويقترح المهمة التالية. لا يحتاج المالك أن يفكر كل أسبوع "ماذا أحسّن؟".
|
||
|
||
## 1. الوحدات
|
||
|
||
| الوحدة | الدور |
|
||
|--------|------|
|
||
| `message_curator` | يقيّم كل رسالة عربية (0..100) ويحدد publish/needs_edit/reject. يكشف العبارات المخاطرة + يقترح صيغة بديلة. |
|
||
| `playbook_curator` | يقيّم playbooks بناءً على outcomes (accept/reply/meeting/deal) ويُصنّف winner/promising/needs_work/candidate_archive. |
|
||
| `mission_curator` | يقيّم نتائج الميشن (TTV, opportunities, drafts, meetings, revenue) ويقرر ship_it_widely/iterate/rework. |
|
||
| `skill_inventory` | فهرس deterministic لكل قدرات Dealix (20+ skill عبر 5 طبقات). |
|
||
| `curator_report` | تقرير عربي أسبوعي يجمع الكل. |
|
||
|
||
## 2. Message Grading
|
||
|
||
`grade_message(text, sector, channel)` يفحص:
|
||
- محتوى عربي (≥30%).
|
||
- طول معقول (12-80 كلمة).
|
||
- خلوّ من 8 عبارات محظورة (ضمان 100%, آخر فرصة، ...).
|
||
- إشارات أسلوب طبيعي سعودي (تحية + لاحظت/شفت + يناسبك/تحب).
|
||
- WhatsApp: لا "عميل عزيز" ولا "لجميع العملاء".
|
||
- bonus لذكر القطاع.
|
||
|
||
## 3. Playbook Scoring
|
||
|
||
```
|
||
score = 100 * (
|
||
0.10 * accept_rate
|
||
+ 0.20 * reply_rate
|
||
+ 0.30 * meeting_rate
|
||
+ 0.40 * deal_rate
|
||
)
|
||
```
|
||
|
||
تيرز:
|
||
- ≥70: **winner**
|
||
- ≥40: **promising**
|
||
- ≥20: **needs_work**
|
||
- <20: **candidate_archive**
|
||
|
||
استراتيجية الـrecommend: **promising أولاً** (winners مشبعة)، ثم winner، ثم بقية الـtiers.
|
||
|
||
## 4. Mission Scoring
|
||
|
||
`score_mission` يجمع:
|
||
- opportunities × 2 (max 20)
|
||
- drafts_approved × 4 (max 20)
|
||
- meetings_booked × 5 (max 20)
|
||
- revenue / 5,000 (max 20)
|
||
- risks_blocked × 5 (max 10)
|
||
- TTV ≤10min: +10، ≤60min: +5
|
||
|
||
## 5. Mission Recommender
|
||
|
||
- لو ما شُغّل `first_10_opportunities` → ابدأ به.
|
||
- لو الأولوية `fill_pipeline` → `meeting_booking_sprint`.
|
||
- لو `rescue_lost_revenue` → `revenue_leak_rescue`.
|
||
- لو `expand_partners` → `partnership_sprint`.
|
||
- الافتراضي: `customer_reactivation`.
|
||
|
||
## 6. Weekly Curator Report
|
||
|
||
`build_weekly_curator_report(messages, playbooks, missions, sector)` يُرجع:
|
||
|
||
```json
|
||
{
|
||
"summary_ar": [
|
||
"تمت مراجعة 24 رسالة، 5 playbook، و2 مهمة هذا الأسبوع.",
|
||
"تم اقتراح أرشفة 4 رسالة ضعيفة الجودة.",
|
||
"تم اكتشاف 3 أزواج رسائل متشابهة (للدمج).",
|
||
],
|
||
"messages": {"total", "publishable", "needs_edit", "to_archive", "duplicate_pairs"},
|
||
"playbooks": {"total", "winners", "promising", "to_merge_groups"},
|
||
"missions": {"total", "ship_it_widely", "iterate", "rework_or_retire"},
|
||
"next_playbook": {"recommended_id", "title_ar", "reason_ar"},
|
||
"recommended_next_action_ar": "..."
|
||
}
|
||
```
|
||
|
||
## 7. Endpoints
|
||
|
||
```
|
||
GET /api/v1/growth-curator/skills/inventory
|
||
POST /api/v1/growth-curator/messages/grade
|
||
POST /api/v1/growth-curator/messages/improve
|
||
POST /api/v1/growth-curator/messages/duplicates
|
||
POST /api/v1/growth-curator/missions/next
|
||
POST /api/v1/growth-curator/report/weekly
|
||
GET /api/v1/growth-curator/report/demo
|
||
```
|
||
|
||
## 8. حدود
|
||
|
||
- لا يصدر LLM call.
|
||
- لا يحذف playbooks تلقائياً — يقترح فقط.
|
||
- لا يدمج بدون موافقة.
|
||
- التقرير يبقى actionable: ≤7 أسطر summary.
|