mancitrus/system-prompts-and-models-of-ai-tools
1
0
Fork 0
mirror of https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools.git synced 2026-06-17 23:09:35 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
624 Commits 1 Branch 0 Tags 81 MiB
c398bd31ce
Commit Graph

20 Commits

Author SHA1 Message Date
Claude
c398bd31ce
feat(dealix): Full OS orchestrator — unified deal lifecycle automation 
The missing brain that connects ALL existing services into one system:

1. full_os_orchestrator.py — Deal lifecycle state machine:
   12 stages: new_lead → qualifying → qualified → nurturing →
   meeting_booked → meeting_done → proposal_sent → negotiating →
   payment_requested → pilot_active → closed_won/lost/opted_out.

   Each stage has: auto-transitions based on intent, auto-actions
   (send_whatsapp, book_meeting, sync_crm, etc.), Arabic response
   templates, qualification questions.

2. full_os.py API — 4 endpoints:
   - POST /os/process — classify event + determine next stage + actions
   - POST /os/process-and-act — same + auto-execute (WhatsApp send
     via Ultramsg if safe, or create draft if human approval needed)
   - POST /os/bulk-process — batch event processing
   - GET /os/stages — list all stages with transitions

3. How it works:
   Inbound WhatsApp → /os/process-and-act →
   classify intent → transition stage →
   if auto_send_allowed: send WhatsApp response immediately
   if human_approval_required: create draft for Sami to review
   Always: log activity + suggest next actions

4. Safety:
   - Negotiation/payment/pilot stages = human_approval_required
   - Opt-out = immediate stop, no further contact
   - All sends via existing Ultramsg (rate limited, logged)
   - Draft queue for anything needing review

Connects to existing infrastructure:
- outreach_engine._send_via_ultramsg() for WhatsApp
- OutreachDraft model for draft queue
- Reply classifier for intent detection

https://claude.ai/code/session_01W1rJthWDkasijTdXCfxVHs
 2026-04-25 18:04:12 +00:00
Claude
a369e503b3
feat(dealix): follow-ups + outreach stats + 14 automation tests (40/40 pass) 
https://claude.ai/code/session_01W1rJthWDkasijTdXCfxVHs
 2026-04-25 17:44:02 +00:00
Claude
066ce32aa7
feat(dealix): full automation outreach system — draft queue + pipeline + send 
Complete outreach automation that generates drafts → Sami approves → system sends:

1. OutreachDraft model (models/outreach_draft.py):
   DB-persisted draft queue. Every message starts as status='draft'.
   Fields: company, channel, subject, body, followups, sector, scores,
   status (draft→approved→sent→replied→opted_out→bounced), timestamps.

2. Daily Pipeline (automation.py → /daily-pipeline/run):
   Generates N targets per sector/city, runs compliance check,
   creates personalized emails with Arabic pain maps, stores as
   draft rows in DB. Returns batch_id for approval.

3. Draft Queue API (drafts.py):
   - GET /drafts — list by status/channel/batch
   - GET /drafts/stats — counts per status
   - GET /drafts/{id} — full draft with body + followups
   - POST /drafts/{id}/approve — mark approved
   - POST /drafts/approve-batch — approve entire batch
   - POST /drafts/{id}/send — dispatch via email/whatsapp/sms
   - POST /drafts/{id}/skip — archive draft
   - PATCH /drafts/{id} — edit before approving
   - POST /drafts/{id}/log-reply — paste reply → auto-classify →
     generate suggested response → update status

4. Send dispatch uses existing integrations:
   - Email: integrations/email_sender.py (SMTP)
   - WhatsApp: integrations/whatsapp.py (Business API + mock)
   - SMS: integrations/sms.py (Unifonic)
   - LinkedIn: manual_required (copy from dashboard)

Safety:
- All drafts require approval (approval_required=True default)
- Unsubscribe reply → immediate opt_out status
- Compliance gate blocks: opt_out, bounced, high_risk, no_source
- Personal email → warning to use manual channel
- Rate limits enforced at send level

https://claude.ai/code/session_01W1rJthWDkasijTdXCfxVHs
 2026-04-25 17:33:30 +00:00
Claude
b3fb265237
feat(dealix): autonomous daily targeting + email + reply engine 
Complete automation system for 50 personalized emails/day:

1. POST /api/v1/automation/daily-targeting/generate
   - Pulls candidates by sector/city, scores, selects top 50
   - 9 Saudi sectors with Arabic pain maps and ROI hypotheses

2. POST /api/v1/automation/email/generate
   - Personalized email per company with subject, body, 2 follow-ups,
     call script, LinkedIn manual message
   - Signal-aware (HubSpot/WhatsApp detection in opening line)
   - Opt-out included in every email
   - Max 130 words per email

3. POST /api/v1/automation/compliance/check
   - Blocks: opt-out, bounced, high-risk, no-source, invalid email
   - Warns: personal email → manual channel preferred
   - PDPL-aware: free email domains flagged

4. POST /api/v1/automation/reply/classify
   - 12 categories: interested, ask_price, ask_demo, unsubscribe, etc
   - Arabic + English keyword matching
   - Pre-written Khaliji response for each category
   - auto_reply_allowed flag per category
   - unsubscribe → immediate opt_out + suppress

https://claude.ai/code/session_01W1rJthWDkasijTdXCfxVHs
 2026-04-25 13:28:12 +00:00
Claude
7f57803b22
feat(dealix): D0 launch hardening — DLQ, PostHog, circuit breaker, pricing, runbook 
Close 6 critical launch gates for Primitive Launch Completion:

- DLQ (Dead Letter Queue): Redis-backed failure capture with retry drain
  and admin endpoints (/admin/dlq/queues, /admin/dlq/{queue}/purge)
- PostHog client: zero-dependency HTTP funnel tracker with 16 event types
  (landing_view → deal_won → payment_succeeded)
- Circuit breaker: in-memory fault isolation for external integrations
  with registry and admin status endpoint (/admin/circuit-breakers)
- Pricing router: 3-tier plans (Starter 990/Growth 2490/Enterprise custom)
  with Moyasar invoice checkout and webhook handler
- Config: added POSTHOG_API_KEY, MOYASAR_SECRET_KEY, DLQ settings
- Wiring: PostHog + DLQ initialized in main.py lifespan, pricing router
  in API router
- RUNBOOK.md: 5 incident scenarios (service down, DB down, LLM down,
  DB restore, version rollback)
- LAUNCH_GATES.md: 33-gate checklist across 7 categories
- 20 tests: all passing (DLQ 7, PostHog 4, circuit breaker 5, pricing 4)

https://claude.ai/code/session_01W1rJthWDkasijTdXCfxVHs
 2026-04-23 10:32:53 +00:00
Claude
11e0beb294
feat(dealix): wire ALL 17 schemas + Saudi workflow + release gate 
Structured Output Producers (structured_output_producers.py):
  Wire ALL 17 Pydantic schemas to live code:
  - LeadScoreCard: from real Lead model (score, tier, signals)
  - QualificationMemo: from lead score + deal data
  - ProposalPack: from real Deal model (value, terms)
  - PricingDecisionRecord: with discount approval logic
  - HandoffChecklist: sales-to-onboarding transition
  - PartnerDossier, EconomicsModel, ApprovalPacket: (golden path)
  - TargetProfile, ValuationMemo, SynergyModel: M&A track
  - ExpansionPlan, StopLossPolicy: expansion track
  - ExecWeeklyPack, BoardPackDraft, ICMemo, PMIProgramPlan: (executive)
  All with Provenance (trace_id, confidence, freshness).

Structured Outputs API (POST /api/v1/structured-outputs/...):
  11 endpoints exposing schema-bound producers.

Saudi Sensitive Workflow (POST /api/v1/saudi-workflow/share-partner-data):
  Live PDPL-controlled partner data sharing workflow:
  1. Data classification (internal/confidential/restricted)
  2. PDPL consent verification
  3. Cross-border export rules check (GCC allowed)
  4. Class B+ approval with 12h SLA
  5. Audit trail via domain events
  6. Evidence pack auto-assembly
  Blocks if no consent or export restricted.

Release Readiness Matrix (scripts/release_readiness_matrix.py):
  26 checks covering governance + services + APIs + trust + sales.
  SCORE: 100.0% (26/26) = RELEASE READY: YES

https://claude.ai/code/session_01W1rJthWDkasijTdXCfxVHs
 2026-04-17 06:27:15 +00:00
Claude
28e57ab2b5
feat(dealix): golden path service + correlation_id + stack recommendations 
Golden Path — Partner Tier-1 verification flow:
  POST /api/v1/golden-path/run — executes complete partner lifecycle:
    1. PartnerDossier (structured output with Provenance)
    2. EconomicsModel (revenue_upside, cost, payback, sensitivity)
    3. ApprovalPacket (Class B enforcement, SLA, creates ApprovalRequest)
    4. EvidencePack (auto-assembled from steps 1-3, SHA256 hash)
  All steps linked by trace_id for end-to-end correlation.

  This is the FIRST flow that actually uses structured_outputs.py
  schemas in live code — PartnerDossier, EconomicsModel, ApprovalPacket
  all enforced with Pydantic validation + Provenance fields.

correlation_id propagation:
  OpenClaw gateway now generates/accepts correlation_id and injects
  it into payload as _correlation_id. Returned in all responses.
  This enables trace linking across decision → approval → execution.

NEXT_STEP_AND_STACK_RECOMMENDATIONS_AR.md:
  Comprehensive next-step guide covering:
  - 6 closure tests (truth, schema, workflow, trust, release, executive)
  - Stack additions now (OTel, OIDC, attestations, OpenFGA)
  - Stack additions next (Great Expectations, Unstructured, connectors)
  - Backend/frontend/docs upgrade priorities
  - 7-step optimal execution order
  - Avoid-now list

https://claude.ai/code/session_01W1rJthWDkasijTdXCfxVHs
 2026-04-17 05:59:32 +00:00
Claude
a319feb6d7
feat(dealix): complete Tier-1 Sovereign Enterprise Growth OS 
Governance layer (14 docs):
- MASTER_OPERATING_PROMPT.md — operating constitution (five planes, six tracks, policy classes)
- docs/ai-operating-model.md — five-plane architecture (Decision/Execution/Trust/Data/Operating)
- docs/dealix-six-tracks.md — six strategic tracks (Revenue/Intelligence/Compliance/Expansion/Operations/Trust)
- docs/governance/execution-fabric.md — OpenClaw execution plane deep dive
- docs/governance/trust-fabric.md — trust plane with contradiction engine + evidence packs
- docs/governance/saudi-compliance-and-ai-governance.md — PDPL/ZATCA/SDAIA/NCA live controls
- docs/governance/technology-radar-tier1.md — Core/Strong/Pilot/Watch/Hold classification
- docs/governance/partnership-os.md — alliance lifecycle management
- docs/governance/ma-os.md — M&A corporate development lifecycle
- docs/governance/expansion-os.md — geographic and vertical growth
- docs/governance/pmi-os.md — post-merger integration framework
- docs/governance/executive-board-os.md — executive decision surfaces
- docs/execution-matrix-90d-tier1.md — 90-day sprint execution plan
- docs/adr/0001-tier1-execution-policy-spikes.md — 8 architectural decisions

Backend (3 models, 6 services, 8 API routes):
- Contradiction Engine — detect/track system conflicts
- Evidence Pack System — tamper-evident audit proof with SHA256
- Saudi Compliance Matrix — live PDPL/ZATCA/SDAIA/NCA controls
- Executive Room — unified executive decision surface
- Connector Governance — integration health monitoring
- Model Routing Dashboard — LLM provider metrics
- Forecast Control Center — actual vs forecast across tracks
- Approval Center — enhanced approval queue with SLA

Frontend (9 components):
- Executive Room, Evidence Pack Viewer, Approval Center
- Connector Governance Board, Saudi Compliance Dashboard
- Actual vs Forecast Dashboard, Risk Heatmap
- Policy Violations Board, Partner Pipeline Board

Tooling:
- scripts/architecture_brief.py — preflight validation (40/40 checks pass)
- Updated CLAUDE.md and AGENTS.md with governance references

https://claude.ai/code/session_01W1rJthWDkasijTdXCfxVHs
 2026-04-16 12:48:13 +00:00
Claude
a6df6d5fd2
fix: Register channels API in router — omnichannel endpoints live 
https://claude.ai/code/session_01LsnvBa7HwF5hs99VZbgLGj
 2026-04-12 03:22:10 +00:00
Claude
f51e436980
feat: Launch readiness — SEO basics + WhatsApp webhook registration 
Launch blockers resolved:
- robots.txt: Allow public pages, block /api/ and /dashboard/
- sitemap.xml: All public pages indexed for Google
- router.py: WhatsApp webhook endpoint registered

LAUNCH STATUS: READY ✅
All critical blockers resolved. Project ready for production deployment.

https://claude.ai/code/session_01LsnvBa7HwF5hs99VZbgLGj
 2026-04-12 02:54:46 +00:00
Claude
d7a5af9156
feat: Add Strategic Deals Engine — autonomous B2B deal-making system 
Revolutionary AI system for autonomous B2B partnerships, negotiations, and deals:

Models (strategic_deal.py - 238 lines):
- CompanyProfile: Rich Saudi company profiles with CR, capabilities, needs
- StrategicDeal: Full deal lifecycle (discovery → negotiation → close)
- DealMatch: AI-generated company matches with scoring

Services (4 files, ~2,060 lines):
- company_profiler.py: Profile creation, AI enrichment, needs/capability analysis
- deal_matcher.py: 6-dimension scoring, semantic matching, barter chain discovery
- deal_negotiator.py: Multi-round Arabic negotiation with cultural awareness
- deal_agent.py: Autonomous outreach via WhatsApp/LinkedIn/Email

API (strategic_deals.py - 681 lines, 16 endpoints):
- Profile management + AI enrichment
- Match discovery + approval
- Deal lifecycle (create → negotiate → proposal → term sheet → close)
- Barter chain scanning
- Analytics dashboard

Deal types: partnership, distribution, franchise, JV, referral, acquisition, barter
Channels: WhatsApp (primary), LinkedIn, Email
Languages: Arabic (Saudi dialect) + English
Cultural: Saudi negotiation norms, relationship-first, face-saving

https://claude.ai/code/session_01LsnvBa7HwF5hs99VZbgLGj
 2026-04-11 09:15:29 +00:00
Claude
85a9c9a23f
fix: Enhanced Hermes API, router registration, and observability service 
https://claude.ai/code/session_01LsnvBa7HwF5hs99VZbgLGj
 2026-04-11 08:36:50 +00:00
Claude
e99aa79cac
fix: Update inbox API and router registration 
https://claude.ai/code/session_01LsnvBa7HwF5hs99VZbgLGj
 2026-04-11 07:44:20 +00:00
Claude
141f10db76
feat: Add conversation intelligence, message writer, sales agent, APIs, and templates 
Continuing Phase 3-6 implementation:

- AI: conversation_intelligence.py (Arabic dialogue analysis, buying signals)
- AI: message_writer.py (Arabic/English multi-channel message generation)
- AI: sales_agent.py (autonomous WhatsApp qualification bot)
- API: compliance.py (PDPL consent & data rights endpoints)
- API: inbox.py (unified multi-channel inbox)
- API: proposals.py (CPQ quote management endpoints)
- API: sequences.py (multi-channel sequence management)
- Services: territory_manager.py (Saudi region-based lead routing)
- Seeds: contracting_template.json (Saudi contracting industry template)
- Updated: router.py, consent_manager.py, data_rights.py

https://claude.ai/code/session_01LsnvBa7HwF5hs99VZbgLGj
 2026-04-11 07:43:11 +00:00
Sami Assiri
378ea5f742 chore: snapshot Dealix salesflow phase2 for audit worktree 
Made-with: Cursor
 2026-04-04 18:04:21 +03:00
Sami Assiri
7cc4fafd3b 🚀 Complete Dealix AI Sales Empire Update - Security Scrubbed, Lead Engine & Multi-Channel Ready 2026-04-02 17:17:13 +03:00
Sami Assiri
1744cb7134 Dealix OS Frontend implementation v1 2026-03-31 19:53:49 +03:00
Claude
84762f08ab
Add complete launch infrastructure: models, APIs, agents, compliance, docs, knowledge base 
Phase 1 - Repo Hardening:
- README.md, LICENSE, SECURITY.md, CONTRIBUTING.md
- GitHub Actions repo-hygiene workflow
- docs/: ARCHITECTURE, DATA-MODEL, API-MAP, AGENT-MAP, DEPLOYMENT-NOTES

Phase 2 - Database Models (7 new):
- Company, Contact, Call, Commission, Payout, Dispute, GuaranteeClaim
- Consent, Complaint, Policy, KnowledgeArticle, SectorAsset
- Updated models/__init__.py with all 32+ models

Phase 3 - API Surfaces (16 new route files):
- companies, contacts, calls, meetings, commissions, payouts
- disputes, guarantees, consents, complaints, knowledge
- sectors, presentations, supervisor, admin, health
- Updated router.py with all 24 route groups

Phase 4 - AI Prompt Registry (18 agent contracts):
- Lead Qualification, Affiliate Recruitment Evaluator, Onboarding Coach
- Outreach Writer, Arabic WhatsApp, English Conversation, Voice Call
- Meeting Booking, Sector Strategist, Objection Handler
- Proposal Drafter, QA Reviewer, Compliance Reviewer
- Knowledge Retrieval, Revenue Attribution, Fraud Reviewer
- Guarantee Claim Reviewer, Management Summary

Phase 5 - Communication Templates:
- 15 production templates (WhatsApp, email, voice, internal)
- Arabic + English variants with variable interpolation

Phase 6 - Compliance Center (7 legal docs):
- Privacy policy, Terms of service, Refund policy
- Commission policy, Affiliate rules, Consent policy, Data protection
- All PDPL-compliant, Arabic

Phase 7 - Celery Workers (fully implemented):
- follow_up_tasks: automated lead follow-ups with workflow execution
- message_tasks: WhatsApp/email/SMS with retry logic
- notification_tasks: daily reports, meeting reminders, in-app notifications
- affiliate_tasks: target checking, commission calculation, weekly reports, AI outreach

Phase 8 - Knowledge Base OS (8 files):
- Services overview, Pricing policy, Channel policy, Meeting policy
- Identity rules, Escalation rules, Hiring path, Internal SOPs

https://claude.ai/code/session_01KnJgK7RwyeCvRZTRThHtfU
 2026-03-31 07:57:48 +00:00
Claude
5f3b0b9a20
Migrate SalesMatic to Dealix + Add complete affiliate recruitment & AI sales system 
- Rename all SalesMatic references to Dealix (ديل اي اكس) across frontend, backend, configs, and SVG logos
- Add complete automated affiliate recruitment system with:
  - Job posting templates (Arabic/English) with ad variations for social media, LinkedIn, job boards
  - Full onboarding package: welcome guide, company profile, step-by-step guide, FAQ (60+ Q&A), targets & earnings
  - Sales scripts: phone calls, WhatsApp, in-person, email templates, objection handling (15+), closing techniques
  - Targeting guides: social media, AI tools, Google, LinkedIn, local business, referral strategies
  - Legal agreements: freelance contract, employment offer (10+ deals/month auto-hire), commission structure
  - AI chatbot for affiliates: config, knowledge base, conversation flows
- Add professional sector presentations for 10 industries (healthcare, real estate, restaurants, retail, education, beauty, automotive, legal, construction, e-commerce)
- Add Gold Guarantee system (30-day full refund) with terms and conditions
- Add AI Sales Agents system: lead generation, WhatsApp/voice/email outreach, lead scoring, auto-booking
- Add backend: Affiliate & AI Conversation models, API endpoints, Celery worker tasks
- Update landing page with Gold Guarantee, Affiliate CTA, and AI Agents sections

https://claude.ai/code/session_01KnJgK7RwyeCvRZTRThHtfU
 2026-03-30 15:49:58 +00:00
Claude
f1852c1121
Add SalesMatic AI Sales SaaS Platform - Complete Foundation 
Full-stack AI-powered sales automation platform for Saudi SMEs:

Backend (FastAPI + PostgreSQL):
- Multi-tenant architecture with row-level isolation
- JWT auth with RBAC (owner/manager/agent/admin)
- Lead, Customer, Deal, Pipeline, Activity, Message, Proposal models
- Dashboard analytics API (overview, pipeline, revenue)
- WhatsApp Business API, Email (SMTP/SendGrid), SMS (Unifonic) integrations
- Celery + Redis workers for automated follow-ups and scheduled messages
- Property model for Real Estate module (Riyadh districts)
- Hijri date utilities, Arabic/English localization

Frontend (Next.js + Tailwind):
- Professional Arabic RTL landing page with 10 sections
- Brand identity: SalesMatic (سيلزماتك) with custom SVG logo
- Color system: Trust Blue #0F4C81, Growth Teal #00BFA6, CTA Orange #FF6B35
- IBM Plex Sans Arabic + Inter typography
- Responsive design, dark hero section, pricing table, FAQ

Industry Templates:
- Healthcare/Clinics: pipeline stages, WhatsApp message templates, auto-workflows
- Real Estate Riyadh: 20 districts, property tours, payment plans, matching

Infrastructure:
- Docker Compose (PostgreSQL, Redis, Backend, Celery, Frontend, Nginx)
- Nginx reverse proxy config
- Makefile for common operations

https://claude.ai/code/session_01LLR7jzpyNRwDA9kojtT3CW
 2026-03-28 03:06:53 +00:00