Benjamin_Boenisch/breakpilot-core
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
212 Commits 4 Branches 0 Tags
8b2e9ac3287a68fd92ab4713ad89ef4f1fba04ae
Commit Graph

17 Commits

Author SHA1 Message Date
Sharang Parnerkar
8b2e9ac328 content(pitch-deck): tidy slide text — remove OVH, generalize issue tracker, add live support, Mac Studio option
All checks were successful
Build pitch-deck / build-push-deploy (push) Successful in 1m4s
Details
CI / go-lint (push) Has been skipped
Details
CI / python-lint (push) Has been skipped
Details
CI / nodejs-lint (push) Has been skipped
Details
CI / test-go-consent (push) Successful in 32s
Details
CI / test-python-voice (push) Successful in 34s
Details
CI / test-bqas (push) Successful in 32s
Details 
Solution slide:
- Continuous Code Security: "Jira tickets" -> "tickets in the issue tracker of your choice"
- German Cloud / Full Integration: removed OVH (now "BSI cloud DE or FR"),
  removed "AI task creation from audio", added "Live support via Jitsi (video) and Matrix (chat)",
  "Mac Mini" -> "Mac Mini/Studio"

Products / Modular toolkit slide:
- Regional bubble: "OVH FR" -> "FR"

How It Works:
- Cloud step: removed OVH and "pre-configured Mac Mini" mentions

Engineering deep dive:
- "Docker Containers" stat -> "Services"; "Coolify -> Hetzner" -> "orca -> Hetzner"
- "Dockerfiles / Fully containerized" stat -> "Infra Components / orca (Rust) + infisical + pg + qdrant"
- devopsStack: Coolify -> orca (Rust), Docker Compose -> Private Registry (registry.meghsakha.com),
  HashiCorp Vault -> Infisical, EU-Cloud list drops OVH
- Service Architecture Infrastructure section: add orca (Rust), Infisical, Private Registry
- Footer note drops OVH

Chat / Presenter (consistency):
- chat/route.ts system prompt: OVH removed, Jira-Integration -> Issue-Tracker-Integration
- presenter-faq.ts + presenter-script.ts: OVH references removed across all answers,
  Jira mentioned alongside GitLab/Linear/Gitea as examples, Mac Mini -> Mac Mini/Studio

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-14 16:14:40 +02:00
Benjamin Admin
1bd57da627 feat: Presenter-Script aktualisiert + COMPLAI + Cookie-Generator (12 Module) 
Presenter-Script komplett synchronisiert:
- COMPLAI statt ComplAI überall
- 12 Module aufgezählt (inkl. DSR, Consent, Notfallpläne, Cookie-Generator)
- 110 Gesetze statt 84
- 25.000 Prüfaspekte statt Controls
- SOM 24 Mio. statt 7,2 Mio.
- Gründung Jul/Aug 2026 statt Q4
- Umlaute korrigiert (standardmäßig, wählbar, Lücken, abschließen)

Folie 3 (Cover): COMPLAI groß über BrandName-Komponente
Folie 7: +Cookie-Generator als 12. Modul
Onepager: +Cookie-Generator
DB: Metrics auf 12 Module

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-27 21:46:06 +01:00
Benjamin Admin
f2b225106d fix: Umlaute überall korrekt + Meilenstein-Daten aktualisiert 
Umlaute: ä, ö, ü in i18n.ts, presenter-script.ts, presenter-faq.ts
  (oe→ö, ae→ä, ue→ü, ~60 Ersetzungen gesamt)

Meilensteine (DB):
  - Plattform-Entwicklung: Januar 2026
  - Compliance SDK 8 Module: März 2026
  - RAG 110 Regularien: April 2026
  - 2 Pilottestkunden: Januar bis Juli 2026
  - GmbH-Gründung: Jul/Aug 2026

KI-Pipeline: 110+ Verordnungen, 25.000+ Prüfaspekte, 1.500+ Pflichten

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-27 19:33:47 +01:00
Benjamin Admin
8aca75118c fix: Zahlen und Texte korrigiert — Problem, USP, KPIs 
Problem-Text: Neuer Wortlaut (US-KI-Anbieter, 30.000+ Unternehmen,
egal ob 10 oder 5.000 MA, Datenmissbrauch-Risiko)

USP: "auf deutscher oder franzoesischer Cloud"

KPI-Kacheln: 170+ Originaldokumente entfernt, 40.000→25.000+
Sicherheitskontrollen, 84→110 Gesetze & Regularien (nur EU+DACH),
761K→500K+ Lines of Code

Konsistent in: i18n (DE+EN), Executive Summary (Slide+PDF),
Competition, AI Pipeline, SDK Demo, Regulatory Landscape,
Presenter Script, FAQ

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-27 11:54:26 +01:00
Benjamin Admin
f514667ef9 feat: Modularer Baukasten + mitarbeiterbasiertes Pricing + Savings-ROI 
Produkte: 8 Module als Baukasten (Code Security, CE-Risiko, Compliance-Docs,
Audit Manager, LLM, Academy, Jira, Full Compliance)
Pricing: nach MA (<50: 15k, 50-250: 30k, 250+: 40-50k EUR/Jahr)
Cloud Standard (BSI DE/OVH FR), Mac Mini nur fuer <10 MA

Geschaeftsmodell: ROI-Rechnung statt HW-Amortisation
(Kunde zahlt 40-50k, spart 50-110k: Pentests, CE, Auditmanager)

So funktioniert's: Cloud-Vertrag statt HW aufstellen,
Audit vorbereiten statt Audit bestehen

Competition: Pricing-Tiers auf Cloud-Modell umgestellt
FAQ: Alle 65+-Referenzen + alte Tier-Preise entfernt

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-26 18:10:11 +01:00
Benjamin Admin
9e712465af feat: Audit-Abweichungen End-to-End in Solution + Executive Summary 
Nach dem Audit: Haupt-/Nebenabweichungen automatisch abarbeiten —
Rollen zuweisen, Stichtage, Tickets, Nachweise einfordern,
Eskalation an GF. Kein Excel, kein Hinterherlaufen.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-26 17:40:50 +01:00
Benjamin Admin
bf22d436fb feat: Problem-Narrative — KI-Dilemma statt Bussgeld-Zahlen 
Echte KMU-Sorgen statt irrelevante 4.1B-Statistik:
1. KI-Dilemma: Wollen KI, aber keinen Copilot/Claude im Code
2. Patriots Act: Selbst EU-Server der US-Player unsicher
3. Regulierungs-Tsunami: 5+ Gesetze, 50k/Jahr Stichproben

Quote: "Maschinenbauer brauchen eine KI-Loesung, die in Deutschland
laeuft, ihren Code schuetzt und Compliance automatisiert."

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-26 17:34:15 +01:00
Benjamin Admin
f689b892de feat: Komplette Story-Ueberarbeitung — KMU-Maschinenbau-Narrative 
Problem: Regulierungs-Tsunami (5+ Gesetze, persoenliche GF-Haftung),
jaehrliche Stichproben (50k+ EUR/Jahr), Datensouveraenitaet (0 DE-Alternativen)

Loesung: Kontinuierliche Code-Security statt Stichproben,
Compliance auf Autopilot (VVT, TOMs, DSFA, Loeschfristen, CE),
Deutsche Cloud (BSI DE / OVH FR), Jitsi, Matrix, Jira-Integration

ROI: Kunde zahlt 50k/Jahr, spart 50k+ (Pentests, CE, Auditmanager)

DB: Funding 1M EUR, SOM 24M EUR

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-26 17:25:40 +01:00
Benjamin Admin
2f2338c973 feat: Executive Summary ueberarbeitet — Kernfeatures statt Hardware 
- Funding: 1 Mio EUR (DB), Use of Funds: 35% Vertrieb, 20% Workshops
- SOM: 7.2M → 24M EUR (DB), Wettbewerbs-Benchmark
- Executive Summary: Mac Mini/Studio entfernt, stattdessen:
  Full Compliance GPT, ISMS, CE-Risikobeurteilung, DAST/SAST/SBOM,
  VVT, TOMs, DSFA, Loeschfristen, Jira-Integration
- USP: Full KI Compliance Check + CE Software + DevSecOps
- Geschaeftsmodell-Text aktualisiert

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-26 17:01:25 +01:00
Benjamin Admin
10eb0ce5f9 feat: Maschinenbau als Branche + Zahlen 9→10 Branchen 
- Maschinenbau als neue Kern-Branche in Matrix (15 Regularien)
- Alle Branchen-Counts aktualisiert (synced mit breakpilot-lehrer)
- 9→10 Branchen ueberall konsistent (i18n, KPIs, Presenter, FAQ)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-26 15:56:19 +01:00
Benjamin Admin
32616504a6 feat: RAG-Zahlen korrigiert + Branchen-Regulierungs-Matrix 
- Alle Zahlen aktualisiert: 170+ Originaldokumente, 40.000+ Controls,
  84 Regularien, 9 Branchen (statt 57 Module / 19 Regularien / 2.274 Texte)
- Neue Folie: Regulatorische Landschaft mit Branchen-Regulierungs-Matrix
- Konsistent in: Solution, Executive Summary (Slide+PDF), Competition,
  AI Pipeline, SDK Demo, Presenter Script, FAQ

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-26 15:40:44 +01:00
Benjamin Admin
4bce3724f2 feat: Executive Summary Onepager-Slide mit PDF-Download 
Neue Folie als erste Content-Slide (nach Intro) mit kompakter
Investor-Uebersicht: Problem/Loesung, KPIs, Markt, Team, Funding.
PDF-Download via window.print() ohne zusaetzliche Dependencies.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-03-26 15:00:54 +01:00
Benjamin Admin
c1a8b9d936 feat(pitch-deck): update Engineering + AI Pipeline slides with current data 
Engineering slide:
- Woodpecker CI → Gitea Actions + Coolify
- Stats: 481K LOC, 10 containers, 48+ modules, 14 Dockerfiles
- Infrastructure: Hetzner + SysEleven (BSI) + OVH, no US providers
- Service architecture: compliance-only (Frontend, Backend, Infra)

AI Pipeline slide:
- 38+ indexed regulations, 6,259 extracted controls, 325+ obligations
- 6 Qdrant collections, 2,274+ chunks
- UCCA policy engine (45 rules, E0-E3 escalation)
- LLM: 120B on OVH + 1000B on SysEleven (BSI), via LiteLLM
- QA: PDF-QA pipeline, Gitea Actions CI, Coolify deploy

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-20 23:08:34 +01:00
Benjamin Admin
87b00a94c0 feat(pitch): add SDK demo slide with screenshot gallery + inline preview 
- New annex slide 'annex-sdk-demo' with auto-scrolling screenshot gallery
  (22 real screenshots from Müller Maschinenbau demo project)
- Browser chrome mockup, fullscreen view, thumbnail strip navigation
- Inline SDK dashboard preview on Product slide
- Seed script for creating demo data + taking Playwright screenshots
- Presenter script for SDK demo narration

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-20 20:51:17 +01:00
Benjamin Admin
978f0297eb feat(pitch): rewrite pitch content — Cloud SDK as core product 
Restructure all pitch messaging: Cloud-based SDK platform with 65+ modules
is the CORE product. Mac Mini/Studio repositioned as side product for small
firms. Updated presenter scripts (20 slides), FAQ (35 entries), and chat
system prompt with new Kernbotschaften covering company compliance, Code/CE
scanning, EU AI hosting, Jira integration, and additional features.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-20 18:10:33 +01:00
Benjamin Admin
bcbceba31c feat(presenter): add browser TTS (Web Speech API) + fix German umlauts 
- Integrate Web Speech API into usePresenterMode for text-to-speech
- Speech-driven paragraph advancement (falls back to timer if TTS unavailable)
- TTS toggle button (Volume2/VolumeX) in PresenterOverlay
- Chrome keepAlive workaround for long speeches
- Voice selection: prefers premium/neural voices, falls back to any matching lang
- Fix all German umlauts across presenter-script, presenter-faq, i18n, route.ts

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-20 12:11:12 +01:00
Benjamin Admin
3a2567b44d feat(pitch-deck): add AI Presenter mode with LiteLLM migration and FAQ system
All checks were successful
CI / go-lint (push) Has been skipped
Details
CI / python-lint (push) Has been skipped
Details
CI / nodejs-lint (push) Has been skipped
Details
CI / test-go-consent (push) Successful in 27s
Details
CI / test-python-voice (push) Successful in 25s
Details
CI / test-bqas (push) Successful in 25s
Details
CI / Deploy (push) Successful in 4s
Details 
- Migrate chat API from Ollama to LiteLLM (OpenAI-compatible SSE)
- Add 15-min presenter storyline with bilingual scripts for all 20 slides
- Add FAQ system (30 entries) with keyword matching for instant answers
- Add IntroPresenterSlide with avatar placeholder and start button
- Add PresenterOverlay (progress bar, subtitle text, play/pause/stop)
- Add AvatarPlaceholder with pulse animation during speaking
- Add usePresenterMode hook (state machine: idle→presenting→paused→answering→resuming)
- Add 'P' keyboard shortcut to toggle presenter mode
- Support [GOTO:slide-id] markers in chat responses
- Dynamic slide count (was hardcoded 13, now from SLIDE_ORDER)
- TTS stub prepared for future Piper integration

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-20 11:45:55 +01:00