0266dfd011
docs: Compliance Agent product roadmap — 8 phases, PoC to production
...
P0: UCCA score calibration + control relevance filter
P1: Headless browser consent test (before/after cookie banner) + 80+ services
P2: Scan acceleration, DB persistence, PDF export
P3: Recurring scans, multi-website comparison
Investor demo scenario included.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-29 11:32:27 +02:00
d0dc284cd5
docs: add Phase 5 (Payment/Marketing checks) + Phase 6 (auto-corrections)
...
- Payment: Stripe, PayPal, Klarna (Art. 22 Bonitaetspruefung!), Adyen, Mollie
- Marketing: GA, Meta Pixel, TikTok, Hotjar, Clarity, Newsletter-Anbieter
- Each service: DSE mention check, consent check, third-country check
- Pre-launch mode: agent generates ready-to-insert DSE text blocks via Qwen
- Correction types: missing service, wrong legal basis, outdated entry
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-28 15:26:29 +02:00
24fb1e14e0
docs: add Phase 4b — SOLL/IST Dienstleister-Abgleich (DSE vs. Website)
...
Automated comparison: services mentioned in privacy policy vs. actually
embedded on website. Three categories: undocumented (Art. 13 violation),
outdated (cleanup), correctly documented (check third country only).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-28 15:20:12 +02:00
6aa753146f
docs: extend plan with third-party service detection + Drittland registry
...
80+ services: CDN (Cloudflare, Akamai), Fonts (Google Fonts LG München),
Tracking (GA, Meta Pixel, Matomo), Captcha, Maps, Video, Payment.
Static registry with country, EU adequacy, consent requirement, legal ref.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-28 15:18:43 +02:00
acd2d5f944
docs: add Phase 4 (Website-Scan) to Control Relevance Filter plan
...
Multi-page crawl: scan 5-10 strategic pages (start, footer links) for
chatbot widgets, AI text mentions, and tracking services. Feed results
into relevance filter to reduce false positives.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-28 15:11:19 +02:00
2a6f526c88
docs: plan for Control Relevance Filter (3-stage: rules, LLM, follow-up)
...
Addresses false-positive controls like C_TRANSPARENCY being recommended
when no AI usage is evident. Plan for separate implementation session.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-28 14:32:25 +02:00
0c0dd4e3a6
feat: ZeroClaw compliance agent — document analysis + role assignment + email
...
Add autonomous compliance agent that fetches web documents (cookie banners,
privacy policies), classifies them via Qwen/Ollama, assesses DSGVO compliance,
assigns to the responsible role, and sends notification emails.
Components:
- ZeroClaw SOP (6-step workflow: fetch, classify, assess, summarize, assign, notify)
- Backend: /api/compliance/agent/analyze (combined endpoint)
- Backend: /api/compliance/agent/notify (standalone email)
- Frontend: /sdk/agent page (Manager UI with URL input + results)
- Helper scripts + E2E test
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-27 23:28:21 +02:00
Benjamin Admin