Files
webdev-pipeline/backlog/tasks/task-11 - Create-the-OpenRouter-AI-audit-pipeline.md
2026-06-03 21:18:36 +02:00

45 lines
1.8 KiB
Markdown

---
id: TASK-11
title: Create the OpenRouter AI audit pipeline
status: To Do
assignee: []
created_date: '2026-06-03 19:13'
labels:
- mvp
- agent
- llm
dependencies:
- TASK-8
- TASK-9
- TASK-10
references:
- PRD.md
priority: high
ordinal: 11000
---
## Description
<!-- SECTION:DESCRIPTION:BEGIN -->
Implement the LLM-powered audit generation pipeline using Vercel AI SDK and OpenRouter. The pipeline combines Google/Places data, Playwright crawl data, screenshots, PageSpeed signals, and local skills to generate structured internal findings plus final German audit, email, subject, call script, and follow-up drafts.
<!-- SECTION:DESCRIPTION:END -->
## Acceptance Criteria
<!-- AC:BEGIN -->
- [ ] #1 Vercel AI SDK is configured with OpenRouter and environment/Convex secrets
- [ ] #2 Model profiles exist for classification, multimodal audit analysis, German text generation, and final quality review
- [ ] #3 Structured audit outputs use Zod schemas and are stored in Convex with raw prompts/responses and model metadata
- [ ] #4 Screenshots can be passed to multimodal-capable models where supported
- [ ] #5 Generated customer-facing text follows Ich-Form, German language, no scores, no prices, no generic KI-Slop, and factual observation plus suggestion style
<!-- AC:END -->
## Implementation Plan
<!-- SECTION:PLAN:BEGIN -->
1. Add OpenRouter provider setup through Vercel AI SDK.
2. Define Zod schemas for internal findings, audit summary, email draft, subject, call script, follow-up, and quality review.
3. Build model-profile configuration for fast classification, multimodal analysis, and German copy generation.
4. Combine lead, crawl, screenshot, PageSpeed, and selected skills into prompt inputs.
5. Persist all prompts, model responses, normalized findings, final texts, and generation errors in Convex.
<!-- SECTION:PLAN:END -->