FlowSync
Open App
中文
ProEducation5 nodes
Score 73

Course Content Builder

Provide source materials and a syllabus outline — the agent researches, structures into modules and lessons, generates slide decks with learning objectives, exercises, and assessment questions.

Run this template Fork & customise

What does this workflow do?

Drop your URLs — the pipeline runs 5 automated steps: Trafilatura (URLs→text) → Docling (pdf→markdown) → LLM Reasoning (text→json) → LLM Reasoning (json→markdown) → Python-PPTX (markdown→pptx) — and delivers pptx. Every node is visible, auditable, and replaceable.

System flow

1. Trafilatura — Boilerplate-free main-content extraction from any web page 2. Docling — Layout-aware document parsing that preserves reading order and tables 3. LLM Reasoning — Large-language-model step that extracts, classifies, validates or writes structured output 4. LLM Reasoning — Large-language-model step that extracts, classifies, validates or writes structured output 5. Python-PPTX — Builds the PowerPoint deck — layouts, charts, speaker notes

Pipeline breakdown

Trafilatura URLs Docling pdf LLM Reasoning text LLM Reasoning json Python-PPTX markdown
  1. Trafilatura trafilatura — Boilerplate-free main-content extraction from any web page URLs → text
  2. Docling docling — Layout-aware document parsing that preserves reading order and tables pdf → markdown
  3. LLM Reasoning llm — Large-language-model step that extracts, classifies, validates or writes structured output text → json
  4. LLM Reasoning llm — Large-language-model step that extracts, classifies, validates or writes structured output json → markdown
  5. Python-PPTX python-pptx — Builds the PowerPoint deck — layouts, charts, speaker notes markdown → pptx

Workflow Reputation Score

Based on executions, success rate, update frequency, component quality, and user rating.

73Overall
★★★★★ 4.4
▶Executions
30
✓Success rate
100
↻Update frequency
70
⚙Component quality
90
★User rating
88

Based on executions, success rate, update frequency, component quality, and user rating.

Components used

Trafilaturatrafilatura

Boilerplate-free main-content extraction from any web page

adbar/trafilatura ↗
Doclingdocling

Layout-aware document parsing that preserves reading order and tables

DS4SD/docling ↗
LLM Reasoningllm

Large-language-model step that extracts, classifies, validates or writes structured output

FlowSync proprietary
Python-PPTXpython-pptx

Builds the PowerPoint deck — layouts, charts, speaker notes

scanny/python-pptx ↗

How is this different from n8n or Zapier?

Unlike generic workflow builders, FlowSync workflows ship pre-configured with AI skills baked into every node — OCR, LLM reasoning, transcription, super-resolution — not just webhook triggers. Each node is white-box auditable: you see input, output, and config. Deployment is instant — no self-hosting, no API-key per node.

Use cases

  • Online course creation
  • Training module development
  • Workshop material preparation
  • Employee onboarding curriculum

Author & Source

This workflow is maintained by the FlowSync team. All components are open-source or commercially licensed. Source code for each component is linked in the Components section above.

Pricing: Free tier available · PRO tier · Official

Data handling

Data is processed in-memory during pipeline execution only. No files are stored permanently unless you choose to save outputs to your account.

FlowSync Workflow Marketplace · 73 reputation score · 30% execution · 100% success · 5-node white-box pipeline · maintained by FlowSync Official

Ready to run?

Provide source materials and a syllabus outline — the agent researches, structures into modules and lessons, generates slide decks with learning objectives, exercises, and assessment questions.

Run Course Content Builder → Browse all workflows →