An automated newsletter that curates, filters, summarizes, and emails the week's best AI/ML engineering posts.
Powered by Amazon Bedrock (Claude) · orchestrated on AWS, defined with the CDK.
-green){kind=icon}
🇰🇷 한국어 README
- AI-powered curation — Claude (via Amazon Bedrock) scores each post for relevance and writes a structured, multi-section summary.
- Multi-source aggregation — pulls from ~20 tech blogs via RSS and resilient HTML scraping (AWS, Google, Meta, OpenAI, Anthropic, NVIDIA, and more), with SSRF-guarded requests and per-source health tracking.
- Content quality gate — drops posts whose visible text is too thin to summarize before they reach the LLM, so the digest never ships empty write-ups.
- Crawl-health monitoring — tracks every source's fetch status and raises an SNS alert when a source fails, so silent breakage surfaces fast.
- Serverless infrastructure — AWS Lambda or Batch (config-selectable), scheduled by EventBridge, defined as code with the AWS CDK.
- Professional email — responsive HTML templates with dark-mode support, per-source logos, and score badges, delivered through Amazon SES.
AWS architecture — infrastructure & data flow:
Processing pipeline — ingestion → delivery:
| Module | Responsibility |
|---|---|
feed_parser.py |
RSS parsing + resilient HTML scraping (BeautifulSoup4 / Selenium), per-source health tracking |
summarizer.py |
Content gate → relevance filter → rank/cap → summarize, all via Bedrock |
newsletter_renderer.py |
HTML generation with Jinja2 (responsive, dark-mode, score badges) |
aws_helpers.py |
S3, SES, SNS, SSM, and Batch operations |
collect → gate → filter → rank → summarize → greet → render → deliver
- Lambda / Batch — execution environment selected by
lambda_or_batch. - EventBridge — scheduled execution (default: Saturdays 01:00 UTC).
- S3 — config, recipients, generated newsletters, and article HTML.
- SSM Parameter Store — LangChain API key and Batch queue/definition names.
- SES — newsletter delivery. SNS — run/health notifications.
- Bedrock (us-west-2) — Claude Sonnet 4.6 (filter + summarize), Claude Haiku 4.5 (greeting).
- Language / IaC: Python 3.12+, AWS CDK, Docker
- AI: Amazon Bedrock, LangChain
- Scraping: Feedparser, BeautifulSoup4, Selenium
- Rendering / config: Jinja2, Pydantic, YAML
Create app/configs/config-{stage}.yaml (e.g. config-dev.yaml). The four
top-level sections map to the Pydantic models in
app/configs/config.py:
resources:
project_name: tech-digest
stage: dev
lambda_or_batch: batch
cron_expression: "cron(0 1 ? * 6 *)" # Saturdays 01:00 UTC
scraping:
min_content_length: 600 # drop posts thinner than this (visible chars)
rss_urls:
- "https://aws.amazon.com/blogs/amazon-ai/feed/"
- "https://www.amazon.science/index.rss"
summarization:
filtering_model_id: anthropic.claude-sonnet-4-6
summarization_model_id: anthropic.claude-sonnet-4-6
greeting_model_id: anthropic.claude-haiku-4-5-20251001-v1:0
min_score: 0.7 # keep posts scoring >= this
max_posts: 5 # cap kept posts (applied before summarizing)
newsletter:
sender: "your-verified-sender@example.com"
header_title: "Weekly AI Tech Blog Digest"Model IDs come from the
LanguageModelIdcatalog inapp/src/constants.py.
python scripts/deploy_infra.py# Install runtime dependencies
pip install -r requirements.txt
# Configure environment
cp .env.template .env # then edit .env
# Generate and send a digest for a given week
python app/main.py --end-date 2026-06-03 --recipients you@example.com
# Or submit it as a Batch job
python app/run_batch.py --end-date 2026-06-03 --language ko --recipients you@example.com# Install dev tooling (ruff, mypy, pytest)
pip install -e ".[dev]"
# Lint, format-check, type-check, and test
ruff check .
ruff format --check .
cd app && mypy src # run from app/ so the dual import layout resolves
pytest # fast, offline unit/integration suite (240 tests)These same checks run in CI on every push and pull request
(.github/workflows/ci.yml).
MIT