Beware of PII in Testing Data: The Security Iceberg and Where PII Actually Hides
Using 'production-similar' data in pre-production is a major security risk. Learn why traditional masking fails, where hidden PII hides, and how to fix it.
Speedscale Blog
Latest insights on Agentic AI workflows, cloud native architectures, and performance optimization best practices from the Speedscale team.
Featured Post
Recent Posts
Build WireMock mappings fast from real traffic
Skip hand-writing WireMock stubs. Speedscale records your real request and response traffic and exports it straight to WireMock mappings.
Five things your logs will never tell you
Logs, metrics, and traces are a lossy compression of production. Five things you can do with a traffic data lake that observability can't.
Fixing 403 auth errors when you replay traffic
Replay an authenticated flow and the protected calls fail with 403. Here is how proxymock recommendations fix the expired bearer token in one click.
Capture once, test forever
Production traffic is the most complete record of what your system does, and most teams throw it away. One capture powers reproduce, validate, and sandbox.
We won't train on your data is not a security architecture
MSA clauses and contractual guarantees aren't an architecture. If your production traffic leaves your cloud, you're trusting a policy, not a system.
Validate Spring Boot Upgrades with Traffic Replay
Spring Boot upgrades silently change JSON contracts and autoconfiguration. Use traffic replay to catch every regression before production.
The AI Code Explosion: Why Your Mocking Strategy is Breaking Down
AI-generated code breaks traditional mocking. Here's how BYOC capture and replay with proxymock keeps verification grounded in real production traffic.
Logs told me something broke. Traffic showed me what.
Capture production traffic and store it in your own Elasticsearch with Speedscale BYOC. Pull it locally with es-gather.py and reproduce bugs with proxymock.
Your AI agent is fixing the wrong service
I tested 100 bugs across 240 microservices the model has never seen. Alert only: 51% pass rate, wrong service 34% of the time. Traffic captures: 77%.