Back to the library

Evaluation & Safety

Testing, validation, reliability and security.

THE OPEN NOTEBOOK

Browse the notes

Search a concept, explore a category, or find something new to explore.

5 notes

Code review in the AI era

Strategies for code review in the AI era: independent reviewer agents, evidence, and risk-oriented human review.

10 min read
#Code review#Software quality#Testing#Coding agents

Testing strategy for AI-produced code

Testing strategies for AI-produced code: automation, Playwright, independent validation, regressions, and CI/CD.

12 min read
#Testing#Software quality#Continuous integration#Coding agents

Security of applications developed with agents

Security strategies for applications developed with AI agents.

12 min read
#Security#Testing#Credentials and SSH#Code review

Credentials, SSH, and infrastructure access

Good practices for granting AI agents controlled infrastructure access without exposing credentials to the model.

6 min read
#Credentials and SSH#Security#MCP#Artificial intelligence

Protecting context and sensitive data

Strategies to protect context, sensitive data, and AI agents against prompt injection and unauthorized access.

7 min read
#Prompt injection#Security#Context engineering#Artificial intelligence
RSSMidnight Notes · Collection of knowledge and ideas.
Evaluation & Safety | Midnight Notes