Distributed Tracing for Multi-Step Agent Workflows
Traces show you which step in a multi-agent workflow actually broke.
Mei-Ling Sørensen
Contributing Editor
Mei-Ling Sørensen
Mei-Ling has covered developer tooling and API ecosystems since the early days of the webhook economy, and her reporting has tracked how integration patterns have evolved from simple webhooks to fully autonomous agent pipelines. She is the site's primary voice on third-party integrations and the agentic coding frameworks that wire them together.
10 stories
REST API Design for Programmatic Agent Dispatch
Design REST APIs for machine clients, not humans: prioritize idempotency and structured errors.
Mei-Ling Sørensen
CI Pipeline Integration for Agents That Auto-Triage Build Failures
Security and credentials matter more than the agent logic itself.
Mei-Ling Sørensen
Triggering Agents From Slack Commands in Engineering Workflows
Slack Code lets teams trigger coding agents from chat, keeping work visible and scoped.
Mei-Ling Sørensen
Securing Agent Access to Third-Party APIs and SaaS Credentials
Agents leak credentials because they hold broader access than tasks require.
Mei-Ling Sørensen
GitHub Token Scoping for Agents That Open Pull Requests
Limit agent GitHub tokens to the three permissions a pull request actually requires.
Mei-Ling Sørensen
Short-Lived AWS Credentials for Coding Agent Sessions
Minting fresh credentials for every agent session limits the damage from inevitable compromises.
Mei-Ling Sørensen
Linting and Static Analysis for Agent YAML Files
Configuration files for AI agents need the same code review rigor as production systems.
Mei-Ling Sørensen
Code Review Checklists for Agent Configuration PRs
Agent configuration changes deserve the same security scrutiny as firewall rules.
Mei-Ling Sørensen
Refactoring Monolithic Agent Configs Into Composable Units
Breaking monolithic agent configs into versioned, composable units prevents silent failures.
Mei-Ling Sørensen