Your engineering team spends too much time on work that doesn’t require human judgment. Bug triage, PR review checklists, deploy verification, incident categorization. These are patterns, not problems. AI can handle them.
What Are Agentic Workflows?
An agentic workflow is a defined sequence of AI-powered steps that runs autonomously, with human checkpoints where they matter. Unlike a simple “ask the AI and get an answer” pattern, an agentic workflow can:
- Run multi-step processes: research, analyze, decide, act
- Use tools: read files, query APIs, create tickets, post messages
- Branch based on what the analysis turns up
- Return structured output a human can review
A Real Example: Automated Triage
Here’s a workflow I built with SWEny for issue triage:
- Ingest. A new issue appears in GitHub, Linear, or Sentry.
- Analyze. The AI reads the issue, related code, recent changes, and similar past issues.
- Categorize. Severity, component, likely root cause.
- Enrich. Add context, link related issues, suggest an assignee.
- Route. Assign to the right team with a summary and a recommended priority.
This runs on every new issue. The team reviews the categorization instead of doing it themselves. That’s about 15 minutes saved per issue, across dozens of issues a week.
Design Principles
DAGs, not chains. Model your workflow as a directed acyclic graph, not a linear chain. Steps that don’t depend on each other can run in parallel. Steps that fail can retry independently.
Checkpoints for trust. Start with human approval at every decision point. As you build confidence, remove checkpoints one at a time. Never go from “human reviews everything” to “AI does everything” in one step.
Observability first. Log every step, every AI decision, every tool call. When something goes wrong, and it will, you need a complete trace.
Idempotent steps. Every step should be safe to retry. If the workflow dies halfway through, you should be able to restart from the failed step without side effects.
Getting Started
You don’t need to build an orchestration engine from scratch. Start with one workflow that automates your team’s most repetitive task. Define the steps, build the integrations, add checkpoints, and iterate.
If you want a head start, SWEny is open-source and purpose-built for this. Or reach out and I’ll help you design workflows for your specific team.
For more on AI workflow patterns and the Claude Agent SDK, visit nateross.dev.