Skip to content
GitHub Agentic Workflows

Blog

Meet the Workflows: Testing & Validation

Peli de Halleux

Let’s continue our tour of Peli’s Agent Factory!

In our previous post, we explored interactive and ChatOps workflows - agents that respond to slash commands and GitHub reactions, providing on-demand assistance with full context. We learned that context is king: the right agent at the right moment is far more valuable than scheduled runs.

But making code better is only half the battle. We also need to ensure it keeps working. As we refactor, optimize, and evolve our codebase, how do we know we haven’t broken something? How do we catch regressions before users do? That’s where testing and validation workflows come in - the skeptical guardians that continuously verify our systems still function as expected. We learned the hard way that AI infrastructure needs constant health checks, because what worked yesterday might silently fail today. These workflows embody trust but verify.

These agents keep everything running smoothly through continuous testing:

We learned the hard way that AI infrastructure needs constant health checks. The Smoke Tests run every 12 hours to validate that our core systems (engines, firewall, MCP servers) are actually working. It’s caught outages before users noticed them. The Multi-Device Docs Tester uses Playwright to test our documentation on different screen sizes - it found mobile rendering issues we never would have caught manually. The CI Coach analyzes our CI/CD pipeline and suggests optimizations (“you’re running tests sequentially when they could be parallel”).

These workflows embody the principle: trust but verify. Just because it worked yesterday doesn’t mean it works today.

But what about the infrastructure itself? Who watches the watchers? Time to go meta.

Continue reading: Tool & Infrastructure Workflows →


This is part 11 of a 16-part series exploring the workflows in Peli’s Agent Factory.

Meet the Workflows: Interactive & ChatOps

Peli de Halleux

Let’s keep exploring Peli’s Agent Factory!

In our previous post, we explored creative and culture workflows - agents that bring joy, build team culture, and create moments of delight. We discovered that AI agents don’t have to be all business; they can have personality while making work more enjoyable.

But sometimes you need help right now, at the exact moment you’re stuck on a problem. You don’t want to wait for a scheduled run - you want to summon an expert agent with a command. That’s where interactive workflows and ChatOps come in. These agents respond to slash commands and GitHub reactions, providing on-demand assistance with full context of the current situation. We learned that context is king - the right agent at the right moment with the right information is far more valuable than a dozen agents running on cron schedules.

These agents respond to commands, providing on-demand assistance whenever you need it:

  • Q - Workflow optimizer that investigates performance and creates PRs
  • Grumpy Reviewer - Performs critical code reviews with, well, personality
  • Workflow Generator - Creates new workflows from issue requests

Interactive workflows changed how we think about agent invocation. Instead of everything running on a schedule, these respond to slash commands and reactions - /q summons the workflow optimizer, a 🚀 reaction triggers analysis. Q (yes, named after the James Bond quartermaster) became our go-to troubleshooter - it investigates workflow performance issues and opens PRs with optimizations.

The Grumpy Reviewer gave us surprisingly valuable feedback with a side of sass (“This function is so nested it has its own ZIP code”). We learned that context is king - these agents work because they’re invoked at the right moment with the right context, not because they run on a schedule.

While ChatOps agents respond to commands, we also need workflows that continuously verify our systems still function as expected.

Continue reading: Testing & Validation Workflows →


This is part 10 of a 16-part series exploring the workflows in Peli’s Agent Factory.

Meet the Workflows: Creative & Culture

Peli de Halleux

Let’s explore the fun side of Peli’s Agent Factory!

In our previous post, we explored security and compliance workflows - the essential guardrails that manage vulnerability campaigns, validate network security, and prevent credential exposure. These workflows let us sleep soundly knowing our agents operate within safe boundaries.

But here’s the thing: work doesn’t have to be all business. While we’ve built serious, production-critical workflows for quality, releases, and security, we also discovered something unexpected - AI agents can bring joy, build team culture, and create moments of delight. Not every workflow needs to solve a critical problem; some can simply make your day better. Let’s explore the playful side of our agent factory, where we learned that personality and fun drive engagement just as powerfully as utility.

Not everything needs to be serious! These agents remind us that work can be fun:

  • Poem Bot - Responds to /poem-bot commands with creative verses (yes, really)
  • Daily Team Status - Shares team mood and status updates
  • Daily News - Curates relevant news for the team

Okay, hear us out: the Poem Bot started as a joke. Someone said “wouldn’t it be funny if we had an agent that writes poems about our code?” and then we actually built it. And you know what? People love it. It became a team tradition to invoke /poem-bot after particularly gnarly PR merges. We learned that AI agents don’t have to be all business - they can build culture and create moments of joy.

The Daily News workflow curates relevant articles, but it also adds commentary and connects them to our work. These “fun” workflows have higher engagement than some of our “serious” ones, which tells you something about what makes people actually want to interact with automation.

Scheduled workflows are great, but sometimes you need help right now. Enter ChatOps and interactive workflows.

Continue reading: Interactive & ChatOps Workflows →


This is part 9 of a 16-part series exploring the workflows in Peli’s Agent Factory.

Meet the Workflows: Security & Compliance

Peli de Halleux

Great to have you back at Peli’s Agent Factory!

In our previous post, we explored operations and release workflows that handle the critical process of shipping software - building, testing, generating release notes, and publishing. These workflows need to be rock-solid reliable because they represent the moment when our work reaches users.

But reliability alone isn’t enough - we also need security. When AI agents can access APIs, modify code, and interact with external services, security becomes paramount. How do we ensure agents only access authorized resources? How do we track vulnerabilities and enforce compliance deadlines? How do we prevent credential exposure? That’s where security and compliance workflows become our essential guardrails - the watchful guardians that let us sleep soundly at night.

These agents are our security guards, keeping watch and enforcing the rules:

Security workflows were where we got serious about trust boundaries. The Security Compliance agent manages entire vulnerability remediation campaigns with deadline tracking - perfect for those “audit in 3 weeks” panic moments. We learned that AI agents need guardrails just like humans need seat belts.

The Firewall workflow validates that our agents can’t access unauthorized resources, because an AI agent with unrestricted network access is… let’s just say we sleep better with these safeguards. These workflows prove that automation and security aren’t at odds - when done right, automated security is more consistent than manual reviews.

After all this serious infrastructure talk, let’s explore the fun side: agents that bring joy and build team culture.

Continue reading: Creative & Culture Workflows →


This is part 8 of a 16-part series exploring the workflows in Peli’s Agent Factory.

Meet the Workflows: Operations & Release

Peli de Halleux

Welcome to another stop in Peli’s Agent Factory!

In our previous post, we explored metrics and analytics workflows - the agents that monitor other agents, turning raw activity data into actionable insights. We built our central nervous system for the agent ecosystem, learning that you can’t optimize what you don’t measure.

Now comes the moment of truth: actually shipping software to users. All the quality checks, metrics tracking, and iterative improvements culminate in one critical process - the release. Operations and release workflows handle the orchestration of building, testing, generating release notes, and publishing. These workflows can’t afford to be experimental; they need to be rock-solid reliable, well-tested, and yes, even a bit boring. Let’s explore how automation makes shipping predictable and stress-free.

The agents that help us actually ship software:

  • Release - Orchestrates builds, tests, and release note generation
  • Daily Workflow Updater - Keeps actions and dependencies current (because dependency updates never stop)

Shipping software is stressful enough without worrying about whether you formatted your release notes correctly. The Release workflow handles the entire orchestration - building, testing, generating coherent release notes from commits, and publishing. What’s interesting here is the reliability requirement: these workflows can’t afford to be creative or experimental. They need to be deterministic, well-tested, and boring (in a good way).

The Daily Workflow Updater taught us that maintenance is a perfect use case for agents - it’s repetitive, necessary, and nobody enjoys doing it manually. These workflows handle the toil so we can focus on the interesting problems.

After all this focus on shipping, we need to talk about the guardrails: how do we ensure these powerful agents operate safely?

Continue reading: Security & Compliance Workflows →


This is part 7 of a 16-part series exploring the workflows in Peli’s Agent Factory.