# How to stop babysitting your agents

URL: https://getunblocked.com/events/how-to-stop-babysitting-your-agents/
When: Sep 2, 2026 · 9:00 AM PT
Speaker: Brandon Waselnuk, Developer Relations, Unblocked

Agents can generate code. Getting it right for your system is the hard part – you end up wasting time and tokens in the back and forth. See how a context layer gives agents exactly what they need to generate mergeable code the first time.

---

Your agents are fast, capable, and completely context-blind.

They generate code that compiles but doesn’t reflect how your system actually works. You’re likely already seeing the impact: ballooning token costs, longer review cycles, and inconsistent outputs. And as the industry shifts toward autonomous background and cloud agents, these problems only compound.

More MCPs, rules, and bigger context windows give agents access to information, but not understanding. The teams pulling ahead have a context engine to give agents exactly what they need for the task at hand.

What we’ll cover:

- Where teams get stuck on the AI maturity curve and why progress stalls
- Why naive RAG, bigger context windows, and more rules don’t solve the root problem
- What a context engine is and how it actually works in practice
- Real-world lessons from building a context engine at scale
- A live demo comparing agent output on the same coding task, with and without organizational context

You’ll walk away with:

- A clear mental model for how to make AI agents context-aware
- Practical insight into reducing token costs and review cycles
- A framework for improving output quality without overloading context
- An understanding of how leading teams are scaling AI effectively
- Concrete ideas you can apply immediately to your own workflows
- 2 open source tools you can try out today

Who should attend:

- Engineering leaders driving AI adoption at scale
- Developers working with AI agents in development workflow

## Additional resources
- [Context Maturity Assessment](https://getunblocked.link/rDZjBLz) — An interactive assessment tool to see where your team sits and how to bring your agentic development workflows to the next level.
- [Context Engine Simulator](https://github.com/unblocked/context-engine-simulator) — A local tool that A/B tests whether pre-gathered organizational context helps AI coding agents complete tasks faster, cheaper, and better. No accounts needed, runs entirely with your preferred agent and optional MCP connectors you and your team use.
- [Repo Rules Agent](https://getunblocked.com/blog/oss-repo-rules-agent/) — A CLI tool + skill that turns CLAUDE.md, AGENTS.md, .cursorrules, and ~40 other rules-files scattered around your repo into a queryable index coding agents can consult on demand.
- [Engineering Social Graph](https://getunblocked.com/blog/oss-social-graph-builder/) — A CLI tool that builds a weighted collaboration graph from your GitHub PR history. Point it at a repo, and it maps who reviews whose code, detects teams from review patterns, identifies domain experts for every code area, and flags knowledge silos. Then it renders an interactive visualization you can open in a browser.