Skip to content

Knowledge base

Getting Started and Learning

Getting started with agentic engineering is a learning problem, not a tool installation. Developers are slower in their first hours with coding agents and faster after structured practice, and how the learning is organized decides the difference more than which tool is bought.

Written by

Updated:

Getting Started 2

Our position. We hold that mastery comes through practice on real work, not through a two-day workshop. Train on your own code, ideally on the migration you have been postponing (opens in a new tab).

Agentic engineering changes the engineer’s role, so the first weeks go into new habits: what to delegate, how to brief the agent and how to check its work. Official documentation, courses and practitioner writing cover the tool.

Why are developers slower at first?

In a randomized trial, experienced open-source developers were about 19% slower with early-2025 AI tools on repositories they knew well (METR, Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity (opens in a new tab)). DORA models adoption as a J-curve: performance dips while teams learn, adapt pipelines and absorb extra verification work (The learning curve). Practitioners describe the same curve for one person: at the start you are faster by hand, and the payoff arrives once the workflow is built (Vom Coder zum Dirigenten (opens in a new tab)).

Start here

  • The learning curve — Why early agentic-engineering practice feels slower and how that distorts productivity measurements.
  • Effective beginner practices — Practical habits that help beginners build judgment, feedback loops, and safe autonomy.
  • Engineering foundations — Why design, architecture, judgment, and software fundamentals matter more when code becomes cheap.
  • Organizational learning — How teams turn individual agent use into shared, measurable organizational capability.

Resources

Official Documentation

Tutorials & Videos

Community & Discovery

Education & Courses

Strategic Reading

In this section

  • Effective beginner practices

    Beginners get good with coding agents by practicing in a domain they can judge, keeping tasks and feedback loops small, and granting the agent more autonomy only once reviewing every small step turns into rubber-stamping.

  • Engineering foundations

    Engineering foundations matter more when agents write the code, because the work that remains is judging it: framing the problem, seeing what the agent missed, and verifying output that a model inferred rather than compiled.

  • The learning curve

    Developers are often slower in their first weeks with coding agents, and team performance dips while people learn before gains appear. Measurements taken in that window, or built on self-reports and code volume, misread the tools in both directions.

  • Organizational learning

    Individual AI use becomes team capability only when the organization changes with it: incentives, ownership of risk and trust. Without that, pilots succeed technically and still stall, and usage grows while the company learns nothing.