Getting Started
Getting started with agentic engineering means changing how you work, not upgrading a tool: you learn to specify, delegate and verify instead of typing code. Expect to be slower at first. The productivity evidence shows a learning curve before the gains, and the teams that get through it protect time to practice.
Written by
-
Benedikt Stemmildt Founder & Co-CEO
Updated:
Getting Started 2
Our position. The learning curve cannot be compressed (opens in a new tab): it takes months of practice, not hours.
Start with your own learning path, calibrate your expectations against the productivity evidence, then turn individual practice into team capability.
Where do you start?
- Getting Started & Learning — the mindset shift over the tool upgrade, why the learning curve distorts the productivity data, what effective beginners do differently, and the official docs, courses, and strategic reading to start from.
- Productivity & Workflow — what the evidence actually shows about AI productivity, how to measure impact without fooling yourself, and practitioner workflows that hold up.
Related
- Getting Started and Learning: how the first weeks with a coding agent go, and what effective beginners do differently.
- Productivity and Workflow: what the evidence shows about speed and quality, and how to measure your own.
- Agentic Engineering: the discipline this leads into, from specification to verification.
- Evidence: the studies behind the productivity claims.
- Leadership: the environment that decides whether a team’s adoption pays off.
Resources
Posts
- The learning curve cannot be compressed (opens in a new tab) - LinkedIn post holding that getting good with coding agents takes months of practice, not hours.
In this section
- 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.
- Productivity and Workflow
Measured effects of AI-assisted engineering range from slowdowns to large throughput gains. Enablement, measurement discipline and the workflow around the code decide where a team lands, far more than the model or the tool.