DX
also called Developer Experience
How it feels to build with a tool or platform.
The quality of a developer’s experience — onboarding, feedback loops, error messages, documentation, time to first success. A first-order driver of adoption.
In AI tools, DX is mostly about trust: clear failures, inspectable context, predictable cost, and the ability to intervene. Latency and noise destroy it faster than missing features do.
For AI tooling, the analogous drivers are the time to first useful output, the quality of error messages when the agent does something wrong, and how quickly a change can be verified. Those are the things that decide whether a team keeps using a tool past the second week.
Time to first useful result
Two agent tools are being evaluated by the same team.
The one that produces something correct in the first ten minutes gets adopted; the one that needs an afternoon of configuration does not, even when its ceiling is higher. Onboarding friction is a first-order adoption variable, not a polish item.
- reportState of AI-assisted software development 2025 ↗
Frames AI as an amplifier of the organisation it lands in: the same tooling helps strong delivery cultures and compounds problems in weak ones.
- docsBest practices for using GitHub Copilot to work on tasks ↗
Recommends bounded tasks with explicit acceptance criteria, and names what is a bad fit for unattended delegation: ambiguous, security-sensitive, production-critical or deeply domain-specific work.
AX · Agent Experience
How it feels to be an agent using your product.
AI-Assisted Development
Day-to-day engineering with a model in the loop.
Observability
Being able to see what the system actually did.
Adoption Curve
The path from a few enthusiasts to real usage.