Agentic coding: No effect on my development speed

Posted: 2026-03-11

Summary

Giving an AI agent a natural-language description of small programming tasks takes me longer than trying to accomplish them directly.

Box plot of ln(actual/estimated)

Overview

Scatterplot

Observations and caveats

When giving tasks to AI, I still fully review the outputs. I often end up reworking significant portions of the AI-generated code.

Data

Metric ai human
Samples 27 25
Median 1.533 0.867
Geo Mean 1.343 1.083
Mean 1.678 1.347
Min 0.300 0.400
Max 4.800 4.500
StdDev 1.119 0.982
MAD 0.617 0.367

The mean/median values are based on the ratio of actual time to estimated time.

Histogram of `ln(actual/estimated)

Open questions

Methodology

Source data

This is based on 52 observations from 2025-10-07 to 2026-03-23 corresponding to individual development tasks. For each, I estimated the time it would take me to accomplish

Development method

Estimate before method selection

I estimate the time required before selecting development method: my estimates reflect how much time I think it would take me to implement the task manually (i.e., “human” method).

Random method selection

I select the method randomly with a coin flip:

(( RANDOM % 2 )) && echo ai || echo human