---
title: "Progressive reduction, ten years later"
author: Dan Birman
url: https://dbirman.com/reduction
updated: 2026-11-09
summary: "In 2015 I argued that interfaces should get simpler as people learn them, and step back in when people forget."
---

# Progressive reduction, ten years later

October 2026 · 4 min

Drafted with Claude from my notes. I’m still editing it.

In 2015 I argued that interfaces should get simpler as people learn them, and step back in when people forget. I still think that’s right, but more and more, the software is the one learning.

## What I said in 2015

I called it progressive reduction, borrowing the term from the team at LayerVault. Start with more guidance. Track how well someone knows each feature. Remove the guidance as they get proficient. And the part most people skipped: proficiency decays. When someone stops using a feature, the guidance should come back.

## What changed

With AI agents, the roles flip: the person is deciding how much to trust a tool that’s learning the task. The guidance now is oversight: approvals, previews, check-ins.

And products are already reducing it. Anthropic found that new Claude Code users let the agent run without approvals in about 20% of sessions, rising to over 40% after a few hundred sessions ([Anthropic](https://www.anthropic.com/research/measuring-agent-autonomy)). That’s progressive reduction, driven by familiarity. The curve shows people getting used to the agent. It says nothing about whether the agent got better.

## The half we forgot

That half is decay. In 2015, the interface came back when a person’s skill faded. Today, almost nothing comes back when an agent’s reliability fades, or when the task changes under it.

People calibrate trust per task, not per agent ([Pochampally et al.](https://arxiv.org/abs/2607.18257)). An assistant that’s flawless at sorting your inbox has earned nothing toward paying your invoices. Most products can’t tell the difference, because autonomy is a single setting per agent.

## Progressive reduction for agents

1. **Reduce oversight per task, not per agent.** Earned room on one kind of work doesn’t transfer to another.
2. **Reduce on evidence, not habit.** Count verified outcomes, not the agent’s own reports. Agents regularly say “done” when they aren’t ([OverclaimBench](https://arxiv.org/abs/2609.20812)). That’s [pattern 05](https://dbirman.com/record).
3. **Bring oversight back when the record slips.** A skipped step, a false “done,” an action the person had to reverse.
4. **Bring it back when the task changes.** A new counterparty, a bigger amount, a tool it hasn’t used before.
5. **Say so when it happens.** “I’ll check with you on payments again for a while. I made a mistake last week.” Stepping back in without explanation feels like a bug.

## Why it matters

Progressive reduction was about matching the interface to what a person could handle that day. Agents need the same honesty in the other direction: oversight that matches what the agent has earned, this week, on this task.

The original: [Progressive Reduction: Evolving the Experience for Your Most Frequent Users](https://medium.com/@dan_birman/progressive-reduction-evolving-the-experience-for-your-most-frequent-users-bc588b080147) (2015).