# When the plan changes, does an adaptive heuristic choose better work?

Reasoning Under Change: Research software. Published 27 Oct 2026. Question: Where does judgment sit?
Scope: Up to 20 tasks · 4 budgets · 1 authored simulation
Page: https://jasonlovell.ai/work/reasoning-under-change
Code: https://github.com/jlov7/reasoning-under-change-release

Exact work selection from a small queue with prerequisites, named budgets and revision history, beside a test of whether an adaptive heuristic helps.

## Finding

In an authored changing simulation, the reactive baseline completed 59 of 64 accepted actions and the adaptive heuristic 43 of 64. The negative result is kept.

## In practice

For a small queue, exact selection is cheap. Measure an adaptive layer before trusting it.

## What I built

An exact selector over a prerequisite graph within named budgets, replanning that keeps completed work, and counterfactuals for what forcing a task in would displace.

## Where the evidence stops

At most 20 tasks, four named budgets, capacity 0 to 128 and a one-second planning deadline. The simulation is authored, with no live model, human trial or production use. That the adaptive approach works better is not established, and this is not general AI reasoning.

---
By Jason Lovell. Independent work, separate from my role at PwC. I build everything here myself, end to end, with Claude Code and Codex. I write the question and the test first, read the runs, and keep the results that go against me.