Checked fact 123712 Oct 2026Agents and apps

In Anthropic's post the initializer agent wrote over 200 features as JSON for a claude.ai clone, each initially marked as failing, and Anthropic prompted the coding agents, with strongly worded instructions, to edit the file only by changing the passes field.

Toned down to what the source says

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

In the claude.ai clone example, this meant over 200 features ... These features were all initially marked as failing ... We prompt coding agents to edit this file only by changing the status of a passes field, and we use strongly-worded instructions like It is unacceptable to remove or edit tests

What the source said when we opened it, on 12 Oct 2026.

The source

Effective harnesses for long-running agents
Anthropic Engineering · 2025-11-26

Open the source archived copy

Checked

Checked by the notis newsroom on 12 Oct 2026, against the source above.

In the story

How an agent harness runs a model and enforces limits 12 Oct 2026

Cite this fact

Short permanent address

In a sentence

“In Anthropic's post the initializer agent wrote over 200 features as JSON for a claude.ai clone, each initially marked as failing, and Anthropic prompted the coding agents, with strongly worded instructions, to edit the file only by changing the passes field.” ai notis, checked 12 Oct 2026. Source: Effective harnesses for long-running agents (Anthropic Engineering). https://ainotis.com/c/1237

As a reference (APA style)

ai notis. (2026, October 12). In Anthropic's post the initializer agent wrote over 200 features as JSON for a claude.ai clone, each initially marked as failing, and Anthropic prompted the coding agents, with strongly worded instructions, to edit the file only by changing the passes field [Checked claim 1237]. ai notis. https://ainotis.com/c/1237

Anyone may quote this address. It does not change; if we correct the story, this page says so.