Red Shell · Common Errors

All mistakes/Section 1: The Foundations Every Task Must Get Right

1.1The deliverable sits below the complexity bar

Fails a client CORE standard

The mistake

The deliverable misses its type's complexity floor. Typically the Agent Objective says dashboard, no prompt asks for interaction, and the page ships static.

Do this instead

Before prompt 1, check the deliverable type against its floor, and have a prompt ask for the interaction the data supports.

Where it happened

One real task. Each shows the spot and what it should have been; click any line to open the task there.

the words at faultthe row or field at faultmissing from the taskwhat is righta task file

Example 1Commerce & Product · 3 Leg A turns

What is wrongThe Agent Objective asks for "one local HTML dashboard"; the golden ada_list.html has no script, button, filter or link. Static, it clears neither the dashboard nor the interactive HTML floor.

Leg A turn 1 asks Model A for ada_list.html, a shop list giving brand, price, size and a picture per item. Leg A turns 2 and 3 add rules and layout.

Where it shows

…He needs one local HTML dashboard, 'ada_list.html ', that Ada can use at the store…
No script, no button, no filter, no link: one table and nine pictures.
None of the three asks the page to do anything when clicked.

What it should have been

…with the amounts I usually buy. Put the buy list in a table I can sort by price, and let Ada hide what's not on Fresh. It should be detailed…
Controls that respond: the list sorts by price and hides what Fresh does not stock.

How it breaks the standardNothing on ada_list.html responds, so the task ships a document, the lowest priority type on the Complexity Bar, though 14 Fresh orders could feed sorting or filters. Model A and Model B never see the Agent Objective, and no Leg A prompt asks for interaction, so no criterion grades it.

The rule it breaksGuidelines · Complexity Bar A styled static page does not qualify. Both are P0 floors.

Catch it in your own task

Ask what the page does when someone clicks it. If nothing, it is a document, whatever the Agent Objective calls it.

Where the correct guidance is written

Section titles as they print, so you can search for them in the document.

Guidelines · Complexity Bar

Interactive HTML: Interaction that actually works: controls that respond, state that changes, filters or navigation. A styled static page does not qualify. Dashboard: Several linked views over data the model extracted itself. One chart is not a dashboard.

Both are P0 floors.

Guidelines · 1.3 Defining the Draft History

The Draft History (Agent Objective, Desired Outcome, Multimodal Upload) is not embedded in the agent by default.

So only a prompt can ask for a dashboard.

Why it matters

A page that does nothing when clicked clears neither the interactive HTML floor nor the dashboard floor. It is a document, the lowest priority deliverable on the bar, so the task falls short of what the client asked for however good the reasoning underneath is. The deliverable is set by the prompts at scenario stage, so it cannot be patched later.

Every example taken apart, with the task, how it breaks the standard and what it should have been: 1.1 The deliverable sits below the complexity bar, in the explanations →