Development record
When an agent asks the person a question through the interactive question tool, the example that makes the question answerable must be visible IN the question: in the question text and in each option's preview. Prose written before the tool call is not visible while the question shows. On 2026-09-29 the person twice answered 'explain in laypersons terms' / 'show me the example, I can't see it' because the example sat in prose above the question.
When an agent asks the person a question through the interactive question tool, the example that makes the question answerable must be visible IN the question: in the question text and in each option's preview. Prose written before the tool call is not visible while the question shows. On 2026-09-29 the person twice answered 'explain in laypersons terms' / 'show me the example, I can't see it' because the example sat in prose above the question.
Delivered: the GRILL rule in 5357c4c68 (the quoting rule aligned in 3f07017cf); the interview command page line in 66b5512e9 (commands/intent.md is the only interview page; no grill page exists); the eval or lint that flags an option with no example is owned by iss-2609300112146660.
Grounds
- pursued: guidance a person needs in order to answer must stay visible while they answer, not sit where the answering surface hides it. Primary sources: Nielsen Norman Group, K. Sherwin, 'Placeholders in Form Fields Are Harmful' (2014, https://www.nngroup.com/articles/form-design-placeholders/): disappearing guidance strains short-term memory and essential information belongs where it is visible at all times; GOV.UK Design System, Radios (https://design-system.service.gov.uk/components/radios/): the question sits in the legend and each option carries its own short hint. Shown wrong if a product thinker answering a question built to this rule still asks to see the example.
Frontmatter
| id | iss-2609291925134691 |
|---|---|
| type | issue |
| lifecycle | resolved |
| severity | minor |
.abcd/work/issues/resolved/iss-2609291925134691-when-an-agent-asks-the-person-a-question.md
open on GitHub ↗ · commit history ↗
mentions1
- iss-2609300112146660No check flags a question put to the human whose options carry no example. GRILL rule 11 and the planning interview page (commands/intent.md) say the example that makes a question answerable goes in the question text and each option's preview carries its own concrete example, but nothing verifies a question against that, so the rule holds only while an agent remembers it. This is the eval or lint the remedy of iss-2609291925134691 floated and that record's fix did not build.