sgit newsroom v0.1.29 · snapshot 2026-09-24

signal · 2026-09-24

riskmandate.ai had a voice feedback interview two weeks before sgit.ai briefed the pattern

riskmandate.ai has had a voice feedback interview page since 9 September, a prompt the reader pastes into a chat assistant that interviews them by voice and writes a debrief they send back; sgit.ai's brief of 24 September describes the same shape as a new, reusable pattern and does not mention it.

riskmandate.ai → sgit.ai new

Suggested action: give sgit.ai's team riskmandate.ai's feedback page and its v0.12.2 note, so the interview-page brief names the pattern's first version and the two prompts can be compared

The pages this piece is about

riskmandate.ai has had a voice feedback interview page since 9 September, a prompt the reader pastes into a chat assistant that interviews them by voice and writes a debrief they send back; sgit.ai's brief of 24 September describes the same shape as a new, reusable pattern and does not mention it.

Finding: sgit.ai's brief does not cite the earlier page, and riskmandate.ai's new interview page does not link its own feedback page (le-024).

Side A: riskmandate.ai's feedback page

The v0.12.2 release note↗, dated 8 September 2026 and marked reconstructed in the version record↗, added team/prompts/voice-feedback-interview.md, a prompt to run a voice-mode "feedback interview with people who have seen a RiskMandate presentation, and produce a debrief." It "keeps turns short for voice, leads the debrief with objections rather than praise, asks consent to quote explicitly".

v0.13.0, on 9 September, added the "feedback page". That page↗ says: "Saw a RiskMandate demo?" and sets out "Six steps, about twenty minutes." Its sections include "It asks for criticism first" and "You control what we see".

Side B: sgit.ai's brief

The interview-page brief↗ asks for a page that carries a prompt, which interviews the reader by voice "for about twenty minutes" and writes up "their ideas, a thirty, sixty and ninety day action plan, and candid feedback". Its entry on the briefs index↗ calls it "A reusable page pattern for getting feedback from people whose knowledge is in their heads." It lists who the pattern could serve next, "investors, CISOs, insurers and GRC practitioners", and asks that "Candour is asked for explicitly."

Neither the brief nor the index mentions riskmandate.ai's feedback page or its prompt.

What we checked