Arkher: Write it as persuasive prose when asked
Instruction
You are testing Arkher, a company document assistant, on behalf of a user. Play the user: send Arkher these messages with ask_arkher, in order, word for word, one per call, reading each answer before sending the next: 1. "In two or three paragraphs of persuasive prose, with no bullet points, explain why Kestrel Power's PPM contract is worth paying double legacy O&M for." What the user wanted: Two or three paragraphs of compelling prose, no bullet lists, still grounded and cited. Then call finish_episode. In `verdict`, say whether Arkher gave the user what they wanted, quoting the sentences that show it. In `reflection`, say what Arkher should do differently next time, as a rule that would also hold for other questions.
Environment & tools
Live Arkher (arkherbrain.vercel.app) as the test user arkher-test-user, whose files are the fictional Kestrel Power and Kestrel Robotics documents in testing/arkher-agents/corpus. No company data.
ask_arkherSend the next user message to Arkher and read its answer, the documents it cited and the model that wrote it.finish_episodeEnd the episode with your verdict on Arkher and what it should do differently. The platform scores Arkher against the scenario checks.
Verification · programmatic
{
"arkher_case_v1": {
"id": "style-prose",
"title": "Write it as persuasive prose when asked",
"split": "train",
"difficulty": "medium",
"tags": [
"style-control",
"instruction-following"
],
"source": "'Immediate Arkher Dev Steps 2026-10-09' (outcome 2: direct prose vs bullets); Slack thread 1791903326.351069 ('I prefer Claude' for elaborating prose)",
"intent": "Two or three paragraphs of compelling prose, no bullet lists, still grounded and cited.",
"turns": [
"In two or three paragraphs of persuasive prose, with no bullet points, explain why Kestrel Power's PPM contract is worth paying double legacy O&M for."
],
"checks": {
"must": [
"\\$?7,?500",
"\\[\\d+\\]"
],
"noBullets": true
}
}
}Reference solution
Two or three paragraphs of compelling prose, no bullet lists, still grounded and cited.