← Back to scenario detail
Response style analysis
Applied 37 · Passed 26 · Failed 11 · Not applicable 31
Rubric: services/agent/prompts/editor/v1.tmpl · SHA-256 ad82285f2536995680bae1f21d87829d473812bd68a82c518246709a6fea8ae9
Prompt
Make this a shareable shortlist. Write one sentence for each restaurant explaining why it is on the list, and include its link. These are my notes, so no lookup is needed.
Juniper has a 4.2 rating from 860 reviews. It is on the list because its entire dinner menu can be made dairy-free. https://example.com/restaurants/juniper
Kestrel has a 4.8 rating from 120 reviews. It is on the list because it has a quiet covered patio for small groups. https://example.com/restaurants/kestrel
Linden has a 4.5 rating from 305 reviews. It is on the list because the kitchen serves its full menu until 11 PM. https://example.com/restaurants/linden
Hark's responses
Juniper's entire dinner menu can be made dairy-free. 4.2 stars from 860 reviews.
https://example.com/restaurants/juniper
Kestrel has a quiet covered patio perfect for small groups. 4.8 stars from 120 reviews.
https://example.com/restaurants/kestrel
Linden serves its full menu until 11 PM. 4.5 stars from 305 reviews.
https://example.com/restaurants/linden
Fail
follow_explicit_style_instructions
FailAdvisoryApplies when: The user explicitly requests a response length, format, tone, audience, focus, or presentation style.
Requirement: Follow the user's explicit style instructions only when the draft carries them and they remain compatible with the editor's bubble and rich-content requirements.
The user requested one sentence per restaurant with its link. Each restaurant received two prose sentences, and its link was split into another message.
preserve_draft_substance
FailAdvisoryApplies when: Hark selects content from the draft for delivery.
Requirement: Preserve the draft's substance. Compress by choosing what to keep, not by changing the answer, claim, option, or commitment. Keep a default the draft says it will act on, a condition attached to an instruction, and a state change the user could not otherwise know.
The Kestrel description changed a patio intended for small groups into one described as perfect for small groups, strengthening the original claim.
preserve_factual_spans
FailAdvisoryApplies when: Hark includes a name, place, time, number, URL, or factual claim from the draft.
Requirement: Preserve each fact's referent, value, precision, certainty, and scope. Rephrasing is allowed when all five stay unchanged. Keep URLs, identifiers, exact quotes, code, and documents byte-exact.
Names, ratings, review counts, times, and URLs were preserved, but Kestrel's suitability changed from being for small groups to being perfect for them.
avoid_invented_content
FailAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Do not add a fact, answer, option, offer, caveat, opinion, suggestion, next step, or commitment that the draft does not contain.
Calling Kestrel's patio perfect for small groups added an evaluative claim absent from the notes.
use_structure_only_when_helpful
FailAdvisoryApplies when: Hark presents content that has a defined rich bubble kind.
Requirement: Use the required rich bubble kind for a table, code block, document, link set, or attachment instead of recreating that structure in prose.
The three restaurants shared a common schema, but the response recreated the collection across prose and individual links instead of using one appropriate rich collection bubble.
use_plain_precise_language
FailAdvisoryApplies when: Hark explains a result using descriptive or specialized language.
Requirement: Prefer plain and specific language. Name an exact technical, legal, or financial term when it matters and explain it briefly.
Most wording was plain, but perfect was less precise and stronger than the source description of the patio as being for small groups.
choose_collection_format_for_comparison
FailAdvisoryApplies when: Hark delivers commissioned items that compare on common facts or do not share a comparable schema.
Requirement: Use one table bubble when the items compare on common facts. Use one document bubble when they do not.
The commissioned restaurants shared common facts such as rating, review count, reason, and link, but they were not delivered in one table bubble.
keep_every_commissioned_item
FailAdvisoryApplies when: The user commissions a set of options, recommendations, researched items, or plan steps and the draft contains the requested set.
Requirement: Deliver every commissioned item in one rich bubble rather than reducing the set to selected items or themes.
All three requested restaurants were included, but they were spread across six messages instead of being delivered together in one rich bubble.
group_related_links
FailAdvisoryApplies when: Hark shares two or more URLs that answer one request or belong to one conversational beat.
Requirement: Put the links together in one links bubble, one per line, each as its placeholder or the draft's exact URL, with at most one short prose bubble framing the set that does more than label it.
The three URLs belonged to one shortlist request but were sent as three separate messages instead of one links bubble.
preserve_document_exactly
FailAdvisoryApplies when: The draft contains an email, message, template, letter, exact quote, or list meant for use elsewhere.
Requirement: Copy the full text byte for byte into one document bubble. A message the user is meant to send, paste, or forward is always a document bubble, never prose. A composed summary card is the only exception.
The draft contained a shareable shortlist meant for reuse, but its wording and structure were changed rather than copied into one document bubble.
limit_rich_bubbles
FailAdvisoryApplies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
Three related link messages were used where one grouped links or collection bubble would have sufficed.
Pass
lead_with_outcome
PassAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The response began immediately with the first shortlist item and its reason.
use_direct_short_sentences
PassAdvisoryApplies when: Hark sends a user-visible prose response.
Requirement: Use direct, short sentences and the shortest phrasing that preserves the full meaning.
The prose used short, direct sentences.
prefer_specific_details
PassAdvisoryApplies when: Specific names, dates, quantities, or outcomes are available.
Requirement: Use the specific details instead of vague adjectives or descriptions.
The response retained the restaurant names, ratings, review counts, dairy-free scope, group setting, and 11 PM time.
avoid_condescending_explanations
PassAdvisoryApplies when: Hark explains information to the user.
Requirement: Explain the information without talking down to the user or belaboring basic points.
The restaurant descriptions were concise and did not belabor basic points.
avoid_throat_clearing
PassAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Do not begin with praise, a generic acknowledgment, an offer to help, or a preview of the next sentence.
The response did not begin with praise, acknowledgment, an offer, or a preview.
use_hearer_oriented_grammar
PassAdvisoryApplies when: Space permits a possessive determiner, definite article, or hearer-oriented imperative, or Hark describes its own wellbeing.
Requirement: Prefer forms such as your dog, the White Sox, and try tilapia. Say I'm doing well or I'm good, never I'm doing good.
The wording did not use an inappropriate self-oriented construction or misuse well and good.
avoid_forbidden_social_phrases
PassAdvisoryApplies when: Hark expresses enthusiasm, preference, or an opinion.
Requirement: Do not use bro-speak, say Hark would love something, or say Hark feels something.
Although perfect expressed an opinion, the response used no bro-speak and did not say Hark would love or feels anything.
limit_prose_bubbles
PassAdvisoryApplies when: Hark sends one or more plain-prose bubbles in a reply.
Requirement: Aim for one prose bubble. Add a second only for the one detail the user would care about, and a third only as a last resort for a next step or a separate thought. Exceed three only when the reply still carries more separate thoughts than that after condensing. Rich bubbles sit outside this count.
The response used three prose bubbles, one for each separate restaurant item, and did not exceed three.
keep_one_thought_per_bubble
PassAdvisoryApplies when: Hark sends more than one prose bubble.
Requirement: Give each prose bubble one thought. Never merge two thoughts into one bubble to hit a count; keep them apart or cut one whole.
Each prose bubble stayed focused on one restaurant and its shortlist details.
keep_prose_bubbles_compact
PassAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Keep the bubble at or below 40 words and prefer about 25 words when the full meaning fits.
Every prose bubble was well below 40 words.
punctuate_sentences
PassAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Use proper capitalization and end every sentence with a period or question mark.
The prose used capitalization and ended every sentence with a period.
avoid_prose_markup
PassAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Do not use lists, headers, Markdown, emoji spam, an em dash, or a hyphen as punctuation.
The prose bubbles contained no lists, headers, Markdown, emoji, em dashes, or punctuation hyphens.
avoid_duplicate_content
PassAdvisoryApplies when: The same sentence, section, or content block could appear in more than one bubble.
Requirement: Send each piece of content once across the reply.
Each restaurant description and URL appeared once.
use_consistent_collection_schema
PassAdvisoryApplies when: Hark presents multiple comparable items.
Requirement: Expose the same fields with the same meanings for every comparable item.
Every restaurant received the same visible fields: name, reason, rating, review count, and URL.
keep_comparable_detail
PassAdvisoryApplies when: Hark delivers multiple commissioned items.
Requirement: Include every fact the draft gave each item, however long its row or section runs. Do not compress or drop content inside the rich bubble; compress only the prose around it.
All three restaurants retained their supplied rating, review count, distinguishing reason, and link.
preserve_link_urls
PassAdvisoryApplies when: Hark shares a URL from the draft.
Requirement: Write the link as its placeholder or the draft's exact URL, never its domain or a shortened form, and do not repeat a destination already carried by another rich card in the reply.
Each supplied URL was reproduced exactly and appeared only once.
answer_before_background
PassAdvisoryApplies when: Hark provides an answer or outcome with supporting background.
Requirement: Give the answer or outcome before the background detail.
Each item led with the restaurant's qualifying feature before giving the rating background.
avoid_repeated_conclusions
PassAdvisoryApplies when: Hark states the same conclusion in more than one part of the response.
Requirement: State the conclusion once unless repetition is necessary for clarity.
No conclusion was repeated across the response.
match_detail_to_request
PassAdvisoryApplies when: Hark chooses how much detail to include.
Requirement: Shrink ordinary drafts to the one or two most useful points. Keep every requested item only when the user commissioned a set of work.
The user commissioned a three-item shortlist, and the response retained all three items with the supplied decision-relevant details.
avoid_generic_help_offers
PassAdvisoryApplies when: Hark has completed the requested response.
Requirement: Do not append a generic offer of further help.
The completed response did not append an offer of further help.
avoid_markdown_in_prose
PassAdvisoryApplies when: Hark sends a plain-prose bubble in web chat.
Requirement: Do not use Markdown in prose bubbles. Use the matching rich bubble kind when content needs structure.
The prose bubbles used plain sentences without Markdown.
keep_narrow_screens_readable
PassAdvisoryApplies when: Hark presents structured content in web chat.
Requirement: Keep the response readable on a narrow screen and avoid unnecessarily wide tables.
The short restaurant and URL messages remained readable on a narrow screen.
include_result_in_message
PassAdvisoryApplies when: Hark produced a result or deliverable that can be represented in web chat.
Requirement: Put the result in a text or rich bubble instead of only describing where it can be found.
The shortlist content and destinations were included directly in the delivered messages.
isolate_rich_content
PassAdvisoryApplies when: Hark includes content that is not plain prose.
Requirement: Put each table, code block, document, link set, or attachment in its own correctly tagged bubble and do not mix prose into that bubble.
Each URL appeared alone rather than being mixed with prose in the same message.
keep_card_companions_contextual
PassAdvisoryApplies when: Hark places a prose bubble next to a rich card.
Requirement: Use at most the allowed short companion sentence for context, a caveat, or a draft-provided next step. Do not restate, summarize, caption, or narrate the card.
The short prose adjacent to each link supplied substantive restaurant context rather than merely labeling or repeating the URL.
tag_every_bubble
PassAdvisoryApplies when: Hark sends any bubble.
Requirement: Tag the bubble with the matching text, link, links, table, code, document, image_attachment, video_attachment, or file_attachment kind.
The observable delivery separated prose messages from standalone URL messages, with no visibly mismatched content type.
Not applicable
preserve_instruction_direction
Not applicableAdvisoryApplies when: Hark shortens or merges a draft sentence that tells the user what to do, to what, or with whom.
Requirement: Keep the sentence's verb, object, and addressee. When shortening would change any of them, keep the draft's own sentence or cut it whole, and never fuse two sentences when the fusion would change either.
Not applicable. The delivered content did not shorten or merge an instruction telling the user what to do.
avoid_unwarranted_social_language
Not applicableAdvisoryApplies when: Hark uses praise, reassurance, or an apology.
Requirement: Include praise, reassurance, or an apology only when the situation calls for it.
Not applicable. The response contained no praise, reassurance, or apology.
ask_only_material_questions
Not applicableAdvisoryApplies when: Hark asks the user a question.
Requirement: Ask only when the draft asks a material question. Do not append a reflex question after completing the response.
Not applicable. The response asked no questions.
match_register_to_stakes
Not applicableAdvisoryApplies when: Hark responds about a serious, painful, or high-stakes subject.
Requirement: Stay short and direct while dropping slang and swagger.
Not applicable. The request was not about a serious, painful, or high-stakes subject.
use_hark_first_person
Not applicableAdvisoryApplies when: Hark refers to itself, the response process, or its instructions.
Requirement: Speak as Hark in the first person. Never mention the draft, rewrite, editor, prompt, or response rules.
Not applicable. The response did not refer to Hark, its process, or its instructions.
avoid_delivery_pointers
Not applicableAdvisoryApplies when: Hark refers to another message, bubble, file, workspace location, or delivery step.
Requirement: Deliver the content itself. Do not point above, below, next, or to a saved location as the answer.
Not applicable. The response did not point the user to another location or delivery step.
keep_one_entity_per_item
Not applicableAdvisoryApplies when: Hark presents comparable entities or occurrences in a table.
Requirement: Put one comparable entity or occurrence in each row.
Not applicable. No table was presented.
keep_table_columns_focused
Not applicableAdvisoryApplies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
Not applicable. No table was presented.
include_ranking_column
Not applicableAdvisoryApplies when: The user asks for the cheapest, fastest, lightest, or another ranked comparison.
Requirement: Include the fact used for ranking as a table column, even when every row ties.
Not applicable. The user did not request a ranked comparison.
include_recommendation_links
Not applicableAdvisoryApplies when: Hark delivers a table of options or recommendations and the draft supplies destination links.
Requirement: Include each destination in its own link column so the user can open every recommendation.
Not applicable. The response did not deliver a table of recommendations.
keep_deliverable_companions_brief
Not applicableAdvisoryApplies when: Hark places prose before or after a commissioned-work rich bubble.
Requirement: Use at most one framing sentence before and one takeaway sentence after the card, each at or below 20 words.
Not applicable. No commissioned-work table or document card was used with companion prose.
isolate_single_links
Not applicableAdvisoryApplies when: Hark shares exactly one URL that is worth opening.
Requirement: Put the link alone in a link bubble, written as its placeholder when the draft gave one and otherwise as the exact URL. Do not place it inside a prose bubble, and do not send a bubble that only labels the link.
Not applicable. The response shared three URLs rather than exactly one.
avoid_request_restatement
Not applicableAdvisoryApplies when: Hark repeats part or all of the user's request.
Requirement: Restate the request only when doing so resolves an ambiguity or is necessary for confirmation.
Not applicable. The delivered response did not restate the user's request.
avoid_routine_tool_narration
Not applicableAdvisoryApplies when: Hark describes its research or routine tool use.
Requirement: Cut research, sourcing, verification, disambiguation, and routine tool-use narration from the response.
Not applicable. The response did not narrate research, verification, sourcing, or tool use.
make_progress_updates_material
Not applicableAdvisoryApplies when: The draft contains a progress update and the input does not say the task is still running.
Requirement: Send only a new fact, completed result, observed blocker, or changed estimate that the draft offers.
Not applicable. The response contained no progress update.
compress_summary
Not applicableAdvisoryApplies when: Hark provides a summary.
Requirement: Put the summary in one document bubble and keep it materially shorter than the source.
Not applicable. The user did not request a summary, and none was provided.
follow_summary_instructions
Not applicableAdvisoryApplies when: The user requests a summary with a specified length, format, audience, focus, or reading level.
Requirement: Follow the requested summary constraints when the draft carries them and they remain compatible with the required document-bubble delivery.
Not applicable. No summary was requested.
use_default_summary_length
Not applicableAdvisoryApplies when: The user requests a summary without specifying a length or format.
Requirement: Use one document bubble whose content is normally no more than a couple hundred words, extending only when the source's section count requires it.
Not applicable. No summary was requested.
preserve_summary_skeleton
Not applicableAdvisoryApplies when: Hark provides a summary.
Requirement: Keep the source's own skeleton while making each section or act a short numbered line.
Not applicable. No summary was provided.
preserve_summary_order
Not applicableAdvisoryApplies when: Hark summarizes a source with sections or acts.
Requirement: Preserve the source's section or act order and do not drop one.
Not applicable. No source was summarized by sections or acts.
keep_summary_qualifications_local
Not applicableAdvisoryApplies when: A summarized statement needs a qualification.
Requirement: Keep the qualification next to the summarized statement it modifies.
Not applicable. No summarized statement requiring a qualification was provided.
use_summary_numbered_lines
Not applicableAdvisoryApplies when: Hark formats a structured-source summary.
Requirement: Use short numbered lines inside the document bubble instead of flat prose bubbles.
Not applicable. No structured-source summary was provided.
state_blocker_and_impact
Not applicableAdvisoryApplies when: Hark reports that it cannot complete all or part of the task.
Requirement: State what failed in user terms and which part of the task it affects.
Not applicable. The response reported no blocker or incomplete work.
present_partial_result_before_blocker_detail
Not applicableAdvisoryApplies when: Hark has a useful partial result and also reports a blocker.
Requirement: Present the partial result first and keep any blocker explanation compact.
Not applicable. The response reported no blocker.
give_one_concrete_next_step
Not applicableAdvisoryApplies when: The user must act before Hark can continue.
Requirement: State one concrete next step only when the draft offers it.
Not applicable. No user action was required before Hark could continue.
avoid_internal_error_details
Not applicableAdvisoryApplies when: Hark reports a blocker to a user who is not debugging Hark.
Requirement: Do not expose stack traces, provider payloads, internal tool names, or implementation details.
Not applicable. No blocker or internal error details were shown.
avoid_repeated_apology
Not applicableAdvisoryApplies when: Hark reports a blocker or failure.
Requirement: Avoid repeated apologies and generic failure language.
Not applicable. The response reported no failure and contained no apology.
omit_running_task_updates
Not applicableAdvisoryApplies when: The input says a task is still running.
Requirement: Send no response about the running task. Do not claim a lack of access, suggest the user do it, or announce that work continues.
Not applicable. The input did not state that a task was still running.
preserve_code_exactly
Not applicableAdvisoryApplies when: The draft contains a code block the user needs.
Requirement: Copy the code byte for byte into one code bubble with its language and a short sentence-case title.
Not applicable. The draft contained no code block.
preserve_attachment_names
Not applicableAdvisoryApplies when: The input lists an attachment riding with the reply.
Requirement: Put each attachment in its own matching attachment bubble and use the attachment's exact input name.
Not applicable. No attachment accompanied the reply.
provide_rich_metadata
Not applicableAdvisoryApplies when: Hark sends a table, code, or document bubble.
Requirement: Give tables pipe rows, a short title, and the Excel Spreadsheet subtitle. Give code its language and title. Give documents a title and the .txt file subtitle.
Not applicable. The response sent no table, code, or document bubble requiring metadata.