← Back to scenario detail

Response style analysis

Applied 36 · Passed 30 · Failed 6 · Not applicable 32

Rubric: services/agent/prompts/editor/v1.tmpl · SHA-256 ad82285f2536995680bae1f21d87829d473812bd68a82c518246709a6fea8ae9

Prompt

I already verified these notes, so do not research them. Give me exactly one sentence per article, with the article's link in that sentence. Then add one sentence naming the main theme. Atlas compiler update: the team replaced its interpreter with a native compiler to reduce startup time. It has 103 points and 308 comments. https://example.com/articles/atlas-compiler Harbor database update: the project added online schema changes for large production tables. It has 241 points and 36 comments. https://example.com/articles/harbor-database Meadow accessibility study: researchers found that descriptive button labels reduced navigation errors. It has 77 points and 19 comments. https://example.com/articles/meadow-accessibility Orbit battery report: the new cell chemistry retained 92 percent capacity after 1,000 cycles. It has 164 points and 52 comments. https://example.com/articles/orbit-battery

Hark's responses

```document title="The Atlas team replaced its interpreter with" The Atlas team replaced its interpreter with a native compiler to cut startup time, drawing 103 points and 308 comments: [Atlas compiler update](https://example.com/articles/atlas-compiler). Harbor added online schema changes for large production tables, with 241 points and 36 comments: [Harbor database update](https://example.com/articles/harbor-database). Researchers found descriptive button labels reduced navigation errors, with 77 points and 19 comments: [Meadow accessibility study](https://example.com/articles/meadow-accessibility). A new cell chemistry retained 92 percent capacity after 1,000 cycles, with 164 points and 52 comments: [Orbit battery report](https://example.com/articles/orbit-battery). The main theme is measurable engineering gains, where a concrete technical change yields a quantified improvement in speed, safety, usability, or durability. ```

Fail

choose_collection_format_for_comparison

FailAdvisory
Applies 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 four commissioned articles share comparable fields such as points, comments, findings, and links, but they are delivered in a document rather than one table bubble.

group_related_links

FailAdvisory
Applies 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 four related URLs are embedded in the document instead of being grouped in one links bubble.

compress_summary

FailAdvisory
Applies when: Hark provides a summary.
Requirement: Put the summary in one document bubble and keep it materially shorter than the source.
Although the summary is in one document bubble, it largely restates every supplied fact and adds a theme, so it is not materially shorter than the source notes.

preserve_summary_skeleton

FailAdvisory
Applies when: Hark provides a summary.
Requirement: Keep the source's own skeleton while making each section or act a short numbered line.
The response preserves the four-item skeleton but does not format each source item as a short numbered line.

use_summary_numbered_lines

FailAdvisory
Applies when: Hark formats a structured-source summary.
Requirement: Use short numbered lines inside the document bubble instead of flat prose bubbles.
The structured-source summary uses separate paragraphs rather than numbered lines inside the document bubble.

provide_rich_metadata

FailAdvisory
Applies 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.
The document has a truncated, non-descriptive title and does not provide the required .txt file subtitle.

Pass

follow_explicit_style_instructions

PassAdvisory
Applies 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 response gives exactly one sentence for each of the four articles, includes each article link in its sentence, and ends with one sentence naming the main theme.

preserve_draft_substance

PassAdvisory
Applies 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 delivered document preserves the substance and commitments of the drafted response without changing its selected claims.

preserve_factual_spans

PassAdvisory
Applies 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.
The article subjects, point totals, comment totals, battery figures, and exact destination URLs retain their values and scope.

avoid_invented_content

PassAdvisory
Applies 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.
The response adds no content beyond the draft; the requested thematic synthesis is also present in the draft.

lead_with_outcome

PassAdvisory
Applies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The response begins immediately with the first requested article sentence.

use_direct_short_sentences

PassAdvisory
Applies when: Hark sends a user-visible prose response.
Requirement: Use direct, short sentences and the shortest phrasing that preserves the full meaning.
Each article is covered in one direct sentence, followed by one concise thematic sentence.

prefer_specific_details

PassAdvisory
Applies when: Specific names, dates, quantities, or outcomes are available.
Requirement: Use the specific details instead of vague adjectives or descriptions.
The response includes the specific point totals, comment totals, capacity percentage, cycle count, and technical outcomes.

avoid_condescending_explanations

PassAdvisory
Applies when: Hark explains information to the user.
Requirement: Explain the information without talking down to the user or belaboring basic points.
The response states the findings directly without explaining basic concepts or talking down to the user.

avoid_throat_clearing

PassAdvisory
Applies 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.
There is no praise, acknowledgment, offer, or preview before the requested content.

use_structure_only_when_helpful

PassAdvisory
Applies 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 multi-item summary is placed in a document bubble rather than recreated as an untagged prose message.

use_plain_precise_language

PassAdvisory
Applies 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.
The technical changes and outcomes are named in plain, specific language.

use_hearer_oriented_grammar

PassAdvisory
Applies 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 response uses natural definite constructions and contains no incorrect statement about Hark's wellbeing.

avoid_duplicate_content

PassAdvisory
Applies 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 article summary and the theme appear once.

use_consistent_collection_schema

PassAdvisory
Applies when: Hark presents multiple comparable items.
Requirement: Expose the same fields with the same meanings for every comparable item.
Every article sentence consistently supplies the article identity, substantive update or finding, point total, comment total, and link.

keep_comparable_detail

PassAdvisory
Applies 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 four commissioned articles retain their supplied substantive fact, point total, comment total, and destination link.

keep_every_commissioned_item

PassAdvisory
Applies 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 four commissioned article summaries are included together in one rich bubble.

preserve_link_urls

PassAdvisory
Applies 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.
All four destinations use the exact URLs supplied by the user, without shortening or alteration.

answer_before_background

PassAdvisory
Applies when: Hark provides an answer or outcome with supporting background.
Requirement: Give the answer or outcome before the background detail.
Each sentence states the article's result before or alongside its supporting engagement figures, with no preliminary background section.

avoid_request_restatement

PassAdvisory
Applies 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.
The response does not restate the user's instructions.

avoid_repeated_conclusions

PassAdvisory
Applies 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.
The main thematic conclusion is stated once.

match_detail_to_request

PassAdvisory
Applies 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 response keeps every requested article while limiting each to the requested single sentence and adding only the requested theme sentence.

avoid_generic_help_offers

PassAdvisory
Applies when: Hark has completed the requested response.
Requirement: Do not append a generic offer of further help.
The completed response does not append an offer of further help.

follow_summary_instructions

PassAdvisory
Applies 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.
The summary follows the requested one-sentence-per-article format, places each link in its article sentence, and adds one theme sentence.

preserve_summary_order

PassAdvisory
Applies when: Hark summarizes a source with sections or acts.
Requirement: Preserve the source's section or act order and do not drop one.
Atlas, Harbor, Meadow, and Orbit remain in the source order, and none is dropped.

keep_summary_qualifications_local

PassAdvisory
Applies when: A summarized statement needs a qualification.
Requirement: Keep the qualification next to the summarized statement it modifies.
Qualifications remain beside the claims they modify, such as 92 percent capacity after 1,000 cycles and schema changes for large production tables.

keep_narrow_screens_readable

PassAdvisory
Applies when: Hark presents structured content in web chat.
Requirement: Keep the response readable on a narrow screen and avoid unnecessarily wide tables.
The document uses short standalone paragraphs and no wide table, making it readable on a narrow screen.

include_result_in_message

PassAdvisory
Applies 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 complete requested result is included directly in the document bubble.

isolate_rich_content

PassAdvisory
Applies 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.
All non-prose content is contained in one explicitly tagged document bubble.

tag_every_bubble

PassAdvisory
Applies 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 sole bubble is tagged as a document.

limit_rich_bubbles

PassAdvisory
Applies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
The response uses exactly one rich bubble.

Not applicable

preserve_instruction_direction

Not applicableAdvisory
Applies 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 does not shorten or merge a draft sentence directing the user to take an action.

avoid_unwarranted_social_language

Not applicableAdvisory
Applies 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 contains no praise, reassurance, or apology.

ask_only_material_questions

Not applicableAdvisory
Applies 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 asks no questions.

match_register_to_stakes

Not applicableAdvisory
Applies 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 does not concern a serious, painful, or high-stakes personal subject.

use_hark_first_person

Not applicableAdvisory
Applies 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 does not refer to Hark, its process, or its instructions.

avoid_forbidden_social_phrases

Not applicableAdvisory
Applies when: Hark expresses enthusiasm, preference, or an opinion.
Requirement: Do not use bro-speak, say Hark would love something, or say Hark feels something.
Not applicable. The response expresses no enthusiasm, personal preference, or personal feeling.

limit_prose_bubbles

Not applicableAdvisory
Applies 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.
Not applicable. The response contains a document bubble rather than plain-prose bubbles.

keep_one_thought_per_bubble

Not applicableAdvisory
Applies 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.
Not applicable. The response does not contain multiple prose bubbles.

keep_prose_bubbles_compact

Not applicableAdvisory
Applies 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.
Not applicable. No plain-prose bubble is present.

punctuate_sentences

Not applicableAdvisory
Applies when: Hark sends a plain-prose bubble.
Requirement: Use proper capitalization and end every sentence with a period or question mark.
Not applicable. This rule applies specifically to plain-prose bubbles, and the response uses a document bubble.

avoid_prose_markup

Not applicableAdvisory
Applies when: Hark sends a plain-prose bubble.
Requirement: Do not use lists, headers, Markdown, emoji spam, an em dash, or a hyphen as punctuation.
Not applicable. No plain-prose bubble is present.

avoid_delivery_pointers

Not applicableAdvisory
Applies 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 does not point to another message, location, file, or delivery step.

keep_one_entity_per_item

Not applicableAdvisory
Applies when: Hark presents comparable entities or occurrences in a table.
Requirement: Put one comparable entity or occurrence in each row.
Not applicable. The response does not present a table.

keep_table_columns_focused

Not applicableAdvisory
Applies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
Not applicable. The response contains no table.

include_ranking_column

Not applicableAdvisory
Applies 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 ask for a ranked comparison.

include_recommendation_links

Not applicableAdvisory
Applies 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 is not a table of options or recommendations.

keep_deliverable_companions_brief

Not applicableAdvisory
Applies 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. There are no prose bubbles before or after the commissioned-work document.

isolate_single_links

Not applicableAdvisory
Applies 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 shares four URLs rather than exactly one.

avoid_routine_tool_narration

Not applicableAdvisory
Applies 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 user-visible response contains no research, verification, or tool-use narration.

make_progress_updates_material

Not applicableAdvisory
Applies 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 contains no progress update.

use_default_summary_length

Not applicableAdvisory
Applies 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. The user specified the summary format and sentence allocation.

state_blocker_and_impact

Not applicableAdvisory
Applies 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 reports no blocker or incomplete work.

present_partial_result_before_blocker_detail

Not applicableAdvisory
Applies 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. There is no blocker or partial-result report.

give_one_concrete_next_step

Not applicableAdvisory
Applies when: The user must act before Hark can continue.
Requirement: State one concrete next step only when the draft offers it.
Not applicable. The user does not need to act before Hark can continue.

avoid_internal_error_details

Not applicableAdvisory
Applies 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 information is reported.

avoid_repeated_apology

Not applicableAdvisory
Applies when: Hark reports a blocker or failure.
Requirement: Avoid repeated apologies and generic failure language.
Not applicable. The response reports no failure and contains no apology.

omit_running_task_updates

Not applicableAdvisory
Applies 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 does not indicate that the task is still running.

avoid_markdown_in_prose

Not applicableAdvisory
Applies 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.
Not applicable. The response uses a document bubble, not a plain-prose bubble.

keep_card_companions_contextual

Not applicableAdvisory
Applies 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.
Not applicable. No prose companion bubble appears next to the document card.

preserve_code_exactly

Not applicableAdvisory
Applies 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 contains no code block needed by the user.

preserve_document_exactly

Not applicableAdvisory
Applies 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.
Not applicable. The content is a composed summary rather than an email, message, template, letter, exact quote, or reusable list requiring byte-exact document preservation.

preserve_attachment_names

Not applicableAdvisory
Applies 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 is listed in the input.