← Back to scenario detail

Response style analysis

Applied 39 · Passed 16 · Failed 23 · Not applicable 29

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

Prompt

Use the web_fetch tool to answer the prompt. Using the latest standings on https://www.mlb.com/standings, identify the closest MLB division and wild-card races, current tiebreaker positions, and games remaining.

Hark's responses

Last updated Sep 11, 5:09 PM ET. Several games live, so these shift tonight.
### Tightest division and wild card races · MLB standings | Race | Leader | Chaser | Margin | Gm left (ldr/chaser) | |---|---|---|---|---| | NL Wild Card 3 | Padres 78-68 | D-backs 78-69 | 0.5 | 16 / 15 | | AL Central | White Sox 75-71 | Guardians 74-73 | 1.5 | 16 / 15 | | AL Wild Card 3 | Guardians 74-73 | Blue Jays 73-74 | 1.0 | 15 / 15 | | AL East | Rays 87-59 | Yankees 84-62 | 3.0 | 16 / 16 | | AL West | Astros 75-72 | Rangers 72-75 | 3.0 | 15 / 15 | | NL East | Braves 86-61 | Phillies 82-65 | 4.0 | 15 / 15 |
Padres-D-backs is a tie in the loss column; Guardians-Blue Jays same shape. NL Central (Brewers up 9.5) and NL West (Dodgers up 11.0) are over.
https://www.mlb.com/standings

Fail

preserve_draft_substance

FailAdvisory
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 response omitted the draft’s wild-card order and tiebreaker explanation. It also changed “effectively over” to the more certain “are over.”

preserve_factual_spans

FailAdvisory
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.
Most names and numbers were preserved, but “effectively over” became “are over,” changing the certainty of the claim.

lead_with_outcome

FailAdvisory
Applies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The response led with an update timestamp and live-game caveat rather than the closest races or tiebreaker result.

use_structure_only_when_helpful

FailAdvisory
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 comparison was rendered as Markdown table syntax rather than an observably tagged table bubble.

use_plain_precise_language

FailAdvisory
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.
“Same shape” is vague, and “are over” overstates races the draft described as only effectively over.

limit_prose_bubbles

FailAdvisory
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.
Four assistant-message bubbles were delivered, and the structured content was not observably tagged as rich content.

keep_one_thought_per_bubble

FailAdvisory
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.
The final prose bubble combines a tiebreaker observation with separate conclusions about the NL Central and NL West.

keep_prose_bubbles_compact

FailAdvisory
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.
The Markdown table message greatly exceeds 40 words and is not observably isolated as a rich table bubble.

punctuate_sentences

FailAdvisory
Applies when: Hark sends a plain-prose bubble.
Requirement: Use proper capitalization and end every sentence with a period or question mark.
The table title and cells are fragments, and the standalone URL does not end with sentence punctuation; neither is observably tagged as rich content.

avoid_prose_markup

FailAdvisory
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.
The response uses a Markdown heading and Markdown table syntax in an assistant message.

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 races share a common schema, but the response used a Markdown table rather than an observably tagged table bubble.

keep_comparable_detail

FailAdvisory
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.
The response omitted the additional AL and NL wild-card positions and tiebreaker details carried by the draft.

keep_every_commissioned_item

FailAdvisory
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.
The response delivered the race rows but did not deliver the draft’s full wild-card order or its explanation of current tiebreaker positioning.

keep_deliverable_companions_brief

FailAdvisory
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.
The framing bubble has two sentences, and the post-table bubble has two sentences and exceeds the 20-word companion limit.

isolate_single_links

FailAdvisory
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.
The URL is isolated and exact, but it is not observably delivered as a link-tagged bubble.

answer_before_background

FailAdvisory
Applies when: Hark provides an answer or outcome with supporting background.
Requirement: Give the answer or outcome before the background detail.
The timestamp and live-game caveat appeared before the actual race comparison.

match_detail_to_request

FailAdvisory
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 user explicitly requested current tiebreaker positions, but the response omitted the draft’s tiebreaker-order explanation and most wild-card positioning detail.

avoid_markdown_in_prose

FailAdvisory
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.
The response visibly contains a Markdown heading and pipe-table syntax.

isolate_rich_content

FailAdvisory
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.
The table and URL were separated into their own messages, but neither is observably carried in the required correctly tagged rich bubble.

keep_card_companions_contextual

FailAdvisory
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.
The post-table prose summarizes table-related conclusions, contains two separate thoughts, and exceeds the allowed 20 words.

tag_every_bubble

FailAdvisory
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 evidence shows generic assistant messages, with no observable matching text, table, or link bubble tags.

limit_rich_bubbles

FailAdvisory
Applies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
The response presents both a comparison table and a separate source URL even though they are part of one standings deliverable, and neither is observably tagged.

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 table has a title and pipe rows, but no observable “Excel Spreadsheet” subtitle or other required rich-table metadata.

Pass

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 delivered claims, figures, and source URL all appeared in the draft.

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.
The prose sentences were short and direct.

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 used specific teams, records, margins, games remaining, and an update time.

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 did not talk down to the user or explain basic concepts at excessive length.

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.
The response did not begin with praise, acknowledgment, an offer, or a preview.

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.
No wording called for a different possessive, article, imperative, or statement about Hark’s wellbeing.

keep_one_entity_per_item

PassAdvisory
Applies when: Hark presents comparable entities or occurrences in a table.
Requirement: Put one comparable entity or occurrence in each row.
Each table row represents one race.

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 race row uses the same leader, chaser, margin, and games-remaining fields.

keep_table_columns_focused

PassAdvisory
Applies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
The columns directly support comparison of race closeness and games remaining.

include_ranking_column

PassAdvisory
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.
The table includes the margin used to identify the closest races.

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.
The MLB standings URL was preserved exactly and appeared only once.

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 did not unnecessarily restate the user’s request.

make_progress_updates_material

PassAdvisory
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.
The update time and warning that live games could change the standings were concrete facts supported by the draft.

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 did not append an offer of further help.

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 comparison uses only five focused columns with abbreviated labels, limiting horizontal width.

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 race comparison and games-remaining result were included directly in the response.

Not applicable

follow_explicit_style_instructions

Not applicableAdvisory
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.
Not applicable. The user did not specify a response length, tone, audience, or presentation format.

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 response did not shorten or merge a draft instruction to the user.

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 used 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 asked 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 subject was not serious, painful, or high-stakes.

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 did 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 expressed no enthusiasm, preference, or opinion.

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 did not point the user to another bubble or saved location instead of delivering the result.

avoid_duplicate_content

Not applicableAdvisory
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.
Not applicable. No sentence or content block was repeated across bubbles.

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 table contains standings, not options or recommendations with destination links.

group_related_links

Not applicableAdvisory
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.
Not applicable. The response shared only one URL.

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 response did not narrate fetching, researching, or verifying the standings.

avoid_repeated_conclusions

Not applicableAdvisory
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.
Not applicable. No conclusion was stated more than once.

compress_summary

Not applicableAdvisory
Applies 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, and the response did not present, a source summary.

follow_summary_instructions

Not applicableAdvisory
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.
Not applicable. There were no summary-specific instructions.

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 did not request a summary.

preserve_summary_skeleton

Not applicableAdvisory
Applies when: Hark provides a summary.
Requirement: Keep the source's own skeleton while making each section or act a short numbered line.
Not applicable. The response was not a summary of a structured source.

preserve_summary_order

Not applicableAdvisory
Applies 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. The response did not summarize sections or acts.

keep_summary_qualifications_local

Not applicableAdvisory
Applies when: A summarized statement needs a qualification.
Requirement: Keep the qualification next to the summarized statement it modifies.
Not applicable. No structured summary was provided.

use_summary_numbered_lines

Not applicableAdvisory
Applies 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 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 reported no blocker or inability to complete the task.

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. No blocker was reported.

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. No user action was required before Hark could 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 details were reported.

avoid_repeated_apology

Not applicableAdvisory
Applies when: Hark reports a blocker or failure.
Requirement: Avoid repeated apologies and generic failure language.
Not applicable. No failure or apology was reported.

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 web-fetch task had completed before the response was sent.

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 contained no needed code block.

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 draft contained no reusable email, message, template, letter, exact quote, or document.

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 accompanied the response.