← Back to scenario detail

Response style analysis

Applied 39 · Passed 32 · Failed 7 · Not applicable 29

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

Prompt

Use the web_fetch tool to answer the prompt. What planned London Underground, Elizabeth line, and Overground closures does https://tfl.gov.uk/tube-dlr-overground/status/ list for next weekend? Organize them by day.

Hark's responses

That page stops at Friday 18 Sept and shows live disruptions, not planned work. No 19-20 Sept closures listed.
This weekend (12-13 Sept) has 10 lines Saturday and 6 Sunday if that helps.
For next weekend, check TfL's 6-month planned closures PDF.
https://tfl.gov.uk/cdn/static/cms/documents/planned-track-closures.pdf

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 delivered response changes the draft's offer to retrieve the PDF entries into an instruction for the user to check the PDF.
Evidence: E0010, E0014

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.
The draft says the page flags specified lines, while the response reduces this to the less precise claim that the weekend 'has' 10 and 6 lines, changing the claim's scope.
Evidence: E0010, E0013

preserve_instruction_direction

FailAdvisory
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.
The draft offers for Hark to pull the entries, but the response directs the user to check the PDF instead. This changes the actor and action.
Evidence: E0010, E0014

avoid_invented_content

FailAdvisory
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 instruction for the user to check the PDF is a new next step; the draft instead offered for Hark to retrieve the entries.
Evidence: E0010, E0014

prefer_specific_details

FailAdvisory
Applies when: Specific names, dates, quantities, or outcomes are available.
Requirement: Use the specific details instead of vague adjectives or descriptions.
The response gives only counts for 12–13 September even though the specific affected line names were available in the draft.
Evidence: E0010, E0013

avoid_delivery_pointers

FailAdvisory
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.
Instead of delivering the next-weekend entries, the response tells the user to check an external PDF.
Evidence: E0014, E0015

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 companion sentence directs the user to perform the next step, although the draft offered for Hark to retrieve the entries. It functions as a delivery pointer rather than a preserved contextual caveat.
Evidence: E0010, E0014, E0015

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 identifies Saturday and Sunday separately, preserving the requested day-based organization where dates are discussed.
Evidence: E0001, E0013

lead_with_outcome

PassAdvisory
Applies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The first bubble immediately states that the page has no listings for 19–20 September.
Evidence: E0012

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 response uses short, direct sentences throughout.
Evidence: E0012, E0013, E0014

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 explanation is concise and neutral, without belaboring basic points.
Evidence: E0012, E0013, E0014

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 begins with the result rather than praise, acknowledgment, or a preview.
Evidence: E0012

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 single URL is separated from the prose rather than embedded in a prose paragraph.
Evidence: E0014, E0015

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 wording is plain and readily understandable.
Evidence: E0012, E0013, E0014

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 a direct hearer-oriented imperative: 'check TfL's ... PDF.'
Evidence: E0014

limit_prose_bubbles

PassAdvisory
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.
There are three prose bubbles, followed by one isolated URL bubble.
Evidence: E0012, E0013, E0014, E0015

keep_one_thought_per_bubble

PassAdvisory
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 prose bubbles respectively cover the page limitation, the nearer weekend, and the PDF next step.
Evidence: E0012, E0013, E0014

keep_prose_bubbles_compact

PassAdvisory
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.
Every prose bubble is well below 40 words.
Evidence: E0012, E0013, E0014

punctuate_sentences

PassAdvisory
Applies when: Hark sends a plain-prose bubble.
Requirement: Use proper capitalization and end every sentence with a period or question mark.
Each prose sentence is capitalized and ends with a period.
Evidence: E0012, E0013, E0014

avoid_prose_markup

PassAdvisory
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 prose contains no headers, lists, Markdown, emoji, or dash punctuation.
Evidence: E0012, E0013, E0014

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.
No sentence or content block is repeated across bubbles.
Evidence: E0012, E0013, E0014, E0015

keep_deliverable_companions_brief

PassAdvisory
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 prose immediately before the URL is one short sentence under 20 words.
Evidence: E0014, E0015

isolate_single_links

PassAdvisory
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 single exact URL appears alone in its own bubble.
Evidence: E0015

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 PDF URL is reproduced exactly as it appeared in the draft and tool result.
Evidence: E0009, E0010, E0015

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.
The response first states that no 19–20 September closures are listed, then gives supporting context.
Evidence: E0012, E0013

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 request.
Evidence: E0001, E0012

avoid_routine_tool_narration

PassAdvisory
Applies when: Hark describes its research or routine tool use.
Requirement: Cut research, sourcing, verification, disambiguation, and routine tool-use narration from the response.
The response does not narrate web fetching, verification, or other tool use.
Evidence: E0012, E0013, E0014

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 conclusion that the requested dates are not listed appears once.
Evidence: E0012

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.
Given that the fetched page did not contain the requested weekend, the response stays concise and focuses on the limitation and available source.
Evidence: E0006, E0012, E0014

avoid_generic_help_offers

PassAdvisory
Applies when: Hark has completed the requested response.
Requirement: Do not append a generic offer of further help.
The response does not append a generic offer of further help.
Evidence: E0014, E0015

state_blocker_and_impact

PassAdvisory
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.
The response states that the page stops at 18 September and therefore lists no closures for 19–20 September.
Evidence: E0012

avoid_internal_error_details

PassAdvisory
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.
The blocker is described in user terms without internal tools, payloads, or implementation details.
Evidence: E0012

avoid_repeated_apology

PassAdvisory
Applies when: Hark reports a blocker or failure.
Requirement: Avoid repeated apologies and generic failure language.
The response contains no apology or repeated failure language.
Evidence: E0012, E0014

avoid_markdown_in_prose

PassAdvisory
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 prose bubbles contain no Markdown formatting.
Evidence: E0012, E0013, E0014

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 isolated URL and short prose bubbles remain readable on a narrow screen.
Evidence: E0012, E0013, E0014, E0015

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 available result—that the page lists no closures for 19–20 September—is stated directly in the message.
Evidence: E0012

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.
The URL is isolated from the prose in its own bubble.
Evidence: E0014, E0015

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 user-visible evidence shows prose as separate assistant messages and the URL isolated as its own message, consistent with matching text and link bubbles.
Evidence: E0012, E0013, E0014, E0015

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 only one rich-content item: the isolated URL.
Evidence: E0015

Not applicable

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 delivered response asks no question.

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 is 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 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, preference, or opinion.

choose_collection_format_for_comparison

Not applicableAdvisory
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.
Not applicable. The response does not deliver a collection of commissioned closure items for comparison.

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. No table is presented.

use_consistent_collection_schema

Not applicableAdvisory
Applies when: Hark presents multiple comparable items.
Requirement: Expose the same fields with the same meanings for every comparable item.
Not applicable. No multi-item collection is presented.

keep_comparable_detail

Not applicableAdvisory
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.
Not applicable. The response does not deliver multiple commissioned closure items.

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. No table is presented.

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 request a ranked comparison.

keep_every_commissioned_item

Not applicableAdvisory
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.
Not applicable. The draft did not contain the requested set of closures for 19–20 September.
Evidence: E0010

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. No recommendation table is presented.

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. Only one URL is shared.

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 delivered response is not a progress update.

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 response is not presented as a summary of a source.

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. The user did not request a summary.

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. No summary is provided.

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. No sectioned or act-based source is summarized.

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 summary statements requiring local qualifications are presented.

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 is presented.

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. The 12–13 September counts concern a different weekend and are not a partial result for the requested 19–20 September set.
Evidence: E0013

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 evidence does not show that user action was required before Hark could continue; the draft indicated Hark could retrieve the entries itself.
Evidence: E0010

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 task was not still running when the response was delivered.
Evidence: E0006, E0009, E0011

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 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 contains no email, message, template, letter, exact quote, or reusable 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 rides with the reply.

provide_rich_metadata

Not applicableAdvisory
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.
Not applicable. No table, code, or document bubble is sent.