← Back to scenario detail
Response style analysis
Applied 46 · Passed 35 · Failed 11 · Not applicable 22
Rubric: services/agent/prompts/editor/v1.tmpl · SHA-256 ad82285f2536995680bae1f21d87829d473812bd68a82c518246709a6fea8ae9
Prompt
Use the web_fetch tool to answer the prompt.
Using https://www.flysfo.com/passengers/flight-info/flight-status, summarize current SFO departure delays and cancellations today. Identify the most affected destinations and the page timestamp.
Hark's responses
The flight status page loads with JavaScript, so a plain fetch returns only the shell. No flight rows, no delay or cancellation counts, no per-destination data, and no page timestamp. It only shows that results cover +12/-4 hours in local Pacific time.
SFO has a standing travel alert: FAA increased landing separation and runway closures mean about 30% of arriving flights are delayed at least 30 minutes. Runway opens early October 2026.
https://www.flysfo.com/passengers/flight-info/flight-status
https://www.flysfo.com/flight-info/alerts-advisories/travel-impact-faa-reduced-arrival-rates-and-runway-construction
Want me to open it in a browser to read today's departure rows?
Fail
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 delivered alert changes expected delays into observed delays and an expected reopening into a definite reopening.
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.
“Expected to be delayed” becomes “are delayed,” and “expected to reopen” becomes “opens,” changing certainty.
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.
The definite claims that flights “are delayed” and the runway “opens” are stronger facts than the source and draft contain.
keep_prose_bubbles_compact
FailAdvisoryApplies 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 first prose bubble is approximately 42 words, exceeding the 40-word target.
avoid_routine_tool_narration
FailAdvisoryApplies when: Hark describes its research or routine tool use.
Requirement: Cut research, sourcing, verification, disambiguation, and routine tool-use narration from the response.
It narrates the fetch method and page implementation with “loads with JavaScript” and “a plain fetch returns only the shell.”
compress_summary
FailAdvisoryApplies when: Hark provides a summary.
Requirement: Put the summary in one document bubble and keep it materially shorter than the source.
The summarized information is delivered in prose bubbles rather than one document bubble.
use_default_summary_length
FailAdvisoryApplies 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.
Although concise, the summary is not placed in the required single document bubble.
keep_summary_qualifications_local
FailAdvisoryApplies when: A summarized statement needs a qualification.
Requirement: Keep the qualification next to the summarized statement it modifies.
The source qualifies both the delay projection and reopening date as expectations, but those qualifications are removed.
present_partial_result_before_blocker_detail
FailAdvisoryApplies when: Hark has a useful partial result and also reports a blocker.
Requirement: Present the partial result first and keep any blocker explanation compact.
The arrival-alert partial result appears after the blocker explanation rather than before it.
avoid_internal_error_details
FailAdvisoryApplies 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 explanation exposes implementation details about JavaScript rendering and the limitations of a plain fetch.
keep_card_companions_contextual
FailAdvisoryApplies 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 links card is surrounded by multiple prose companions, and the preceding companion contains two sentences rather than one allowed short sentence.
Pass
follow_explicit_style_instructions
PassAdvisoryApplies 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 stays focused on the requested departure status fields and explains that the fetched page did not expose them.
lead_with_outcome
PassAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The response begins with the blocker and immediately states which requested data is unavailable.
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 wording is direct and mostly uses short declarative 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.
It uses the available figures and timing: +12/-4 hours, 30%, 30 minutes, and early October 2026.
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 technical limitation is explained plainly without belaboring basic concepts.
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 starts directly with the page limitation rather than praise or a generic acknowledgment.
use_structure_only_when_helpful
PassAdvisoryApplies 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 two related destinations are separated from prose and presented together.
use_plain_precise_language
PassAdvisoryApplies 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 response uses clear terms such as flight rows, cancellation counts, destination data, JavaScript, and Pacific time.
ask_only_material_questions
PassAdvisoryApplies 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.
The sole question requests permission for a concrete method needed to obtain the missing departure rows, and it was present in the draft.
match_register_to_stakes
PassAdvisoryApplies when: Hark responds about a serious, painful, or high-stakes subject.
Requirement: Stay short and direct while dropping slang and swagger.
The travel-status response is concise, professional, and free of slang or swagger.
use_hark_first_person
PassAdvisoryApplies 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.
The response uses first person in “Want me” and does not mention a draft, editor, prompt, or response rules.
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 closing question directly addresses the user and uses natural conversational grammar.
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.
There are three prose bubbles: the blocker, one contextual alert, and one separate next-step question.
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.
The prose bubbles separately cover the fetch limitation, the arrival alert, and the proposed next step.
punctuate_sentences
PassAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Use proper capitalization and end every sentence with a period or question mark.
Every prose sentence is capitalized and ends with a period or question mark.
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 contain no lists, headings, Markdown, emoji, or dash punctuation.
avoid_delivery_pointers
PassAdvisoryApplies 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.
The browser reference is a concrete proposed next step, not a pointer to another message or saved location as the answer.
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.
The blocker, alert, URLs, and next step each appear once.
group_related_links
PassAdvisoryApplies 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 two related SFO URLs are grouped together, one per line.
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.
Both URLs are presented in their exact source forms without shortening.
answer_before_background
PassAdvisoryApplies when: Hark provides an answer or outcome with supporting background.
Requirement: Give the answer or outcome before the background detail.
The missing-data outcome appears before the contextual arrival alert.
avoid_request_restatement
PassAdvisoryApplies 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 names the missing requested fields to explain the block rather than redundantly restating the request.
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.
The conclusion that the requested departure data is unavailable is stated once.
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 response limits itself to the blocker, one relevant contextual alert, the sources, and a concrete next step.
follow_summary_instructions
PassAdvisoryApplies 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 response addresses the requested focus by identifying exactly which departure-summary fields could not be obtained.
preserve_summary_skeleton
PassAdvisoryApplies when: Hark provides a summary.
Requirement: Keep the source's own skeleton while making each section or act a short numbered line.
The summarized alert has one substantive paragraph and no section or act structure to omit or reorder.
state_blocker_and_impact
PassAdvisoryApplies 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.
It states that the JavaScript departure board was unavailable to the fetch and lists the affected outputs: rows, counts, destinations, and timestamp.
give_one_concrete_next_step
PassAdvisoryApplies when: The user must act before Hark can continue.
Requirement: State one concrete next step only when the draft offers it.
It gives one draft-supported next step: open the board in a browser to read today’s departure rows.
avoid_repeated_apology
PassAdvisoryApplies when: Hark reports a blocker or failure.
Requirement: Avoid repeated apologies and generic failure language.
The blocker is stated directly with no apology or repeated generic failure language.
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 contain no Markdown; the URLs are isolated in their own bubble.
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 structured content is only two URLs on separate lines and does not create a wide layout.
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 blocker, available timing scope, contextual alert, and source URLs are included directly in the response.
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.
The two URLs are isolated from the prose in their own bubble.
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 separates three prose bubbles from one two-link bubble in a manner matching their content types.
limit_rich_bubbles
PassAdvisoryApplies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
The response uses one rich links bubble.
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 response does not shorten or merge a user-directed instruction from the draft.
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 contains no praise, reassurance, or apology.
avoid_forbidden_social_phrases
Not applicableAdvisoryApplies 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 applicableAdvisoryApplies 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. No set of comparable commissioned destinations was available or delivered.
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 of comparable entities is presented.
use_consistent_collection_schema
Not applicableAdvisoryApplies when: Hark presents multiple comparable items.
Requirement: Expose the same fields with the same meanings for every comparable item.
Not applicable. No collection of comparable items is presented.
keep_comparable_detail
Not applicableAdvisoryApplies 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. No multiple commissioned items are delivered.
keep_table_columns_focused
Not applicableAdvisoryApplies 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 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 such as cheapest or fastest.
keep_every_commissioned_item
Not applicableAdvisoryApplies 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 a requested set of affected destinations to deliver.
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. No table of options or recommendations is delivered.
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. There is no commissioned-work rich bubble.
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 shares two URLs rather than exactly one.
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 delivered response is a completed blocker report, not a progress update.
avoid_generic_help_offers
Not applicableAdvisoryApplies when: Hark has completed the requested response.
Requirement: Do not append a generic offer of further help.
Not applicable. The requested task was blocked rather than completed, and the closing question proposes a specific action rather than generic help.
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. The substantive alert being summarized has no sections or acts.
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. The substantive source being summarized is not structured into sections or acts.
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 tool calls had completed before the response was sent.
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. No needed code block appears in the draft or response.
preserve_document_exactly
Not applicableAdvisoryApplies 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 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 attachments are listed in the input.
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. No table, code, or document bubble is sent.