← Back to scenario detail
Response style analysis
Applied 46 · Passed 30 · Failed 16 · Not applicable 22
Rubric: services/agent/prompts/editor/v1.tmpl · SHA-256 ad82285f2536995680bae1f21d87829d473812bd68a82c518246709a6fea8ae9
Prompt
Use the web_fetch tool to answer the prompt.
Which Michelin-recognized San Francisco restaurants on https://www.opentable.com/ have a table for two between 6:30 and 8:00 p.m. next Saturday? List the available times.
Hark's responses
OpenTable blocked plain fetches, so I checked on a browser. Here's what's open Sat Sep 19 for two in that window. Note that OpenTable shows 'Award-winning' only, not which Michelin tier.
### Michelin-recognized restaurants with availability · OpenTable
| Restaurant | Area | Times |
|---|---|---|
| [A16](https://www.opentable.com/r/a16-san-francisco) | Marina | 6:30, 6:45, 7:00, 7:15, 7:30 |
| [Bansang](https://www.opentable.com/r/bansang-san-francisco) | Western Addition | 6:30, 6:45, 7:15, 7:30 |
| [Kitchen Istanbul](https://www.opentable.com/kitchen-istanbul) | Richmond | 6:30, 6:45, 7:00, 7:15, 7:30 |
| [Okane](https://www.opentable.com/okane) | SOMA | 6:30, 6:45, 7:00, 7:15, 7:30 |
| [Trestle](https://www.opentable.com/r/trestle-san-francisco) | FiDi | 7:30, 7:45 |
| [O' by Claude Le Tohic](https://www.opentable.com/r/o-by-claude-le-tohic-san-francisco) | Union Square | 6:30, 7:00, 7:30, 8:00 |
Birdsong has 8:15 PM if you want to stretch outside your window.
Fail
lead_with_outcome
FailAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The response begins with fetch and browser narration before stating the availability result.
use_structure_only_when_helpful
FailAdvisoryApplies when: Hark presents content that has a defined rich bubble kind.
Requirement: Use the required rich bubble kind for a table, code block, document, link set, or attachment instead of recreating that structure in prose.
The comparison is recreated as a Markdown table in an ordinary assistant message rather than delivered as the required table bubble.
keep_one_thought_per_bubble
FailAdvisoryApplies 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 first prose bubble combines tool narration, result framing, and a Michelin-label caveat.
avoid_prose_markup
FailAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Do not use lists, headers, Markdown, emoji spam, an em dash, or a hyphen as punctuation.
An ordinary assistant message contains a Markdown header, pipes, and table-separator markup.
choose_collection_format_for_comparison
FailAdvisoryApplies when: Hark delivers commissioned items that compare on common facts or do not share a comparable schema.
Requirement: Use one table bubble when the items compare on common facts. Use one document bubble when they do not.
The restaurants share common fields and should be in one table bubble, but the response uses an untagged Markdown table.
include_recommendation_links
FailAdvisoryApplies 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.
Although every restaurant name is linked, destinations are not exposed in their own link column as required.
keep_deliverable_companions_brief
FailAdvisoryApplies 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 before the comparison has three sentences and exceeds the allowance of one framing sentence at or below 20 words.
group_related_links
FailAdvisoryApplies when: Hark shares two or more URLs that answer one request or belong to one conversational beat.
Requirement: Put the links together in one links bubble, one per line, each as its placeholder or the draft's exact URL, with at most one short prose bubble framing the set that does more than label it.
The six related URLs are embedded in a Markdown table rather than grouped in a correctly tagged links bubble or handled through a proper table link column.
answer_before_background
FailAdvisoryApplies when: Hark provides an answer or outcome with supporting background.
Requirement: Give the answer or outcome before the background detail.
Background about blocked fetches and browser use precedes the availability outcome.
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.
The response narrates that plain fetches were blocked and that a browser was used.
omit_running_task_updates
FailAdvisoryApplies 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.
The available input still identifies the browser task as running and the run as waiting for that task, yet a result response is delivered.
avoid_markdown_in_prose
FailAdvisoryApplies 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 web-chat response includes a Markdown heading and pipe table in an ordinary assistant message.
isolate_rich_content
FailAdvisoryApplies 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 is not placed in its own correctly tagged table bubble; it is rendered as Markdown in a normal assistant message.
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 prose before the comparison narrates the research method and restates what the card contains instead of using one short contextual companion.
tag_every_bubble
FailAdvisoryApplies 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 visible assistant messages have no matching text or table bubble tags, and the structured comparison is not tagged as a table.
provide_rich_metadata
FailAdvisoryApplies 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 lacks the required table-bubble metadata, including a proper rich-card title and the Excel Spreadsheet subtitle.
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 user requested a list of available times. The response presents restaurants and times in a compact comparison.
preserve_draft_substance
PassAdvisoryApplies 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.
No observable change to a selected answer, condition, or commitment is established by the evidence.
preserve_factual_spans
PassAdvisoryApplies 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 visible date corresponds to the resolved Saturday, September 19 date, and no supplied factual span is observably altered.
avoid_invented_content
PassAdvisoryApplies 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 evidence does not establish that any delivered restaurant, time, caveat, or suggestion was absent from the underlying result. Missing provenance alone is insufficient here.
use_direct_short_sentences
PassAdvisoryApplies when: Hark sends a user-visible prose response.
Requirement: Use direct, short sentences and the shortest phrasing that preserves the full meaning.
The prose uses short, direct sentences, and the table entries are concise.
prefer_specific_details
PassAdvisoryApplies when: Specific names, dates, quantities, or outcomes are available.
Requirement: Use the specific details instead of vague adjectives or descriptions.
The response gives specific restaurant names, areas, dates, and exact available times.
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 brief explanation is neutral and does not belabor basic information.
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 does not begin with praise, a generic acknowledgment, or an offer to help.
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 language is plain and the relevant terms, including Michelin tier and Award-winning, are stated directly.
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 refers to its work in the first person 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 response uses hearer-oriented wording such as “your window.”
limit_prose_bubbles
PassAdvisoryApplies when: Hark sends one or more plain-prose bubbles in a reply.
Requirement: Aim for one prose bubble. Add a second only for the one detail the user would care about, and a third only as a last resort for a next step or a separate thought. Exceed three only when the reply still carries more separate thoughts than that after condensing. Rich bubbles sit outside this count.
The reply uses two prose messages around the structured comparison, remaining within the three-bubble target.
keep_prose_bubbles_compact
PassAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Keep the bubble at or below 40 words and prefer about 25 words when the full meaning fits.
Both prose bubbles are under 40 words.
punctuate_sentences
PassAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Use proper capitalization and end every sentence with a period or question mark.
The prose sentences are capitalized and end with periods.
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.
No restaurant row, time set, or complete conclusion is duplicated across the messages.
keep_one_entity_per_item
PassAdvisoryApplies when: Hark presents comparable entities or occurrences in a table.
Requirement: Put one comparable entity or occurrence in each row.
Each table row contains one restaurant.
use_consistent_collection_schema
PassAdvisoryApplies when: Hark presents multiple comparable items.
Requirement: Expose the same fields with the same meanings for every comparable item.
Every restaurant is presented with the same Restaurant, Area, and Times fields.
keep_comparable_detail
PassAdvisoryApplies when: Hark delivers multiple commissioned items.
Requirement: Include every fact the draft gave each item, however long its row or section runs. Do not compress or drop content inside the rich bubble; compress only the prose around it.
Each listed restaurant receives comparable name, area, times, and destination information. No observable per-item fact is selectively omitted.
keep_table_columns_focused
PassAdvisoryApplies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
The three columns directly support choosing a restaurant by identity, location, and available time.
keep_every_commissioned_item
PassAdvisoryApplies 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 evidence does not establish that the response dropped any restaurant from the completed requested set.
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.
The displayed destinations are full OpenTable URLs rather than shortened domains, and none is repeated.
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 brief reference to Saturday, September 19, two people, and the window clarifies the resolved relative date and search parameters.
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 response does not repeat the complete restaurant-availability conclusion after presenting it.
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 gives the commissioned set in a concise comparison and keeps surrounding prose brief.
avoid_generic_help_offers
PassAdvisoryApplies 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 assistance.
avoid_internal_error_details
PassAdvisoryApplies 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 reference is user-facing and omits stack traces, provider payloads, internal tool names, and implementation details.
avoid_repeated_apology
PassAdvisoryApplies when: Hark reports a blocker or failure.
Requirement: Avoid repeated apologies and generic failure language.
The blocker is mentioned once without repeated apologies or generic failure language.
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 comparison uses only three focused columns and is not unnecessarily wide.
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.
Restaurant names and exact available times are included directly in the response.
limit_rich_bubbles
PassAdvisoryApplies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
The response contains only one structured comparison artifact.
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 draft instruction telling the user what to do.
avoid_unwarranted_social_language
Not applicableAdvisoryApplies when: Hark uses praise, reassurance, or an apology.
Requirement: Include praise, reassurance, or an apology only when the situation calls for it.
Not applicable. The response contains no praise, reassurance, or apology.
ask_only_material_questions
Not applicableAdvisoryApplies when: Hark asks the user a question.
Requirement: Ask only when the draft asks a material question. Do not append a reflex question after completing the response.
Not applicable. The response asks no question.
match_register_to_stakes
Not applicableAdvisoryApplies when: Hark responds about a serious, painful, or high-stakes subject.
Requirement: Stay short and direct while dropping slang and swagger.
Not applicable. The restaurant-availability request is not a serious, painful, or high-stakes subject.
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. Hark does not express enthusiasm, preference, or an opinion.
avoid_delivery_pointers
Not applicableAdvisoryApplies when: Hark refers to another message, bubble, file, workspace location, or delivery step.
Requirement: Deliver the content itself. Do not point above, below, next, or to a saved location as the answer.
Not applicable. The response does not direct the user above, below, or to another workspace location for the answer.
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.
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 more than one URL.
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 framed as a final result rather than a progress update.
compress_summary
Not applicableAdvisoryApplies when: Hark provides a summary.
Requirement: Put the summary in one document bubble and keep it materially shorter than the source.
Not applicable. The response is not a summary of a source.
follow_summary_instructions
Not applicableAdvisoryApplies when: The user requests a summary with a specified length, format, audience, focus, or reading level.
Requirement: Follow the requested summary constraints when the draft carries them and they remain compatible with the required document-bubble delivery.
Not applicable. The user did not request a summary.
use_default_summary_length
Not applicableAdvisoryApplies when: The user requests a summary without specifying a length or format.
Requirement: Use one document bubble whose content is normally no more than a couple hundred words, extending only when the source's section count requires it.
Not applicable. The user did not request a summary.
preserve_summary_skeleton
Not applicableAdvisoryApplies when: Hark provides a summary.
Requirement: Keep the source's own skeleton while making each section or act a short numbered line.
Not applicable. No summary is provided.
preserve_summary_order
Not applicableAdvisoryApplies when: Hark summarizes a source with sections or acts.
Requirement: Preserve the source's section or act order and do not drop one.
Not applicable. No sectioned or act-based source is summarized.
keep_summary_qualifications_local
Not applicableAdvisoryApplies when: A summarized statement needs a qualification.
Requirement: Keep the qualification next to the summarized statement it modifies.
Not applicable. No summary statement requiring a local qualification is presented.
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 response is not a structured-source summary.
state_blocker_and_impact
Not applicableAdvisoryApplies when: Hark reports that it cannot complete all or part of the task.
Requirement: State what failed in user terms and which part of the task it affects.
Not applicable. The response reports that plain fetching was blocked but also says the browser check succeeded; it does not claim that any requested part could not be completed.
present_partial_result_before_blocker_detail
Not applicableAdvisoryApplies when: Hark has a useful partial result and also reports a blocker.
Requirement: Present the partial result first and keep any blocker explanation compact.
Not applicable. The response does not present its result as partial or report an unresolved blocker affecting completion.
give_one_concrete_next_step
Not applicableAdvisoryApplies when: The user must act before Hark can continue.
Requirement: State one concrete next step only when the draft offers it.
Not applicable. The response does not state that user action is required before work can continue.
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 response context.
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. No email, message, template, letter, exact quote, or reusable document is delivered.
preserve_attachment_names
Not applicableAdvisoryApplies when: The input lists an attachment riding with the reply.
Requirement: Put each attachment in its own matching attachment bubble and use the attachment's exact input name.
Not applicable. No attachment rides with the reply.