← Back to scenario detail

Response style analysis

Applied 46 · Passed 27 · Failed 19 · Not applicable 22

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

Prompt

Use the web_fetch tool to answer the prompt. What executive orders, presidential memoranda, or major fact sheets has https://www.whitehouse.gov/briefing-room/ published in the past 14 days? Summarize the practical effect of each.

Hark's responses

Four executive orders and seven fact sheets from the briefing room in the past two weeks.
### Executive Orders and Fact Sheets, Aug 28—Sep 11 · Briefing Room Summary | Item | Practical Effect | Link | |---|---|---| | EO 14426: Accelerating Access to Veterans' Benefits (Sep 8) | Within 30 days, DoD must share all separating service members' records with VA. Within 120-180 days, build permanent IT links and AI benefit tools; TAP connects each member to a job or training before separation. | https://www.whitehouse.gov/presidential-actions/2026/09/accelerating-access-to-veterans-benefits-and-employment-opportunities/ | | EO 14427: DPA Delegations (Sep 8) | Interior and Energy each gain independent DPA energy authority; disputes escalate to the National Energy Dominance Council. | https://www.whitehouse.gov/presidential-actions/2026/09/adjusting-certain-delegations-under-the-defense-production-act-e2de/ | | EO 14425: Supporting America's Ranchers (Sep 4) | Interior decides on gray and Mexican wolf delisting within 90 days; USDA reviews country-of-origin labeling rules. Cross-agency rancher regulation report due in 90 days. | https://www.whitehouse.gov/presidential-actions/2026/09/supporting-americas-ranchers/ | | EO 14424: Fair Competition in Livestock Markets (Sep 4) | Expand Packers and Stockyards investigations, push state meat inspection across state lines, strip some FSIS reporting, and create a guaranteed loan program for small beef processors. | https://www.whitehouse.gov/presidential-actions/2026/09/promoting-fair-competition-in-livestock-markets-and-expanding-market-access-for-american-meat-producers/ | | Working Families Obamacare Refunds (Sep 10) | \$500 per person to nearly 1 million in 30 federal-exchange states with no premium assistance. Checks mail October 2026. | https://www.whitehouse.gov/fact-sheets/2026/09/fact-sheet-president-donald-j-trump-announces-the-working-families-obamacare-refunds/ | | Responding to Canada's Retaliation (Sep 8) | Import bans on Canadian alcohol and dairy (Sep 29), ATVs and more dairy added (Sep 15). Tariffs apply on top of Section 232 and USMCA. Canadian goods pulled from over \$50 billion in GSA procurements. | https://www.whitehouse.gov/fact-sheets/2026/09/fact-sheet-president-donald-j-trump-responds-to-canadas-retaliation/ | | Venezuela Oil Agreement (Aug 31) | North American Blue Energy gets 100-year concessions on 17 fields. DoD's Office of Strategic Capital takes 35% equity; State retains right of first refusal on 80% of oil off-take. | https://www.whitehouse.gov/fact-sheets/2026/08/fact-sheet-president-donald-j-trump-announces-historic-oil-agreement-to-secure-american-energy-dominance-and-drive-venezuelas-economic-recovery/ | | Nine Pharma MFN Deals (Aug 31) | Alcon, Astellas, BeOne, BridgeBio, CSL, Kyowa Kirin, Sun, Teva, UCB—26 manufacturers now cover 89% of branded pharma. All state Medicaid gets MFN pricing. Nine committed \$19.6 billion to US manufacturing. | https://www.whitehouse.gov/fact-sheets/2026/08/fact-sheet-president-donald-j-trump-announces-deal-with-nine-additional-pharmaceutical-manufacturers-to-lower-drug-prices-for-americans/ | | US Space Academy Commission (Aug 28) | NASA Administrator chairs a commission to design a NASA-led academy: governance, curricula, service terms, and site selection. | https://www.whitehouse.gov/fact-sheets/2026/08/fact-sheet-president-donald-j-trump-establishes-a-commission-to-design-the-united-states-space-academy/ | | Ranchers and Livestock Competition Fact Sheets (Sep 4) | Companion documents to the two livestock and ranching executive orders. | https://www.whitehouse.gov/fact-sheets/2026/09/fact-sheet-president-donald-j-trump-supports-americas-ranchers/, https://www.whitehouse.gov/fact-sheets/2026/09/fact-sheet-president-donald-j-trump-promotes-fair-competition-in-livestock-markets-and-expands-market-access-for-american-meat-producers/ |
The livestock orders are the broadest: one tackles market consolidation and processor economics, the other tackles predator delisting and labeling rules.

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.
Compression changed or dropped material qualifications. The rancher row says Interior decides on delisting, omitting that delisting begins only if recovery criteria are met. The Venezuela row also drops the State Department's right to buy 20% at production cost.

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.
Several factual spans changed scope or referent. The response substitutes DoD for the source's Department of War and says tariffs apply on top of USMCA, although the source says they apply regardless of USMCA origin.

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 closing judgment that the livestock orders are the broadest is an added opinion not present in the draft or cited source material.

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 is rendered as Markdown text rather than an observably tagged table bubble.

keep_one_entity_per_item

FailAdvisory
Applies when: Hark presents comparable entities or occurrences in a table.
Requirement: Put one comparable entity or occurrence in each row.
The final table row combines two separate fact sheets into one item.

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 table omits many facts supplied by the draft, including deadlines, conditions, quantities, and implementation details. The final two fact sheets receive only a generic companion label.

include_recommendation_links

FailAdvisory
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.
Most items have an individual link cell, but the last row places two destinations together in one cell instead of giving each item its own link entry.

compress_summary

FailAdvisory
Applies when: Hark provides a summary.
Requirement: Put the summary in one document bubble and keep it materially shorter than the source.
The response is explicitly presented as a summary but is not delivered in a document bubble.

follow_summary_instructions

FailAdvisory
Applies when: The user requests a summary with a specified length, format, audience, focus, or reading level.
Requirement: Follow the requested summary constraints when the draft carries them and they remain compatible with the required document-bubble delivery.
The requested practical-effect focus is followed, but the summary is not delivered in the required document-bubble format.

use_default_summary_length

FailAdvisory
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.
The user did not specify a length, but the summary is presented as a Markdown table rather than one document bubble.

preserve_summary_skeleton

FailAdvisory
Applies when: Hark provides a summary.
Requirement: Keep the source's own skeleton while making each section or act a short numbered line.
The response reorganizes the source material into an unnumbered table instead of preserving the source skeleton as short numbered lines.

keep_summary_qualifications_local

FailAdvisory
Applies when: A summarized statement needs a qualification.
Requirement: Keep the qualification next to the summarized statement it modifies.
The rancher summary omits the local condition that wolf delisting should begin only if Interior determines the recovery criteria have been met.

use_summary_numbered_lines

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

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 structured comparison is visibly rendered with a Markdown header and pipe-table syntax in an assistant message rather than a correctly tagged rich bubble.

keep_narrow_screens_readable

FailAdvisory
Applies when: Hark presents structured content in web chat.
Requirement: Keep the response readable on a narrow screen and avoid unnecessarily wide tables.
The three-column table contains very long practical-effect text and full URLs, making it unnecessarily wide for narrow screens.

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-like content is not observably placed in a correctly tagged table bubble, and a Markdown header is mixed into the same message.

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 closing companion summarizes and ranks the card's livestock entries rather than supplying a caveat, context, or draft-provided next step.

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 and no matching text or table bubble tags.

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 pipe rows and a visible heading but lacks the required Excel Spreadsheet subtitle and is not observably supplied as table metadata.

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 uses a concise comparison and focuses each entry on practical effect, as requested.

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 the result count.

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 companions are short and direct, and the table descriptions are concise.

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 uses dates, order numbers, deadlines, dollar amounts, percentages, and named organizations.

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 explanations are factual and do not belabor basic points or talk down to the user.

avoid_throat_clearing

PassAdvisory
Applies when: Hark sends a user-visible response.
Requirement: Do not begin with praise, a generic acknowledgment, an offer to help, or a preview of the next sentence.
The response begins with the result rather than praise, acknowledgment, or an offer.

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.
Technical terms such as DPA, MFN pricing, Section 232, and USMCA are used in compact, generally understandable descriptions.

match_register_to_stakes

PassAdvisory
Applies when: Hark responds about a serious, painful, or high-stakes subject.
Requirement: Stay short and direct while dropping slang and swagger.
The response maintains a professional register without slang or swagger while discussing government policy.

avoid_forbidden_social_phrases

PassAdvisory
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.
Although the closing bubble offers an opinion, it uses no bro-speak and does not say Hark loves or feels anything.

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 two compact prose companions around the structured comparison.

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 first prose bubble gives the count, and the second gives one comparative takeaway.

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.
Both prose bubbles are well below 40 words.

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.
Both prose bubbles are capitalized and end with periods.

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 two plain-prose companion bubbles contain no lists, headers, Markdown, emoji, or prohibited punctuation.

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 substantive content block is repeated verbatim across the three delivered bubbles.

choose_collection_format_for_comparison

PassAdvisory
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 comparable publications are presented together in one table with consistent decision-oriented fields.

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 table row uses the same Item, Practical Effect, and Link 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 focus on identifying each publication, its practical effect, and its source link.

keep_every_commissioned_item

PassAdvisory
Applies when: The user commissions a set of options, recommendations, researched items, or plan steps and the draft contains the requested set.
Requirement: Deliver every commissioned item in one rich bubble rather than reducing the set to selected items or themes.
All four executive orders and all seven fact sheets are represented in the single comparison, although two fact sheets share one row.

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 framing and takeaway companions are each one sentence and under 20 words.

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 White House destination URLs are shown in their exact full forms rather than shortened to domains.

answer_before_background

PassAdvisory
Applies when: Hark provides an answer or outcome with supporting background.
Requirement: Give the answer or outcome before the background detail.
Each row leads with what the publication does and gives supporting context afterward.

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 response does not state the same conclusion in multiple places.

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.
Because the user commissioned a complete set, the response retains all identified publications while keeping each summary concise.

avoid_generic_help_offers

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

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 result itself is included in the delivered messages rather than merely described as saved elsewhere.

limit_rich_bubbles

PassAdvisory
Applies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
Only one structured table-like artifact is delivered.

Not applicable

preserve_instruction_direction

Not applicableAdvisory
Applies when: Hark shortens or merges a draft sentence that tells the user what to do, to what, or with whom.
Requirement: Keep the sentence's verb, object, and addressee. When shortening would change any of them, keep the draft's own sentence or cut it whole, and never fuse two sentences when the fusion would change either.
Not applicable. The delivered response does not tell the user to perform an action.

avoid_unwarranted_social_language

Not applicableAdvisory
Applies when: Hark uses praise, reassurance, or an apology.
Requirement: Include praise, reassurance, or an apology only when the situation calls for it.
Not applicable. The response contains no praise, reassurance, or apology.

ask_only_material_questions

Not applicableAdvisory
Applies when: Hark asks the user a question.
Requirement: Ask only when the draft asks a material question. Do not append a reflex question after completing the response.
Not applicable. The response asks no questions.

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.

use_hearer_oriented_grammar

Not applicableAdvisory
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.
Not applicable. No relevant possessive, imperative, or wellbeing construction occurs.

avoid_delivery_pointers

Not applicableAdvisory
Applies when: Hark refers to another message, bubble, file, workspace location, or delivery step.
Requirement: Deliver the content itself. Do not point above, below, next, or to a saved location as the answer.
Not applicable. The response does not direct the user to another message, file, or workspace location.

include_ranking_column

Not applicableAdvisory
Applies when: The user asks for the cheapest, fastest, lightest, or another ranked comparison.
Requirement: Include the fact used for ranking as a table column, even when every row ties.
Not applicable. The user did not ask for a ranked comparison.

isolate_single_links

Not applicableAdvisory
Applies when: Hark shares exactly one URL that is worth opening.
Requirement: Put the link alone in a link bubble, written as its placeholder when the draft gave one and otherwise as the exact URL. Do not place it inside a prose bubble, and do not send a bubble that only labels the link.
Not applicable. The response shares multiple item-specific links, not exactly one URL.

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 URLs function as row-level source destinations within a comparison rather than as a standalone conversational link set.

avoid_request_restatement

Not applicableAdvisory
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.
Not applicable. The response does not restate the user's request.

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 delivered response contains no narration of fetching, research, verification, or other tool use.

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 assistant messages contain no progress update.

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. There is no single source with sections or acts whose internal order governs this commissioned research collection.

state_blocker_and_impact

Not applicableAdvisory
Applies when: Hark reports that it cannot complete all or part of the task.
Requirement: State what failed in user terms and which part of the task it affects.
Not applicable. The response reports no blocker or 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 is 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. The user does not need to act before Hark can continue.

avoid_internal_error_details

Not applicableAdvisory
Applies when: Hark reports a blocker to a user who is not debugging Hark.
Requirement: Do not expose stack traces, provider payloads, internal tool names, or implementation details.
Not applicable. No blocker or internal error is reported.

avoid_repeated_apology

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

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 delivered response follows completed tool results rather than an input saying the task is still running.

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. No needed code block appears in the draft or response.

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, template, exact quote, or other reusable document requiring byte-exact delivery.

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 attachments ride with the reply.