← Back to scenario detail

Response style analysis

Applied 53 · Passed 43 · Failed 10 · Not applicable 15

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

Prompt

Use the web_fetch tool to answer the prompt. What major criminal or civil enforcement actions did https://www.justice.gov/news announce in the past seven days? Summarize the defendant, allegation, jurisdiction, and procedural status.

Hark's responses

The DOJ news feed from Sept 11, 2026 shows ten enforcement actions. Note: the archive only holds the most recent batch, not a full seven days.
### DOJ enforcement actions, Sept 11, 2026 · News announcements | Defendant | Allegation | Jurisdiction | Status | |---|---|---|---| | Zakia Khan, 55, Brooklyn | Led $64M Medicaid fraud and kickback scheme via two social adult daycare centers and a home health fiscal intermediary; $56M paid out on false claims | EDNY / National Fraud Enforcement Division | Sentenced to 76 months, $56M restitution, $5M forfeiture; pleaded guilty Aug 2025 | | Luann Middleton, ex-USPS employee | Wire fraud: false total-disability workers' comp claims, ~$40K/yr for nearly 25 years (~$1M) | EDNY, Central Islip, Judge Gary R. Brown | Convicted by jury after 4-day trial; faces up to 20 years | | St. Michael's Eye & Laser Institute and Dr. John Michaelos | False Claims Act: caused submission of false Medicare claims | D. Mass. (Boston) | Civil settlement, $350,000, allegations only | | Unnamed Chicago trader | Unauthorized trading causing $30M in losses | N.D. Ill. | Sentenced to over 16 years | | James David Johnson, 58, Santee, CA | Distributing child sexual abuse material on the dark web | Prosecuted by DOJ Criminal Division | Sentenced to 151 months plus 10 years supervised release | | Glendale, CA man | Conspiracy to steal ~30 USPS carrier vehicles and mail of 200+ victims, including 100 cards | C.D. Cal. | Pleaded guilty | | Compton, CA man | Assaulting and injuring a federal officer by throwing rocks at government vehicles during a Paramount riot | C.D. Cal. | Sentenced to 36 months | | Two Dallas-area women | Aggravated identity theft scheme targeting JCPenney stores nationwide | S.D. Tex. | Sentenced to federal prison | | Adrian Alcantar-Sanchez, 46 | 878.7g of pure fentanyl plus unlawful reentry | E.D. Okla. | 78 months concurrent; pleaded guilty Nov 2025 | | Ohio dairy manager, 54 | Dumping pollutants into a waterway, causing a fish kill | N.D. Ohio | Sentenced after admitting responsibility |
https://www.justice.gov/opa/pr/brooklyn-adult-daycare-owner-sentenced-prison-leadership-role-64m-medicaid-fraud-scheme https://www.justice.gov/usao-edny/pr/former-postal-worker-convicted-stealing-nearly-1-million-tax-free-federal-disability https://www.justice.gov/usao-ma/pr/eye-practice-and-physician-owner-agree-pay-350000-resolve-allegations-false-claims https://www.justice.gov/usao-ndil/pr/chicago-trader-sentenced-more-16-years-federal-prison-engaging-unauthorized-trading https://www.justice.gov/opa/pr/california-man-sentenced-over-12-years-prison-distributing-sadistic-child-sexual-abuse https://www.justice.gov/usao-cdca/pr/glendale-man-pleads-guilty-conspiring-steal-us-postal-service-vehicles-and-mail https://www.justice.gov/usao-cdca/pr/compton-man-sentenced-3-years-federal-prison-injuring-federal-officer-during-anti https://www.justice.gov/usao-sdtx/pr/two-dallas-area-women-sentenced-nationwide-identity-theft-fraud-scheme https://www.justice.gov/usao-edok/pr/illegal-alien-sentenced-possession-intent-distribute-fentanyl-and-unlawful-reentry https://www.justice.gov/usao-ndoh/pr/dairy-manager-sentenced-role-polluting-waterway-waste-caused-fish-kill
Two bulk immigration announcements also landed: Arizona charged 306 people Sept 5–11, and the Western District of Texas filed 500 immigration cases Aug 28 to Sept 10. Want the Sept 5–10 releases too?

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 limitation changes the draft's claim about the machine-readable feed into a claim about the archive, altering the stated blocker.

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 archive only holds the most recent batch” changes the referent from the DOJ news feed to the archive. The response also says there are ten actions while separately presenting two additional enforcement announcements.

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 archive limitation is not the draft's claim. The draft said the machine-readable feed held only the latest batch.

keep_every_commissioned_item

FailAdvisory
Applies when: The user commissions a set of options, recommendations, researched items, or plan steps and the draft contains the requested set.
Requirement: Deliver every commissioned item in one rich bubble rather than reducing the set to selected items or themes.
The two bulk immigration announcements are delivered outside the rich collection rather than with the other commissioned enforcement items in one rich bubble.

keep_deliverable_companions_brief

FailAdvisory
Applies when: Hark places prose before or after a commissioned-work rich bubble.
Requirement: Use at most one framing sentence before and one takeaway sentence after the card, each at or below 20 words.
The framing message before the table exceeds 20 words and uses two sentences. The closing companion also exceeds 20 words.

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 a requested summary but is delivered as a table rather than one 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 focus fields are followed, but the summary is not delivered in the rule's required document-bubble form.

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-source summary uses table rows instead of short numbered lines inside a document bubble.

keep_card_companions_contextual

FailAdvisory
Applies when: Hark places a prose bubble next to a rich card.
Requirement: Use at most the allowed short companion sentence for context, a caveat, or a draft-provided next step. Do not restate, summarize, caption, or narrate the card.
The companions are contextual, but they exceed the allowed short-sentence limit; the closing message also adds separate commissioned items beside the rich content.

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 title, but its subtitle is “News announcements” rather than the required “Excel Spreadsheet.”

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 the requested defendant, allegation, jurisdiction, and procedural-status fields in a comparison table.

lead_with_outcome

PassAdvisory
Applies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The first message immediately states the available result and its date limitation.

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 messages use short, direct sentences.

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 table uses available names, dates, quantities, districts, monetary amounts, and procedural outcomes.

avoid_condescending_explanations

PassAdvisory
Applies when: Hark explains information to the user.
Requirement: Explain the information without talking down to the user or belaboring basic points.
The response states the findings and limitation without belaboring basic concepts or talking 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 a preview.

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.
Comparable enforcement actions are presented as a table, and the source URLs are isolated as a link set.

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 response uses concise legal and procedural terms such as False Claims Act, convicted, pleaded guilty, and sentenced.

ask_only_material_questions

PassAdvisory
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.
The only question is a specific next step tied to the acknowledged date-coverage limitation, and the draft included it.

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 uses a neutral, professional register appropriate for criminal and civil enforcement matters.

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 closing question is directly oriented to the user and contains no problematic self-description.

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.
The response uses two prose messages around the rich content, staying within the normal limit.

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 opening prose message gives the result and its scope limitation; the closing message gives additional bulk-action context and the related next step.

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 messages are under 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.
The prose sentences are capitalized and end with periods or a question mark.

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 plain-prose messages contain no headers, lists, Markdown, em dashes, or decorative markup.

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.
The table contains the action details, while the separate link set contains only destinations. No substantive row is repeated.

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 ten actions sharing common fields are presented in one table.

keep_one_entity_per_item

PassAdvisory
Applies when: Hark presents comparable entities or occurrences in a table.
Requirement: Put one comparable entity or occurrence in each row.
Each row represents one enforcement action or jointly resolved occurrence. The eye practice and its physician owner belong to one settlement.

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 four fields: defendant, allegation, jurisdiction, and status.

keep_comparable_detail

PassAdvisory
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 retains the draft's supplied details for each of its ten rows, with source destinations preserved separately.

keep_table_columns_focused

PassAdvisory
Applies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
All four columns directly match the user's requested decision fields.

group_related_links

PassAdvisory
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.
The ten related DOJ release URLs are grouped together, one per line, in a single message.

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 release URLs are presented in their exact full forms and are not shortened.

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 opening gives the available result before explaining the date-coverage limitation.

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; the table title only identifies the result.

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 fetches, searches, verification steps, or tool use. It only states a user-relevant coverage limitation.

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 states the scope conclusion once and does not repeat a final takeaway.

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 set of enforcement actions, the response appropriately retains multiple items and the requested fields.

avoid_generic_help_offers

PassAdvisory
Applies when: Hark has completed the requested response.
Requirement: Do not append a generic offer of further help.
The closing question proposes a specific date-range follow-up rather than a generic offer of help.

preserve_summary_skeleton

PassAdvisory
Applies when: Hark provides a summary.
Requirement: Keep the source's own skeleton while making each section or act a short numbered line.
The source is a feed of independent announcements rather than a source organized into sections or acts, so there is no section skeleton to lose.

keep_summary_qualifications_local

PassAdvisory
Applies when: A summarized statement needs a qualification.
Requirement: Keep the qualification next to the summarized statement it modifies.
Qualifications remain next to the relevant claims, including “allegations only” in the civil-settlement status.

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 opening states the source-coverage limitation and clearly says it prevents full seven-day coverage.

present_partial_result_before_blocker_detail

PassAdvisory
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.
The response states that ten actions were found before giving the coverage limitation.

give_one_concrete_next_step

PassAdvisory
Applies when: The user must act before Hark can continue.
Requirement: State one concrete next step only when the draft offers it.
The response offers one concrete next step: obtaining the Sept. 5–10 releases. The draft offered the same step.

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 response does not expose HTTP errors, tool names, stack traces, provider payloads, or implementation details.

avoid_repeated_apology

PassAdvisory
Applies when: Hark reports a blocker or failure.
Requirement: Avoid repeated apologies and generic failure language.
The blocker is reported without any apology or generic failure language.

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 two plain-prose messages contain no Markdown. Structured Markdown-like syntax appears only in the table message.

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 table is limited to the four fields the user requested and avoids unnecessary columns.

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 enforcement-action result is included directly in the response rather than merely described as stored elsewhere.

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 table and link set are each isolated in their own messages without prose mixed into them.

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 delivered messages are observably separated by content kind: prose, table, links, and prose.

limit_rich_bubbles

PassAdvisory
Applies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
The two rich messages carry distinct artifacts: the comparison table and its grouped source links.

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 response does not shorten or merge an instruction telling the user what to do.

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.

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.

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 point the user above, below, or to a saved location instead of delivering the content.

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.

include_recommendation_links

Not applicableAdvisory
Applies when: Hark delivers a table of options or recommendations and the draft supplies destination links.
Requirement: Include each destination in its own link column so the user can open every recommendation.
Not applicable. The table reports enforcement actions rather than options or recommendations.

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 more than one URL.

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 response is a completed result, not a progress update.

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 specified the summary's focus and fields, so the default-summary condition does not apply.

preserve_summary_order

Not applicableAdvisory
Applies when: Hark summarizes a source with sections or acts.
Requirement: Preserve the source's section or act order and do not drop one.
Not applicable. The source is not organized into sections or acts requiring preserved narrative order.

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. No task was still running when the response was delivered.

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, letter, exact quote, or 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.