← Back to scenario detail
Response style analysis
Applied 41 · Passed 25 · Failed 16 · Not applicable 27
Rubric: services/agent/prompts/editor/v1.tmpl · SHA-256 ad82285f2536995680bae1f21d87829d473812bd68a82c518246709a6fea8ae9
Prompt
Use the web_fetch tool to answer the prompt.
On https://clinicaltrials.gov/, which phase 3 interventional studies began recruiting in the past 14 days? List condition, intervention, sponsor, enrollment target, and locations.
Hark's responses
I found 44 phase 3 interventional studies recruiting between Aug 28 and Sep 11, 2026. A few list only September 2026 as the start month.
### Phase 3 recruiting studies · Markdown table
| Start | Condition | Intervention | Sponsor | Enroll. | Locations | ID |
|---|---|---|---|---|---|---|
| 2026-09-11 | Secondary immune deficiency | IgPro20 | CSL Behring | 63 | 60 sites: US, Italy, Spain, France | [NCT07648264](https://clinicaltrials.gov/study/NCT07648264) |
| 2026-09-10 | Metastatic urothelial carcinoma | Ivonescimab + enfortumab vedotin vs pembrolizumab + EV | Summit Therapeutics | 800 | 7 US sites | [NCT07815665](https://clinicaltrials.gov/study/NCT07815665) |
| 2026-09-08 | EGFR-mutant oligometastatic NSCLC | Osimertinib ± primary tumor resection | National Taiwan University Hospital | 154 | Taipei, Taiwan | [NCT07738172](https://clinicaltrials.gov/study/NCT07738172) |
| 2026-09-08 | Essential thrombocythemia | INCA033989 vs best available therapy | Incyte | 426 | 177 sites: US, Italy, Japan, Spain | [NCT07623200](https://clinicaltrials.gov/study/NCT07623200) |
| 2026-09-04 | Spinal muscular atrophy | Salanersen vs sham | Biogen | 42 | Flower Mound, US | [NCT07444450](https://clinicaltrials.gov/study/NCT07444450) |
| 2026-09-03 | Generalized anxiety disorder | ITI-1284 | Intra-Cellular Therapies | 900 | Los Angeles, US | [NCT07807865](https://clinicaltrials.gov/study/NCT07807865) |
| 2026-09-03 | Sexual/reproductive health, disability | Disability-focused SRH curriculum | University of Minnesota | 412 | Dar es Salaam, Tanzania | [NCT07772778](https://clinicaltrials.gov/study/NCT07772778) |
| 2026-09-02 | Triple negative breast cancer | Trastuzumab rezetecan + adebrelimab | Suzhou Suncadia | 1000 | Beijing, China | [NCT07679360](https://clinicaltrials.gov/study/NCT07679360) |
| 2026-09-02 | Plaque psoriasis | TQH3906 vs deucravacitinib | Chia Tai Tianqing | 400 | 45 China sites | [NCT07724366](https://clinicaltrials.gov/study/NCT07724366) |
| 2026-09-02 | Myelofibrosis with anemia | Elritercept vs placebo | Takeda | 324 | 195 sites: US, Italy, India, France | [NCT07623161](https://clinicaltrials.gov/study/NCT07623161) |
| 2026-09-01 | Late-life/treatment-resistant depression | Lumateperone vs placebo | Washington Univ (Eric Lenze) | 100 | Tucson, St Louis, US | [NCT07623135](https://clinicaltrials.gov/study/NCT07623135) |
| 2026-09-01 | Pediatric obesity post sleeve gastrectomy | Semaglutide 2.4 mg | Children's Hospital Los Angeles | 150 | Los Angeles, US | [NCT06934655](https://clinicaltrials.gov/study/NCT06934655) |
| 2026-09-01 | Duchenne MD (exon 44) | AOC 1044 vs placebo | Avidity Biosciences | 70 | 13 sites: Germany, Spain, Belgium, Italy, France, UK | [NCT07587242](https://clinicaltrials.gov/study/NCT07587242) |
| 2026-09-01 | Knee osteoarthritis surgery | Periarticular injection ± steroid/Zilretta | Walter Reed NMMC | 240 | Bethesda, US | [NCT07151417](https://clinicaltrials.gov/study/NCT07151417) |
| 2026-09-01 | Gingival recession | Coronally advanced flap graft variants | Aziz Aliyev Institute | 75 | Baku, Azerbaijan | [NCT07763808](https://clinicaltrials.gov/study/NCT07763808) |
| 2026-09-01 | Dengue | Emetine hydrochloride vs placebo | Johns Hopkins | 600 | Baltimore US, Bharatpur Nepal | [NCT07016321](https://clinicaltrials.gov/study/NCT07016321) |
| 2026-09-01 | Cancer (exercise support) | Peer matching, exercise professional support | McMaster University | 183 | Hamilton, Canada | [NCT07408128](https://clinicaltrials.gov/study/NCT07408128) |
| 2026-09-01 | Refractory CMV/adenovirus infection | Family-matched viral CTLs + SOC | New York Medical College | 138 | Valhalla, Milwaukee, US | [NCT07225972](https://clinicaltrials.gov/study/NCT07225972) |
| 2026-09 | Ocular GVHD | d-MAPPS ophthalmic solution | Regenerative Ocular Immunobiologics | 30 | 5 US sites | [NCT07776210](https://clinicaltrials.gov/study/NCT07776210) |
| 2026-09 | Uveal melanoma (adjuvant) | Darovasertib + crizotinib | IDEAYA Biosciences | 450 | Toronto, Canada | [NCT07804186](https://clinicaltrials.gov/study/NCT07804186) |
| 2026-09 | Ulcerative colitis | Ponesimod vs placebo | Vanda Pharmaceuticals | 150 | Chula Vista, Nashville, US | [NCT07686081](https://clinicaltrials.gov/study/NCT07686081) |
| 2026-09 | Transfusion-dependent thalassemia (peds) | Mitapivat vs placebo | Agios | 54 | New York, Philadelphia, Dallas | [NCT07506863](https://clinicaltrials.gov/study/NCT07506863) |
| 2026-09 | Non-transfusion-dependent thalassemia (peds) | Mitapivat vs placebo | Agios | 45 | Palo Alto, New York, Philadelphia, Dallas | [NCT07517133](https://clinicaltrials.gov/study/NCT07517133) |
| 2026-09 | Early psychosis | CBD oral solution vs placebo | University of Oxford | 250 | 17 sites: UK, Germany, Israel, Spain | [NCT06778564](https://clinicaltrials.gov/study/NCT06778564) |
| 2026-09 | PTSD | COMP360 psilocybin | COMPASS Pathways | 300 | Orlando, New York | [NCT07570654](https://clinicaltrials.gov/study/NCT07570654) |
| 2026-09 | Narcolepsy | Samelisant vs placebo | Suven Life Sciences | 240 | Columbia, US | [NCT07540364](https://clinicaltrials.gov/study/NCT07540364) |
| 2026-09 | RET-translocated metastatic NSCLC | Lenvatinib + pembrolizumab | EuroCityClinic | 15 | Saint Petersburg, Russia | [NCT07809256](https://clinicaltrials.gov/study/NCT07809256) |
| 2026-09 | Newly diagnosed multiple myeloma | Belantamab mafodotin or daratumumab + VRd | PrECOG | 500 | La Crosse, US | [NCT07285239](https://clinicaltrials.gov/study/NCT07285239) |
| 2026-09 | Hemophilia A | Emicizumab, FEIBA, rFVIIa | Emory University | 5 | Atlanta, US | [NCT04563520](https://clinicaltrials.gov/study/NCT04563520) |
| 2026-09 | Focal epilepsy | RAP-219 vs placebo | Rapport Therapeutics | 312 | 11 US sites | [NCT07594119](https://clinicaltrials.gov/study/NCT07594119) |
| 2026-08-31 | Cancer-associated VTE | REGN7508 vs apixaban | Regeneron | 1600 | 6 sites: US, South Korea | [NCT07493304](https://clinicaltrials.gov/study/NCT07493304) |
| 2026-08-31 | Extensive-stage SCLC | Tarlatamab SC vs IV | Amgen | 400 | Grand Rapids US, Shanghai China | [NCT07778316](https://clinicaltrials.gov/study/NCT07778316) |
| 2026-08-31 | SARS-CoV-2 | Secutrelvir vs placebo | Shionogi | 2000 | 34 sites: Japan, US, Bulgaria | [NCT07743580](https://clinicaltrials.gov/study/NCT07743580) |
| 2026-08-31 | RSV (immunocompromised adults) | RSVpreF revaccination | Pfizer | 440 | 5 US sites | [NCT07768345](https://clinicaltrials.gov/study/NCT07768345) |
| 2026-08-31 | Pulmonary hypertension with ILD | Inhaled mosliciguat vs placebo | Pulmovant | 376 | Kissimmee, Louisville, Bend | [NCT07816185](https://clinicaltrials.gov/study/NCT07816185) |
| 2026-08-31 | Burn injury resuscitation | Plasma vs standard care | Univ of Pittsburgh (Jason Sperry) | 750 | Pittsburgh, US | [NCT07212998](https://clinicaltrials.gov/study/NCT07212998) |
| 2026-08-30 | Type 2 diabetes with obesity | BGM0504 vs semaglutide | BrightGene | 372 | Nanjing, China | [NCT07743983](https://clinicaltrials.gov/study/NCT07743983) |
| 2026-08-30 | Nasopharyngeal carcinoma anorexia | Nanocrystalline megestrol acetate vs placebo | Sun Yat-sen University | 204 | Guangzhou, Changsha, Fuzhou | [NCT07796789](https://clinicaltrials.gov/study/NCT07796789) |
| 2026-08-28 | Metastatic prostate cancer | ARPI dose optimization (abiraterone/apalutamide/enzalutamide/darolutamide) | University College London | 1500 | Manchester, UK | [NCT07751133](https://clinicaltrials.gov/study/NCT07751133) |
| 2026-08-28 | Platinum-sensitive ovarian cancer | Rina-S ± bevacizumab vs platinum chemo | Genmab | 688 | Danbury, Waukesha, US | [NCT07564141](https://clinicaltrials.gov/study/NCT07564141) |
| 2026-08-28 | KRAS G12D metastatic pancreatic cancer | Zoldonrasib + daraxonrasib vs gem/nab-paclitaxel | Revolution Medicines | 400 | Tampa, US | [NCT07805954](https://clinicaltrials.gov/study/NCT07805954) |
| 2026-08-28 | Stage III EGFR-mutated NSCLC | BL-B01D1 + osimertinib vs osimertinib | Sichuan Baili | 418 | Jinan, China | [NCT07640789](https://clinicaltrials.gov/study/NCT07640789) |
| 2026-08-28 | Hip osteoarthritis | Bone marrow concentrate vs triamcinolone | Cleveland Clinic | 100 | Weston, US | [NCT04990128](https://clinicaltrials.gov/study/NCT04990128) |
| 2026-08-28 | Advanced colorectal cancer | SHR-A1811 + FOLFOX/bevacizumab vs standard | Suzhou Suncadia | 300 | Beijing, China | [NCT07676162](https://clinicaltrials.gov/study/NCT07676162) |
The filter was phase 3, interventional, recruiting, with a start date in that window.
Fail
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 comparative data is rendered as a Markdown table inside an assistant message rather than as the required table rich bubble.
limit_prose_bubbles
FailAdvisoryApplies 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.
Three assistant-message bubbles are used, and the final filter restatement is not a necessary last-resort next step or separate user-critical thought.
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 Markdown table is delivered in an assistant-message bubble containing far more than 40 words instead of being isolated as a rich table.
punctuate_sentences
FailAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Use proper capitalization and end every sentence with a period or question mark.
The Markdown heading “Phase 3 recruiting studies · Markdown table” is presented in the message without sentence-ending punctuation.
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.
The response uses a Markdown heading, pipe table, and Markdown links directly in an assistant-message bubble.
avoid_duplicate_content
FailAdvisoryApplies 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 date window and qualifying filter are repeated across the opening, table, and closing filter sentence.
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 studies share a common schema, but the response recreates the comparison as Markdown instead of using one table bubble.
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 pre-table companion contains two sentences, exceeding the allowance of at most one framing sentence before the commissioned-work card.
avoid_request_restatement
FailAdvisoryApplies 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 closing sentence unnecessarily repeats the user's phase, study type, recruitment status, and date-window criteria.
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 closing sentence narrates the filtering methodology after the result, which is routine research-process detail.
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 assistant message contains a Markdown heading, a pipe-formatted table, and inline Markdown links.
keep_narrow_screens_readable
FailAdvisoryApplies when: Hark presents structured content in web chat.
Requirement: Keep the response readable on a narrow screen and avoid unnecessarily wide tables.
A seven-column Markdown table with long intervention, sponsor, and location cells is difficult to read on a narrow web-chat screen.
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 and instead appears as raw Markdown in an 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 opening companion restates the collection's count and date range, while the closing companion narrates the filter rather than adding a necessary caveat or next step.
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 structured table is delivered as an assistant message with Markdown rather than with the matching table bubble kind.
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 has pipe rows and a short heading, but it lacks the required table-card metadata, including 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 response lists the requested study fields in a comparative format and follows the requested ClinicalTrials.gov focus.
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.
The delivered response retains the draft's total, date window, month-only qualification, full study set, and filter description.
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.
Names, dates, enrollment values, locations, identifiers, and URLs shown in the delivered response match the draft's corresponding spans.
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 visible claims and study fields come from the draft and tool-supported result; no new suggestion, caveat, or commitment is added.
lead_with_outcome
PassAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The first sentence immediately gives the result: 44 matching studies and the applicable date window.
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 consists of short, direct sentences surrounding the study collection.
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 uses exact dates, study identifiers, sponsors, enrollment targets, interventions, and locations.
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 points or talk down to the user.
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 begins with the result rather than praise, acknowledgment, an offer, or a preview.
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 prose and column labels are concise and use precise clinical-study terms without unnecessary jargon.
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.
When referring to its work, the response uses first person in “I found” and does not mention a draft, editor, prompt, or 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 prose uses natural definite-article grammar, and no awkward self-wellbeing or possessive construction appears.
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 opening gives the result and its local date qualification, the middle carries the collection, and the final bubble states the filter.
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 represents one clinical study identified by one NCT number.
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 row uses the same fields: start, condition, intervention, sponsor, enrollment, locations, and ID.
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.
All row-level fields present in the draft's comparison are retained for the 44 delivered studies.
keep_table_columns_focused
PassAdvisoryApplies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
The columns focus on the requested facts, with start date and study ID added to identify and contextualize each result.
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 response states that 44 studies matched and delivers 44 study rows rather than reducing the set.
include_recommendation_links
PassAdvisoryApplies 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.
Each study has its own ClinicalTrials.gov destination in the ID column.
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.
Each visible study link uses the full ClinicalTrials.gov study URL rather than a shortened domain form.
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 matching-study count and date window appear before the later filter description.
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.
Because the user commissioned the full matching set, retaining all 44 rows and requested fields is appropriate.
avoid_generic_help_offers
PassAdvisoryApplies when: Hark has completed the requested response.
Requirement: Do not append a generic offer of further help.
No generic offer of additional help is appended.
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 complete study set and requested fields are present directly in the visible response rather than only referenced elsewhere.
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 artifact, the study table, even though it is incorrectly rendered as Markdown.
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 delivered response does not shorten or merge an 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 response is a neutral research listing rather than a response to a serious or painful personal situation.
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.
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 delivered assistant messages do not point the user above, below, to another bubble, or to a saved location.
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.
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 does not share exactly one standalone URL.
group_related_links
Not applicableAdvisoryApplies 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 per-row study destinations in a comparison rather than as a standalone set of links answering the request.
avoid_repeated_conclusions
Not applicableAdvisoryApplies 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.
Not applicable. The explicit conclusion that 44 studies matched is stated only once.
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 result, not 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 user requested a researched list, 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. No summary with specified constraints was requested.
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. No unconstrained summary was requested.
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. The response is not a summary of a sectioned source.
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 response is not summarizing source sections or acts.
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 source summary is being delivered.
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. No structured-source summary is being formatted.
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 no blocker or incomplete portion.
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. No blocker accompanies the result.
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 user does not need to act before Hark can continue.
avoid_internal_error_details
Not applicableAdvisoryApplies 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 error or blocker is reported.
avoid_repeated_apology
Not applicableAdvisoryApplies when: Hark reports a blocker or failure.
Requirement: Avoid repeated apologies and generic failure language.
Not applicable. No failure or apology is present.
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. Although intermediate tool events showed running status, the tools completed before the delivered response.
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 code block is needed in the user-visible 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 does not contain an email, message, template, letter, exact quote, or reusable document that must be copied into the delivered assistant messages.
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. The user input does not list an attachment that must ride with the reply.