← Back to scenario detail
Response style analysis
Applied 39 · Passed 31 · Failed 8 · Not applicable 29
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
44 phase 3 interventional studies began recruiting between Aug 28 and Sep 11, 2026. Enrollment figures are estimated targets.
### Phase 3 recruiting studies · ClinicalTrials.gov study table
| Condition | Intervention | Sponsor | Enroll | Locations |
|---|---|---|---|---|
| [Secondary immune deficiency](https://clinicaltrials.gov/study/NCT07648264) | IgPro20 | CSL Behring | 63 | 60 sites, US + 10 countries |
| [Metastatic urothelial carcinoma](https://clinicaltrials.gov/study/NCT07815665) | Ivonescimab + enfortumab vedotin vs pembrolizumab + EV | Summit Therapeutics | 800 | 7 sites, US |
| [NSCLC, EGFR-mutant oligometastatic](https://clinicaltrials.gov/study/NCT07738172) | Osimertinib ± primary tumor resection | National Taiwan University Hospital | 154 | 1 site, Taiwan |
| [Essential thrombocythemia](https://clinicaltrials.gov/study/NCT07623200) | INCA033989 vs best available treatment | Incyte | 426 | 177 sites, US + 17 countries |
| [Spinal muscular atrophy](https://clinicaltrials.gov/study/NCT07444450) | Salanersen (BIIB115) vs sham | Biogen | 42 | 1 site, US |
| [Sexual and reproductive health education](https://clinicaltrials.gov/study/NCT07772778) | Disability-focused SRH curriculum | University of Minnesota | 412 | 1 site, Tanzania |
| [Generalized anxiety disorder](https://clinicaltrials.gov/study/NCT07807865) | ITI-1284 | Intra-Cellular Therapies | 900 | 1 site, US |
| [Myelofibrosis with anemia](https://clinicaltrials.gov/study/NCT07623161) | Elritercept vs placebo | Takeda | 324 | 195 sites, US + 30 countries |
| [Plaque psoriasis](https://clinicaltrials.gov/study/NCT07724366) | TQH3906 vs deucravacitinib | Chia Tai Tianqing | 400 | 45 sites, China |
| [Triple negative breast cancer](https://clinicaltrials.gov/study/NCT07679360) | Trastuzumab rezetecan + adebrelimab | Suzhou Suncadia | 1000 | 1 site, China |
| [Gingival recession](https://clinicaltrials.gov/study/NCT07763808) | Three graft techniques | Aziz Aliyev Institute | 75 | 1 site, Azerbaijan |
| [Cancer (exercise support)](https://clinicaltrials.gov/study/NCT07408128) | Peer matching, exercise professional | McMaster University | 183 | 1 site, Canada |
| [Pediatric obesity post-sleeve](https://clinicaltrials.gov/study/NCT06934655) | Semaglutide 2.4 mg | Children's Hospital Los Angeles | 150 | 1 site, US |
| [Dengue](https://clinicaltrials.gov/study/NCT07016321) | Emetine HCl 6/12 mg vs placebo | Johns Hopkins | 600 | 2 sites, US + Nepal |
| [Knee osteoarthritis surgery](https://clinicaltrials.gov/study/NCT07151417) | PAI ± steroid ± Zilretta | Walter Reed | 240 | 1 site, US |
| [Late-life treatment-resistant depression](https://clinicaltrials.gov/study/NCT07623135) | Lumateperone vs placebo | Eric Lenze (WashU) | 100 | 2 sites, US |
| [Refractory CMV/adenovirus infection](https://clinicaltrials.gov/study/NCT07225972) | Viral CTLs + standard care | New York Medical College | 138 | 2 sites, US |
| [Duchenne muscular dystrophy (exon 44)](https://clinicaltrials.gov/study/NCT07587242) | AOC 1044 vs placebo | Avidity Biosciences | 70 | 13 sites, Europe |
| [Ulcerative colitis](https://clinicaltrials.gov/study/NCT07686081) | Ponesimod vs placebo | Vanda Pharmaceuticals | 150 | 2 sites, US |
| [Uveal melanoma, adjuvant](https://clinicaltrials.gov/study/NCT07804186) | Darovasertib + crizotinib | IDEAYA Biosciences | 450 | 1 site, Canada |
| [First-episode psychosis](https://clinicaltrials.gov/study/NCT06778564) | CBD oral solution vs placebo | University of Oxford | 250 | 17 sites, 9 countries |
| [PTSD](https://clinicaltrials.gov/study/NCT07570654) | COMP360 psilocybin | COMPASS Pathways | 300 | 2 sites, US |
| [Ocular GVHD](https://clinicaltrials.gov/study/NCT07776210) | d-MAPPS ophthalmic solution | Regenerative Ocular Immunobiologics | 30 | 5 sites, US |
| [Non-transfusion-dependent thalassemia](https://clinicaltrials.gov/study/NCT07517133) | Mitapivat vs placebo | Agios | 45 | 4 sites, US |
| [Transfusion-dependent thalassemia](https://clinicaltrials.gov/study/NCT07506863) | Mitapivat vs placebo | Agios | 54 | 3 sites, US |
| [Narcolepsy](https://clinicaltrials.gov/study/NCT07540364) | Samelisant vs placebo | Suven Life Sciences | 240 | 1 site, US |
| [Hemophilia A](https://clinicaltrials.gov/study/NCT04563520) | Emicizumab, FEIBA, rFVIIa | Emory University | 5 | 2 sites, US |
| [Newly diagnosed multiple myeloma](https://clinicaltrials.gov/study/NCT07285239) | Belantamab mafodotin or daratumumab + VRd | PrECOG | 500 | 1 site, US |
| [RET-translocated NSCLC](https://clinicaltrials.gov/study/NCT07809256) | Lenvatinib + pembrolizumab | EuroCityClinic | 15 | 1 site, Russia |
| [Focal seizures](https://clinicaltrials.gov/study/NCT07594119) | RAP-219 vs placebo | Rapport Therapeutics | 312 | 11 sites, US |
| [Burn injury resuscitation](https://clinicaltrials.gov/study/NCT07212998) | Plasma vs standard care | Jason Sperry (Pittsburgh) | 750 | 1 site, US |
| [RSV in immunocompromised adults](https://clinicaltrials.gov/study/NCT07768345) | RSVpreF revaccination | Pfizer | 440 | 5 sites, US |
| [Extensive-stage small cell lung cancer](https://clinicaltrials.gov/study/NCT07778316) | Tarlatamab SC vs IV | Amgen | 400 | 2 sites, US + China |
| [Cancer-associated VTE](https://clinicaltrials.gov/study/NCT07493304) | REGN7508 vs apixaban | Regeneron | 1600 | 6 sites, US + South Korea |
| [Pulmonary hypertension with ILD](https://clinicaltrials.gov/study/NCT07816185) | Inhaled mosliciguat vs placebo | Pulmovant | 376 | 3 sites, US |
| [COVID-19, high risk](https://clinicaltrials.gov/study/NCT07743580) | Secutrelvir vs placebo | Shionogi | 2000 | 34 sites, US, Bulgaria, Japan |
| [Nasopharyngeal carcinoma anorexia](https://clinicaltrials.gov/study/NCT07796789) | Megestrol acetate vs placebo | Sun Yat-sen University | 204 | 3 sites, China |
| [Early type 2 diabetes with obesity](https://clinicaltrials.gov/study/NCT07743983) | BGM0504 vs semaglutide | BrightGene | 372 | 1 site, China |
| [Stage III EGFR-mutated NSCLC](https://clinicaltrials.gov/study/NCT07640789) | BL-B01D1 + osimertinib | Sichuan Baili | 418 | 1 site, China |
| [Platinum-sensitive ovarian cancer](https://clinicaltrials.gov/study/NCT07564141) | Rina-S ± bevacizumab | Genmab | 688 | 2 sites, US |
| [Advanced colorectal cancer](https://clinicaltrials.gov/study/NCT07676162) | SHR-A1811 + chemo + bevacizumab | Suzhou Suncadia | 300 | 1 site, China |
| [Metastatic prostate cancer](https://clinicaltrials.gov/study/NCT07751133) | ARPI dose optimization | University College London | 1500 | 1 site, UK |
| [KRAS G12D metastatic pancreatic cancer](https://clinicaltrials.gov/study/NCT07805954) | Zoldonrasib + daraxonrasib vs gem/nab-paclitaxel | Revolution Medicines | 400 | 1 site, US |
| [Hip osteoarthritis](https://clinicaltrials.gov/study/NCT04990128) | Bone marrow aspirate concentrate vs triamcinolone | Cleveland Clinic | 100 | 1 site, US |
Fail
preserve_draft_substance
FailAdvisoryApplies when: Hark selects content from the draft for delivery.
Requirement: Preserve the draft's substance. Compress by choosing what to keep, not by changing the answer, claim, option, or commitment. Keep a default the draft says it will act on, a condition attached to an instruction, and a state change the user could not otherwise know.
The delivered introduction changes “recruiting with a start date” into the stronger claim that the studies “began recruiting.” It also drops the draft’s API-status qualification and CSV reference.
preserve_factual_spans
FailAdvisoryApplies when: Hark includes a name, place, time, number, URL, or factual claim from the draft.
Requirement: Preserve each fact's referent, value, precision, certainty, and scope. Rephrasing is allowed when all five stay unchanged. Keep URLs, identifiers, exact quotes, code, and documents byte-exact.
“Began recruiting” does not preserve the meaning or certainty of the source field. The evidence contains study start dates, many marked estimated, rather than verified recruitment-begin dates.
avoid_invented_content
FailAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Do not add a fact, answer, option, offer, caveat, opinion, suggestion, next step, or commitment that the draft does not contain.
The response introduces the stronger conclusion that all 44 studies began recruiting in the window, which the draft described only as currently recruiting studies with start dates in that window.
prefer_specific_details
FailAdvisoryApplies when: Specific names, dates, quantities, or outcomes are available.
Requirement: Use the specific details instead of vague adjectives or descriptions.
Several locations use vague summaries such as “US + 10 countries,” “Europe,” and “9 countries” even though specific countries and sites were available.
use_plain_precise_language
FailAdvisoryApplies 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 table uses many unexplained abbreviations, including SRH, CTLs, GVHD, VRd, VTE, ILD, and ARPI, reducing clarity for a general reader.
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 framing companion contains two sentences, while the rule permits at most one framing sentence before the card.
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.
Although contextual, the companion uses two sentences; the rule allows at most one short companion sentence.
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 a short title and pipe rows, but no visible “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 uses a table with the requested condition, intervention, sponsor, enrollment, and location fields.
lead_with_outcome
PassAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The response begins with the result count and 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 two short, direct sentences.
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.
It starts immediately with the result rather than praise, acknowledgment, or a preview.
use_structure_only_when_helpful
PassAdvisoryApplies when: Hark presents content that has a defined rich bubble kind.
Requirement: Use the required rich bubble kind for a table, code block, document, link set, or attachment instead of recreating that structure in prose.
The comparable studies are presented in one table rather than recreated as prose.
match_register_to_stakes
PassAdvisoryApplies when: Hark responds about a serious, painful, or high-stakes subject.
Requirement: Stay short and direct while dropping slang and swagger.
The clinical-research response remains professional and avoids slang or swagger.
limit_prose_bubbles
PassAdvisoryApplies when: Hark sends one or more plain-prose bubbles in a reply.
Requirement: Aim for one prose bubble. Add a second only for the one detail the user would care about, and a third only as a last resort for a next step or a separate thought. Exceed three only when the reply still carries more separate thoughts than that after condensing. Rich bubbles sit outside this count.
There is one prose bubble before the table.
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.
The prose bubble is well below 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.
Both prose sentences are capitalized and end with periods.
avoid_prose_markup
PassAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Do not use lists, headers, Markdown, emoji spam, an em dash, or a hyphen as punctuation.
The plain-prose bubble contains no list, header, Markdown, emoji, or dash punctuation.
avoid_delivery_pointers
PassAdvisoryApplies when: Hark refers to another message, bubble, file, workspace location, or delivery step.
Requirement: Deliver the content itself. Do not point above, below, next, or to a saved location as the answer.
The delivered prose does not point the user to another message, file, or saved location.
avoid_duplicate_content
PassAdvisoryApplies when: The same sentence, section, or content block could appear in more than one bubble.
Requirement: Send each piece of content once across the reply.
The introductory count and qualification are not duplicated in the table rows.
choose_collection_format_for_comparison
PassAdvisoryApplies 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.
All studies share the same requested fields and are presented in one table.
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 study.
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 five 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.
The delivered table retains the per-row facts present in the draft table for all 44 studies.
keep_table_columns_focused
PassAdvisoryApplies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
The five columns directly match the facts requested by the user.
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.
All 44 studies from the draft are retained in one table.
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 ClinicalTrials.gov study URLs are preserved exactly from the draft and appear once each.
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 count and date-window outcome appear before the study details.
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 opening reports the result count and scope rather than merely repeating the request.
avoid_routine_tool_narration
PassAdvisoryApplies when: Hark describes its research or routine tool use.
Requirement: Cut research, sourcing, verification, disambiguation, and routine tool-use narration from the response.
The delivered response does not narrate web fetching, API calls, verification, or shell processing.
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 main result is stated once.
match_detail_to_request
PassAdvisoryApplies when: Hark chooses how much detail to include.
Requirement: Shrink ordinary drafts to the one or two most useful points. Keep every requested item only when the user commissioned a set of work.
Because the user commissioned a complete set, the response retains all 44 listed studies.
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.
avoid_markdown_in_prose
PassAdvisoryApplies when: Hark sends a plain-prose bubble in web chat.
Requirement: Do not use Markdown in prose bubbles. Use the matching rich bubble kind when content needs structure.
The plain-prose bubble contains no Markdown; the structured material is separated into the table bubble.
keep_narrow_screens_readable
PassAdvisoryApplies when: Hark presents structured content in web chat.
Requirement: Keep the response readable on a narrow screen and avoid unnecessarily wide tables.
The table uses only the five requested columns and does not add unnecessary dimensions.
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 result count and complete study table are included directly in the response.
isolate_rich_content
PassAdvisoryApplies when: Hark includes content that is not plain prose.
Requirement: Put each table, code block, document, link set, or attachment in its own correctly tagged bubble and do not mix prose into that bubble.
The table is separated from the plain-prose bubble and presented as one structured block.
tag_every_bubble
PassAdvisoryApplies when: Hark sends any bubble.
Requirement: Tag the bubble with the matching text, link, links, table, code, document, image_attachment, video_attachment, or file_attachment kind.
The observable delivery separates a plain-text bubble from a table bubble with matching presentation.
limit_rich_bubbles
PassAdvisoryApplies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
The response uses one rich table bubble.
Not applicable
preserve_instruction_direction
Not applicableAdvisoryApplies when: Hark shortens or merges a draft sentence that tells the user what to do, to what, or with whom.
Requirement: Keep the sentence's verb, object, and addressee. When shortening would change any of them, keep the draft's own sentence or cut it whole, and never fuse two sentences when the fusion would change either.
Not applicable. The delivered response does not shorten an instruction telling the user to act.
avoid_condescending_explanations
Not applicableAdvisoryApplies when: Hark explains information to the user.
Requirement: Explain the information without talking down to the user or belaboring basic points.
Not applicable. The response does not provide a potentially condescending explanation.
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 questions.
use_hark_first_person
Not applicableAdvisoryApplies 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 applicableAdvisoryApplies 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_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.
keep_one_thought_per_bubble
Not applicableAdvisoryApplies 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.
Not applicable. There is not more than one prose bubble.
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 cheapest, fastest, or otherwise ranked comparison.
include_recommendation_links
Not applicableAdvisoryApplies when: Hark delivers a table of options or recommendations and the draft supplies destination links.
Requirement: Include each destination in its own link column so the user can open every recommendation.
Not applicable. The table is an informational study list, not a table of options or recommendations.
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 stand-alone 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 destinations for individual table rows rather than as a stand-alone link set.
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 researched results, 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 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 default-length 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.
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. The response is not a summary.
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 present.
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.
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 or partial-result limitation is reported.
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 blocker or internal error is reported.
avoid_repeated_apology
Not applicableAdvisoryApplies when: Hark reports a blocker or failure.
Requirement: Avoid repeated apologies and generic failure language.
Not applicable. The response reports no failure and contains no apology.
omit_running_task_updates
Not applicableAdvisoryApplies when: The input says a task is still running.
Requirement: Send no response about the running task. Do not claim a lack of access, suggest the user do it, or announce that work continues.
Not applicable. The final input state does not indicate that the task is still running.
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 user-needed code block is delivered.
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 for delivery.
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 input does not list an attachment riding with the reply.