← Back to scenario detail

Response style analysis

Applied 38 · Passed 21 · Failed 17 · Not applicable 30

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

Prompt

Use the web_fetch tool to answer the prompt. Review today's top 10 launches on https://www.producthunt.com/. Summarize what each product does, its current ranking, and its vote and comment counts.

Hark's responses

Today's top 10 Product Hunt launches (Sept 11, 2026).
### Product Hunt top 10 · September 11, 2026 | # | Product | What it does | Votes | Comments | |---|---|---|---|---| | 1 | [Anysite.io](https://www.producthunt.com/products/anysite) | B2B data layer inside your AI agent: ask for company/people lists with titles and emails, via MCP or REST | 396 | 150 | | 2 | [Loqua](https://www.producthunt.com/products/loqua) | Voice-first assistant that turns speech into writing, reads your screen, and runs tasks by voice | 351 | 87 | | 3 | [Raycast 2.0](https://www.producthunt.com/products/raycast) | New generation of the extendable Mac productivity launcher | 276 | 14 | | 4 | [Wisry](https://www.producthunt.com/products/wisry) | AI agents scan Meta/TikTok ad libraries, clone winning ads to your brand, and launch them for ROAS | 246 | 19 | | 5 | [Cline Desktop App](https://www.producthunt.com/products/cline-4) | Open-source coding agent app for open-weight models, drives editor, terminal, and browser | 224 | 16 | | 6 | [easyspecs.ai](https://www.producthunt.com/products/easyspecs-ai) | Documents undocumented codebases into specs so spec review replaces reviewing AI-written code | 143 | 23 | | 7 | [Sliick](https://www.producthunt.com/products/sliick) | Free in-browser 3D device mockups for screenshots and videos, no watermark | 129 | 8 | | 8 | [Devin Voice](https://www.producthunt.com/products/devin-voice) | Talk to Cognition's Devin and it plans, codes, and ships the task | 115 | 1 | | 9 | [Moji](https://www.producthunt.com/products/moji-2) | Lightweight cross-platform Markdown reader/editor with live preview and PDF/HTML/PNG export | 100 | 7 | | 10 | [ChatHop](https://www.producthunt.com/products/chathop) | Move an AI chat to another assistant mid-thread with context, or copy it as text/Markdown | 96 | 7 |

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 response omits the draft's material clarification that the displayed vote figures are Product Hunt's current scores.
Evidence: E0008, E0010

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 source identifies the figures as scores influenced by voting, discussion, and activity, but the response presents them unqualified as vote counts.
Evidence: E0007, E0010

avoid_throat_clearing

FailAdvisory
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 first bubble is an unnecessary preview that is immediately repeated by the following heading.
Evidence: E0009, E0010

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 recreated as a Markdown table inside an assistant message rather than delivered as the required table bubble.
Evidence: E0010

use_plain_precise_language

FailAdvisory
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.
Calling Product Hunt's broader engagement scores 'Votes' without the available qualification is not precise.
Evidence: E0007, E0010

keep_prose_bubbles_compact

FailAdvisory
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.
The Markdown table is delivered in an assistant-message bubble far exceeding 40 words.
Evidence: E0010

punctuate_sentences

FailAdvisory
Applies when: Hark sends a plain-prose bubble.
Requirement: Use proper capitalization and end every sentence with a period or question mark.
Several table descriptions are clause-like sentences without terminal punctuation.
Evidence: E0010

avoid_prose_markup

FailAdvisory
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 response uses a Markdown heading, Markdown links, and Markdown table syntax in an assistant-message bubble.
Evidence: E0010

avoid_duplicate_content

FailAdvisory
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 top-ten date framing in the first bubble is repeated by the heading in the second bubble.
Evidence: E0009, E0010

choose_collection_format_for_comparison

FailAdvisory
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.
Although the content uses table syntax, it is not delivered as one correctly tagged table bubble.
Evidence: E0010

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.
All ten items are present, but they are not delivered in the required rich table bubble.
Evidence: E0010

group_related_links

FailAdvisory
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 Product Hunt URLs are embedded in Markdown table cells rather than grouped in a links bubble.
Evidence: E0010

avoid_request_restatement

FailAdvisory
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 first bubble restates the top-ten request, and the following heading repeats it again without resolving ambiguity.
Evidence: E0009, E0010

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 second assistant-message bubble contains Markdown heading, link, and table syntax.
Evidence: E0010

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 is expressed as Markdown and mixed with a heading in the same assistant-message bubble rather than isolated in a table bubble.
Evidence: E0010

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 structured comparison appears as a generic assistant message rather than a matching table-kind bubble.
Evidence: E0010

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 lacks a proper rich-table card and the required 'Excel Spreadsheet' subtitle, even though it has pipe rows and a visible heading.
Evidence: E0010

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 follows the requested focus by giving each launch's purpose, ranking, vote figure, and comment count.
Evidence: E0001, E0010

avoid_invented_content

PassAdvisory
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 product descriptions, rankings, counts, date, and links are supported by the draft or fetched result.
Evidence: E0007, E0008, E0010

lead_with_outcome

PassAdvisory
Applies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The response immediately identifies the requested top-ten result.
Evidence: E0009

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 framing is short, and the table descriptions use concise wording.
Evidence: E0009, E0010

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 exact product names, rankings, date, scores, and comment counts.
Evidence: E0010

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 descriptions are factual and do not belabor basic points or talk down to the user.
Evidence: E0010

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 response appropriately uses hearer-oriented forms such as 'your AI agent' and 'your screen.'
Evidence: E0010

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 reply uses only two assistant-message bubbles, within the stated limit.
Evidence: E0009, E0010

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 bubble frames the result, while the second contains the single commissioned comparison.
Evidence: E0009, E0010

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 table row contains exactly one product.
Evidence: E0010

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 product uses the same fields: rank, product, description, votes, and comments.
Evidence: E0010

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.
All item-level facts included in the draft comparison are retained for all ten products.
Evidence: E0008, E0010

keep_table_columns_focused

PassAdvisory
Applies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
The five columns directly address the requested product, purpose, ranking, vote figure, and comment count.
Evidence: E0001, E0010

include_ranking_column

PassAdvisory
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.
The response includes a numbered ranking column from 1 through 10.
Evidence: E0010

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 sentence before the commissioned comparison is only eight words.
Evidence: E0009

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.
Each displayed Product Hunt destination matches the corresponding exact URL in the fetched result and draft.
Evidence: E0007, E0008, E0010

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 response presents the requested result directly without preceding background.
Evidence: E0009, E0010

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.
The user commissioned ten items, and the response includes all ten with the requested fields.
Evidence: E0001, E0010

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 a generic offer of further help.
Evidence: E0010

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 uses only the five fields needed for the request and avoids extra wide columns such as tags or external URLs.
Evidence: E0001, E0010

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 full requested ten-item result appears directly in the delivered messages.
Evidence: E0010

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.

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 question.

match_register_to_stakes

Not applicableAdvisory
Applies when: Hark responds about a serious, painful, or high-stakes subject.
Requirement: Stay short and direct while dropping slang and swagger.
Not applicable. The subject is not serious, painful, or high-stakes.

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 to another message, file, or saved location as the answer.

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 products are reported launches, not options or recommendations offered to the user.

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.

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 response does not narrate fetching, research, verification, or other tool use.

avoid_repeated_conclusions

Not applicableAdvisory
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.
Not applicable. The response does not state a substantive conclusion in multiple places.

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 response is a completed result, not a progress update.

compress_summary

Not applicableAdvisory
Applies when: Hark provides a summary.
Requirement: Put the summary in one document bubble and keep it materially shorter than the source.
Not applicable. This is a commissioned comparison of multiple launches rather than a source-summary deliverable governed by the document-bubble summary rules.

follow_summary_instructions

Not applicableAdvisory
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.
Not applicable. The user did not request a source summary with specified length, audience, reading level, or document format.

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 task commissions a ten-item comparison rather than an unspecified-format source summary.

preserve_summary_skeleton

Not applicableAdvisory
Applies when: Hark provides a summary.
Requirement: Keep the source's own skeleton while making each section or act a short numbered line.
Not applicable. There is no sectioned or acted source being summarized into a document.

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 sectioned or acted source-summary structure to preserve.

keep_summary_qualifications_local

Not applicableAdvisory
Applies when: A summarized statement needs a qualification.
Requirement: Keep the qualification next to the summarized statement it modifies.
Not applicable. The response is a comparative collection rather than a structured source summary.

use_summary_numbered_lines

Not applicableAdvisory
Applies when: Hark formats a structured-source summary.
Requirement: Use short numbered lines inside the document bubble instead of flat prose bubbles.
Not applicable. The task calls for a common-schema comparison, for which the table rule applies instead of structured-source summary lines.

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 incomplete 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. The response reports no blocker alongside a partial result.

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. No user action is required 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. The response does not report a blocker or expose internal errors.

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 successful fetch completed before the final response, so the task was not still running.
Evidence: E0007

keep_card_companions_contextual

Not applicableAdvisory
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.
Not applicable. No correctly formed rich card is present next to the prose bubble.

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. The draft contains no code block needed by the user.

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, message, template, letter, exact quote, or reusable document.

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. The input lists no attachments.

limit_rich_bubbles

Not applicableAdvisory
Applies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
Not applicable. The delivered response contains no correctly formed rich bubble.