← Back to scenario detail

Response style analysis

Applied 48 · Passed 31 · Failed 17 · Not applicable 20

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

Prompt

Use the web_fetch tool to answer the prompt. Please summarize the top 20 articles currently on https://news.ycombinator.com/. Give one sentence per article, then identify the three main themes across the page.

Hark's responses

Top 20 on Hacker News right now, one sentence each.
### Top 20 Hacker News Articles · Current front page | Article | Summary | Link | | --- | --- | --- | | A misalignment of AI in mathematics | AI's goals in mathematics are misaligned with what mathematicians value; 578 comments make it the day's biggest discussion. | https://mathandai.org/ | | I spent $220 on Google app ads and 60% of the installs were robots | Most installs from Google app ads came from bot farms, according to a game developer's investigation. | https://dayzlegame.com/blog/google-ads-bot-farm/ | | GrapheneOS' rewritten Messages app is released | The privacy-focused Android OS released version 13 of its from-scratch Messages app. | https://github.com/GrapheneOS/Messaging/releases/tag/13 | | A Design Space Exploration of Async/Await | Brown researchers map the design tradeoffs different languages make in their async/await models. | https://cel.cs.brown.edu/blog/design-space-async-await/ | | Project Blinkenlights | The classic Chaos Computer Club project that turned building facades into giant low-res displays. | https://blinkenlights.de/en/ | | Show HN: ResolveHQ | An open-source helpdesk running entirely on Cloudflare's edge stack. | https://github.com/mirza-rizvi/ResolveHQ | | Litelm: LiteLLM Without the Bloat | A stripped-down alternative to LiteLLM for calling multiple model providers. | https://github.com/kennethwolters/litelm | | Snap: an inviting programming language for kids and adults | Berkeley's block-based visual language for teaching computer science. | https://snap.berkeley.edu/ | | AlphaGenome maps 9B DNA variants | DeepMind's AlphaGenome produced an atlas of billions of genetic variants. | https://spectrum.ieee.org/alphagenome-atlas | | The EPA is planning to scrap public review rules for data center pollution | The EPA wants to drop public-comment requirements for data center permits. | https://capitalbnews.org/data-centers-permit-rules-epa/ | | Rune is now open source | The Rune build tooling company released its product under an open-source license. | https://rune.build/blog/rune-is-now-open-source | | I've operated petabyte-scale ClickHouse clusters for 5 years | Hard-won operational lessons from running huge ClickHouse deployments at Tinybird. | https://www.tinybird.co/blog/what-i-learned-operating-clickhouse | | So you want to use OpenRouter? | The page's highest-scoring post, a critical practical guide to routing LLM traffic through OpenRouter. | https://mmoustafa.com/blog/so-you-want-to-use-openrouter/ | | Mind-altering drugs played key role in rise of Andean civilization | Psychoactive substances helped consolidate early Andean social hierarchies. | https://www.science.org/content/article/mind-altering-drugs-played-key-role-rise-andean-civilization | | QueryBrew: System-Agnostic SQL-to-SQL Query Optimization | A VLDB paper on rewriting SQL into faster SQL independent of the database engine. | https://www.vldb.org/pvldb/vol19/p4494-schmidt.pdf | | Logo Programming Language | MIT Media Lab's history of Logo, the turtle-graphics language built for children. | https://el.media.mit.edu/logo-foundation/what_is_logo/logo_programming.html | | Zep AI is hiring a Head of Forward Deployed Engineering | Paid YC job listing. | https://www.getzep.com/careers/ | | Show HN: Godot and Rust based multiplexer | A terminal multiplexer built on the Godot engine plus Rust, with panes and more. | https://github.com/godot-pty/gpty | | Hepburn Romanization | A translator's primer on the Hepburn system for writing Japanese in Latin script. | https://www.fink-translate.com/blog/hepburn-romanization.html | | CIA Releases President's Daily Briefs in Commemoration of 9/11 | The CIA declassified presidential daily briefs for the attack's 25th anniversary. | https://www.cia.gov/stories/story/cia-releases-presidents-daily-briefs-in-commemoration-of-the-25th-anniversary-of-9-11/ |
Three themes: AI scrutiny (top post attacks AI's fit with math, OpenRouter and Litelm push back on LLM plumbing), computing history and teaching (Logo, Snap, Blinkenlights), and infrastructure at scale and its costs (petabyte ClickHouse ops, edge tooling, EPA pollution, ad fraud).

Fail

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 draft called the first article the biggest discussion on the page, but the delivered response calls it the day's biggest discussion, changing the claim's scope.

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 phrase “the day's biggest discussion” adds a day-wide scope not present in the draft, which only claimed it was biggest on the page.

use_direct_short_sentences

FailAdvisory
Applies when: Hark sends a user-visible prose response.
Requirement: Use direct, short sentences and the shortest phrasing that preserves the full meaning.
Most summaries are concise, but the themes bubble is a long sentence containing three parenthetical explanations rather than short direct sentences.

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.
Phrases such as “push back on LLM plumbing” and “hard-won” are informal or figurative where more precise wording would be clearer.

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 themes bubble is approximately 42 words, exceeding the 40-word limit.

keep_comparable_detail

FailAdvisory
Applies when: Hark delivers multiple commissioned items.
Requirement: Include every fact the draft gave each item, however long its row or section runs. Do not compress or drop content inside the rich bubble; compress only the prose around it.
The delivered table drops draft-provided facts such as most point totals, YC W24, and parts of several full titles, despite the rule requiring all per-item facts to remain inside the rich bubble.

include_ranking_column

FailAdvisory
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 user requested the top 20 articles, but the table has no rank or front-page-position column.

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 sentence after the table is about 42 words, exceeding the 20-word limit for a rich-card companion.

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.
“Top 20 on Hacker News right now, one sentence each” unnecessarily restates the user's request.

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 summary, but it is delivered as a table rather than the required single 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 response follows the one-sentence and thematic requirements, but it does not use the required document-bubble delivery for a summary.

preserve_summary_skeleton

FailAdvisory
Applies when: Hark provides a summary.
Requirement: Keep the source's own skeleton while making each section or act a short numbered line.
The source's ranked skeleton is kept in order, but the summary does not use short numbered lines as required.

keep_summary_qualifications_local

FailAdvisory
Applies when: A summarized statement needs a qualification.
Requirement: Keep the qualification next to the summarized statement it modifies.
The draft's qualification that the first article “argues” a position is removed, turning the article's thesis into an unqualified assertion.

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 unnumbered table rows rather than short numbered lines in a document bubble.

keep_narrow_screens_readable

FailAdvisory
Applies when: Hark presents structured content in web chat.
Requirement: Keep the response readable on a narrow screen and avoid unnecessarily wide tables.
The three-column table includes many long raw URLs, making it unnecessarily wide on narrow screens.

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 post-table companion exceeds the allowed short length, and the pre-table sentence largely captions the table by repeating its scope.

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 short title, but no visible “Excel Spreadsheet” subtitle.

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 gives one sentence for each of 20 articles and then identifies three themes, matching the requested presentation.

preserve_draft_substance

PassAdvisory
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.
All 20 draft items and the three thematic conclusions remain present. The response compresses supporting details without changing the overall deliverable.

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 introduces and then presents the requested top-20 summaries.

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 specific article titles, organizations, technologies, quantities, and outcomes rather than relying mainly on vague descriptions.

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 summaries are neutral and do not belabor elementary points or talk down to the user.

avoid_throat_clearing

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

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.
The 20 comparable articles are presented in a table instead of being recreated as a long prose list.

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.
Articles involving pollution, drugs, and 9/11 are summarized in a restrained, direct register without swagger.

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.
No awkward self-wellbeing phrasing or relevant possessive error appears.

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 bubbles around one rich table, 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 first prose bubble frames the article summaries, while the second supplies the separately requested themes.

punctuate_sentences

PassAdvisory
Applies when: Hark sends a plain-prose bubble.
Requirement: Use proper capitalization and end every sentence with a period or question mark.
Both prose bubbles are capitalized and end with periods.

avoid_prose_markup

PassAdvisory
Applies when: Hark sends a plain-prose bubble.
Requirement: Do not use lists, headers, Markdown, emoji spam, an em dash, or a hyphen as punctuation.
The plain-prose bubbles contain no headers, lists, Markdown, emoji, em dashes, or punctuation hyphens.

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 article summaries once, and the final bubble adds distinct cross-page themes rather than repeating the rows.

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 20 articles share common fields and are presented together 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 table row represents one Hacker News article or listing.

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 row consistently exposes an article title, summary, and link.

keep_table_columns_focused

PassAdvisory
Applies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
The Article, Summary, and Link columns directly support identifying and understanding each requested item.

keep_every_commissioned_item

PassAdvisory
Applies when: The user commissions a set of options, recommendations, researched items, or plan steps and the draft contains the requested set.
Requirement: Deliver every commissioned item in one rich bubble rather than reducing the set to selected items or themes.
All 20 requested front-page items are included in the single table.

include_recommendation_links

PassAdvisory
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.
Each table row includes its destination in a dedicated Link column.

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 article destinations are shown as the draft's exact URLs without shortening them to domains.

answer_before_background

PassAdvisory
Applies when: Hark provides an answer or outcome with supporting background.
Requirement: Give the answer or outcome before the background detail.
The requested article summaries appear before the cross-page thematic synthesis.

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 three thematic conclusions are stated only once.

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 response keeps all 20 items because the user commissioned that set, while limiting each item to a short summary.

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 more help.

preserve_summary_order

PassAdvisory
Applies when: Hark summarizes a source with sections or acts.
Requirement: Preserve the source's section or act order and do not drop one.
The 20 items appear in the same order as positions 1 through 20 on the fetched page.

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 bubbles contain no Markdown; the structured material is isolated in the table bubble.

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 complete summaries and themes are present in the delivered messages rather than merely referenced 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 is contained in its own message, separate from the prose framing and thematic takeaway.

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 observed delivery distinguishes two prose messages from the structured table message, with no visibly mixed bubble kind.

limit_rich_bubbles

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

use_hark_first_person

Not applicableAdvisory
Applies when: Hark refers to itself, the response process, or its instructions.
Requirement: Speak as Hark in the first person. Never mention the draft, rewrite, editor, prompt, or response rules.
Not applicable. The response does not refer to Hark, its process, or its instructions.

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 personal 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 direct the user above, below, or to another location for the answer.

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 does not share exactly one standalone URL.

group_related_links

Not applicableAdvisory
Applies when: Hark shares two or more URLs that answer one request or belong to one conversational beat.
Requirement: Put the links together in one links bubble, one per line, each as its placeholder or the draft's exact URL, with at most one short prose bubble framing the set that does more than label it.
Not applicable. The URLs function as destinations attached to individual table rows, not as a standalone set of links answering the request.

avoid_routine_tool_narration

Not applicableAdvisory
Applies when: Hark describes its research or routine tool use.
Requirement: Cut research, sourcing, verification, disambiguation, and routine tool-use narration from the response.
Not applicable. The response does not narrate web fetching, research, sourcing, or verification.

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 contains no 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 both the number of summarized items and the one-sentence-per-item format.

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 work.

present_partial_result_before_blocker_detail

Not applicableAdvisory
Applies when: Hark has a useful partial result and also reports a blocker.
Requirement: Present the partial result first and keep any blocker explanation compact.
Not applicable. No blocker accompanies the 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 reports no error or blocker.

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 failure language or apology.

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. Although an intermediate tool event showed running status, the fetch completed before 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.

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, letter, template, exact quote, or text meant to be pasted elsewhere.

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 attachment accompanies the reply.