← Back to scenario detail
Response style analysis
Applied 44 · Passed 21 · Failed 23 · Not applicable 24
Rubric: services/agent/prompts/editor/v1.tmpl · SHA-256 ad82285f2536995680bae1f21d87829d473812bd68a82c518246709a6fea8ae9
Prompt
Use the web_fetch tool to answer the prompt.
What incidents has https://www.cloudflarestatus.com/ reported in the past 14 days? Summarize the affected products and locations, duration, and resolution.
Hark's responses
Cloudflare reported ~43 incidents Aug 28–Sep 11. Three still open: Tunnel availability, Workers Cron Triggers, and WARP geo location. Almost all were minor; one was major (route leak in Palmas, Brazil on Sep 1).
### Cloudflare incidents, past 14 days · Summary table
| Incident | Product | Duration | Status |
|---|---|---|---|
| [Cloudflare Tunnel availability issues](https://www.cloudflarestatus.com/incidents/k7l4hzmthl3k) | Tunnel | Since Sep 11, 2:55 PM | Open |
| [Workers Cron Triggers degraded](https://www.cloudflarestatus.com/incidents/sjs8s0q2x4hw) | Workers | Since Sep 9, 12:17 PM | Open |
| [Incorrect geo location for some WARP users](https://www.cloudflarestatus.com/incidents/9g65dxfbcjln) | WARP | Open | Open |
| [Taiwan datacenter (TPE) network performance](https://www.cloudflarestatus.com/incidents/2njywrxj8qjf) | Network, Taipei | Sep 11, 12:35–3:03 PM (2h28m) | Resolved |
| [Workers VPC hostname route resolution](https://www.cloudflarestatus.com/incidents/9mcdtk1lphgl) | Workers VPC | Sep 11, 06:22–09:38 UTC (3h16m) | Resolved |
| [SSL provisioning delays](https://www.cloudflarestatus.com/incidents/3r3qcgbb0714) | SSL/Let's Encrypt | Sep 10, 7:20–9:05 PM | Resolved |
| [DNS update delays](https://www.cloudflarestatus.com/incidents/nhfcmzd1pv4p) | DNS propagation | Sep 10, 6:58 AM–3:22 PM (8h24m) | Resolved |
| [Bulk Redirects editing](https://www.cloudflarestatus.com/incidents/92j1xmlkscw3) | Dashboard | Sep 10, 8:41–9:57 AM | Resolved |
| [Workers AI errors](https://www.cloudflarestatus.com/incidents/jsvvrtk5hvym) | Workers AI (GLM 5.3) | Sep 9, 7:25 AM–1:09 PM | Resolved |
| [Increased HTTP errors](https://www.cloudflarestatus.com/incidents/dmc0gzyv8gcs) | Network, Philadelphia | Sep 9, 16:40–16:54 UTC (14m) | Resolved |
R2 had four separate 503 episodes, Access email delivery issues hit twice, and Asia-Pacific locations clustered (Taipei, Tokyo, Hong Kong, Singapore).
Fail
follow_explicit_style_instructions
FailAdvisoryApplies 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 user requested affected products, locations, duration, and resolution. The delivered table covers only a subset of incidents and replaces resolution details with a generic status column.
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 draft contained roughly 43 incidents, but the delivered table includes only ten. Most of the commissioned results and their resolution details were dropped.
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.
The draft specified that unlabelled times were PDT. The delivered response removed that qualification, making several displayed times ambiguous and reducing their precision.
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.
Comparable incident data was rendered as a Markdown table inside an assistant message rather than as a correctly tagged table bubble.
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 table message uses a Markdown header, Markdown links, and pipe-table markup in an assistant message.
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 three open incidents are stated in the opening prose and then repeated as the first three table rows.
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.
A table schema was chosen appropriately, but it was delivered as Markdown rather than as one table bubble.
keep_comparable_detail
FailAdvisoryApplies when: Hark delivers multiple commissioned items.
Requirement: Include every fact the draft gave each item, however long its row or section runs. Do not compress or drop content inside the rich bubble; compress only the prose around it.
The table omits most incidents and drops draft-provided location, impact, and resolution details from many included incidents.
keep_every_commissioned_item
FailAdvisoryApplies 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 says there were roughly 43 incidents but delivers rows for only ten, omitting most of the commissioned set.
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 prose before the table exceeds the 20-word limit, and the post-table companion also exceeds 20 words.
group_related_links
FailAdvisoryApplies 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.
Multiple related incident URLs are embedded in Markdown table cells rather than grouped in a links bubble.
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 heading restates the request as “Cloudflare incidents, past 14 days” without resolving an ambiguity or confirming scope.
avoid_repeated_conclusions
FailAdvisoryApplies 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 conclusion that three incidents remain open is stated in prose and repeated in the table.
match_detail_to_request
FailAdvisoryApplies 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 the incidents from the full 14-day period, but the delivered comparison stops after ten rows despite reporting roughly 43 incidents.
compress_summary
FailAdvisoryApplies when: Hark provides a summary.
Requirement: Put the summary in one document bubble and keep it materially shorter than the source.
The response is materially shorter than the source, but the summary is not delivered in one document bubble.
follow_summary_instructions
FailAdvisoryApplies 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 user specified affected products, locations, duration, and resolution as the summary focus. The delivered table omits most incidents and lacks a resolution field.
preserve_summary_skeleton
FailAdvisoryApplies 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 chronological incident list is truncated after ten entries and is not represented as short numbered lines in a document bubble.
use_summary_numbered_lines
FailAdvisoryApplies 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 a Markdown table rather than numbered lines inside a document bubble.
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 structured message contains a Markdown heading, table syntax, and inline Markdown links.
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 heading and Markdown table are combined in one untagged assistant message rather than isolated in a correctly tagged table bubble.
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 repeats the open incidents later shown in the table and exceeds the allowed short contextual sentence.
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 evidence shows generic assistant messages and no matching text or table bubble tags; the Markdown table is not represented as a table bubble.
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 visible heading and pipe rows, but it lacks a proper table-bubble title field and the required “Excel Spreadsheet” subtitle.
Pass
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 delivered claims and incident names are present in the draft or supporting status-page evidence.
lead_with_outcome
PassAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The first bubble immediately gives the incident count, date range, open incidents, and severity overview.
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 uses short, direct sentences without unnecessary elaboration.
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 specific incident names, products, places, dates, times, and durations where included.
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 response reports the findings directly and does not belabor basic concepts.
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, 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 wording is plain and uses exact service and incident terminology.
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.
No awkward self-wellbeing language or avoidable speaker-oriented possessive construction appears.
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.
The response uses two compact prose companions around one structured-content message, staying within the intended limit.
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 first prose bubble gives the overall incident overview, while the last gives the cross-incident pattern takeaway.
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.
Both prose bubbles are under 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.
The prose sentences are capitalized and end with periods.
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 incident.
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 displayed incident uses the same four fields: incident, product, duration, and status.
keep_table_columns_focused
PassAdvisoryApplies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
The four columns are directly related to the user's incident-summary request.
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 displayed incident destinations use the exact Cloudflare status URLs from the draft.
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 high-level result appears before the detailed table and pattern commentary.
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 further help is appended.
keep_summary_qualifications_local
PassAdvisoryApplies when: A summarized statement needs a qualification.
Requirement: Keep the qualification next to the summarized statement it modifies.
Qualifications such as “Almost all,” “small subset,” and product-specific scope are placed next to the claims they modify.
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 displayed table has only four focused columns and avoids an unnecessarily wide schema.
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 response includes the incident overview and a comparison table directly in the messages.
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 questions.
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 request is routine operational-status research rather than a serious, painful, or high-stakes personal subject.
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.
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 response does not point the user to another bubble, file, or saved location as a substitute for the result.
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.
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 incident report, not a set 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 shares more than one URL.
avoid_routine_tool_narration
Not applicableAdvisoryApplies 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 delivered response does not narrate web fetching, shell processing, sourcing, or verification.
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 contains no progress update.
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. The user supplied a specific summary focus, so this is not an unconstrained default-length summary case.
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 source is an incident collection rather than a work organized into sections or acts.
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 inability to complete the task.
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 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. The response does not report a Hark blocker or expose internal implementation details.
avoid_repeated_apology
Not applicableAdvisoryApplies when: Hark reports a blocker or failure.
Requirement: Avoid repeated apologies and generic failure language.
Not applicable. No blocker, failure message, or apology appears.
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 task had completed before the assistant response was delivered.
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 present in the draft or delivered 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 contains no email, message, template, letter, exact quote, or reusable document that needed byte-exact 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. No attachments ride with the reply.
limit_rich_bubbles
Not applicableAdvisoryApplies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
Not applicable. No correctly tagged rich bubble is delivered.