← Back to scenario detail
Response style analysis
Applied 48 · Passed 21 · Failed 27 · Not applicable 20
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
43 incidents in 14 days. Three still open: Tunnel (since Sep 11), Workers Cron (Sep 9), and WARP geolocation (Aug 27). All say the fix is being implemented.
### Cloudflare incidents, Aug 28 Sep 11 · Status page summary
| Incident | Product / Location | Duration | Resolution |
|---|---|---|---|
| [Cloudflare Tunnel availability issues](https://www.cloudflarestatus.com/incidents/k7l4hzmthl3k) | Tunnel | Sep 11, 2:55 PM | Cause identified, fix being implemented |
| [Workers Cron Triggers degraded](https://www.cloudflarestatus.com/incidents/sjs8s0q2x4hw) | Workers | Sep 9, 12:17 PM | Cause identified, fix being implemented |
| [Incorrect geo location for some WARP users](https://www.cloudflarestatus.com/incidents/9g65dxfbcjln) | WARP | Aug 27, 11:46 AM | Cause identified, fix being implemented |
| [Network route leak, Palmas Brazil](https://www.cloudflarestatus.com/incidents/x) | Network, PMW | Sep 1, 2:47
3:05 PM (18 min) | Routes leaked and misdirected traffic; mitigated |
| [HTTP/3 issue on R2 custom domains](https://www.cloudflarestatus.com/incidents/x) | R2, Firefox globally | Aug 31
Sep 3 (3 days) | Bad HTTP/3 advertisement; fixed |
| [Turnstile and Challenge Pages degraded for AS15924](https://www.cloudflarestatus.com/incidents/x) | Turnstile, Challenge Pages | Aug 30
Sep 4 (5 days) | Intermittent verification failures; resolved |
| [DNS update delays](https://www.cloudflarestatus.com/incidents/nhfcmzd1pv4p) | DNS Updates, global | Sep 10, 6:58 AM
3:22 PM (8.5 hr) | Record propagation delays; fixed |
| [Increased HTTP 5xx errors, Singapore](https://www.cloudflarestatus.com/incidents/x) | Network, SIN | Aug 28, 10:36 AM
5:43 PM (7 hr) | Fix deployed |
| [SSL provisioning delays](https://www.cloudflarestatus.com/incidents/3r3qcgbb0714) | SSL Certs (Let's Encrypt) | Sep 10, 7:20
9:05 PM | Upstream Let's Encrypt incident; backlog cleared |
| [Workers VPC hostname route resolution](https://www.cloudflarestatus.com/incidents/9mcdtk1lphgl) | Workers VPC | Sep 11, 06:22
09:38 UTC | Connection and routing errors; fully resolved |
| [Workers AI errors](https://www.cloudflarestatus.com/incidents/jsvvrtk5hvym) | Workers AI | Sep 9, 7:25 AM
1:09 PM | Fix implemented |
| [Taiwan datacenter performance](https://www.cloudflarestatus.com/incidents/2njywrxj8qjf) | Network, TPE | Sep 11, 12:35
3:03 PM | Resolved |
| [Durable Objects errors, Western NA](https://www.cloudflarestatus.com/incidents/x) | Durable Objects | Sep 2, 7:47
8:51 AM | Fibre cut caused routing capacity loss; mitigated |
| [Browser Isolation session failures](https://www.cloudflarestatus.com/incidents/x) | Browser Isolation, Gateway | Sep 7, 7:25 AM
12:14 PM | White screens; fix deployed |
| [TURN service degradation](https://www.cloudflarestatus.com/incidents/x) | Realtime TURN | Aug 22
Sep 7 | Traffic relayed over TCP instead of UDP; fixed |
Most of the other 28 incidents were narrow: R2 errors in North America, Cache Reserve in Paris, cache purge errors, Workers glitches in Narita, edge problems in various cities, and dashboard-only bugs. Nearly all resolved within hours.
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 a summary covering affected products, locations, duration, and resolution. The response gives full rows for only 15 incidents and groups the remaining 28 into a vague paragraph.
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 response drops a material condition from the TURN resolution. The draft said the fix covered new connections while existing connections would continue over TCP until restarted; the delivered row says only that it was fixed.
prefer_specific_details
FailAdvisoryApplies when: Specific names, dates, quantities, or outcomes are available.
Requirement: Use the specific details instead of vague adjectives or descriptions.
The final paragraph replaces available incident names, locations, durations, and resolutions with vague phrases such as “edge problems in various cities” and “dashboard-only bugs.”
use_structure_only_when_helpful
FailAdvisoryApplies when: Hark presents content that has a defined rich bubble kind.
Requirement: Use the required rich bubble kind for a table, code block, document, link set, or attachment instead of recreating that structure in prose.
The comparison is rendered as Markdown text instead of 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 response uses a Markdown heading, Markdown table syntax, and inline Markdown links in an untagged 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 and their fix status are stated in the opening prose and then repeated in 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.
The incidents share a common comparison schema, but only selected incidents appear in the table. The remaining commissioned incidents are collapsed into prose rather than included in one complete table bubble.
use_consistent_collection_schema
FailAdvisoryApplies when: Hark presents multiple comparable items.
Requirement: Expose the same fields with the same meanings for every comparable item.
The displayed rows use a consistent schema, but the other 28 comparable incidents are grouped in prose without the same product, location, duration, and resolution fields.
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 response omits incident-level facts for 28 incidents and removes qualifications from some displayed incidents, including the TURN connection caveat.
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 user commissioned the incidents from the full period. The response reports 43 incidents but provides rows for only 15 and reduces the other 28 to themes.
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.
Both prose companions exceed 20 words. The opening is about 27 words, and the closing is about 31 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 incident URLs are embedded in Markdown table cells rather than grouped in a correctly tagged links bubble.
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 the three open incidents have identified causes and fixes being implemented is given in the opening 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.
Because the user commissioned a complete period-based incident set, every incident should have been retained. The response instead gives detail for only a selected subset.
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 summary is split across three assistant messages and presented as prose plus a Markdown table instead of 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.
Although the table has the requested fields, it does not apply them to all reported incidents and therefore does not fully follow the requested summary focus.
use_default_summary_length
FailAdvisoryApplies 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.
The user did not specify a length or format. The response should therefore use one compact document bubble, but it uses three messages and a substantial Markdown table.
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 is an ordered incident collection, but the response selects 15 incidents, collapses 28 into themes, and does not use short numbered lines.
preserve_summary_order
FailAdvisoryApplies when: Hark summarizes a source with sections or acts.
Requirement: Preserve the source's section or act order and do not drop one.
The source’s reverse-chronological incident order is not preserved across the selected resolved incidents, and many incidents are omitted entirely.
keep_summary_qualifications_local
FailAdvisoryApplies when: A summarized statement needs a qualification.
Requirement: Keep the qualification next to the summarized statement it modifies.
The TURN row says the service was fixed without keeping the qualification that only new connections were fixed immediately and existing connections remained on TCP until restarted.
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 and prose rather than short 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 response visibly uses Markdown heading, table, and link syntax in an assistant message rather than matching rich bubbles.
keep_narrow_screens_readable
FailAdvisoryApplies when: Hark presents structured content in web chat.
Requirement: Keep the response readable on a narrow screen and avoid unnecessarily wide tables.
The four-column table contains long incident names, locations, durations, and resolutions. Its timestamps visibly wrap onto separate lines, making it difficult to scan on a narrow screen.
isolate_rich_content
FailAdvisoryApplies when: Hark includes content that is not plain prose.
Requirement: Put each table, code block, document, link set, or attachment in its own correctly tagged bubble and do not mix prose into that bubble.
The table is not isolated in a correctly tagged table bubble. Its title and Markdown table syntax appear together in one ordinary assistant message.
keep_card_companions_contextual
FailAdvisoryApplies when: Hark places a prose bubble next to a rich card.
Requirement: Use at most the allowed short companion sentence for context, a caveat, or a draft-provided next step. Do not restate, summarize, caption, or narrate the card.
The opening repeats the first three rows of the comparison, and the closing summarizes and substitutes for omitted rows. Both also exceed the allowed brief companion length.
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 observed assistant messages have no matching text, table, or document bubble tags, despite containing prose and structured table content.
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 attempted table has pipe rows and a heading, but it lacks the required Excel Spreadsheet subtitle and is not delivered as a table bubble.
Pass
preserve_factual_spans
PassAdvisoryApplies when: Hark includes a name, place, time, number, URL, or factual claim from the draft.
Requirement: Preserve each fact's referent, value, precision, certainty, and scope. Rephrasing is allowed when all five stay unchanged. Keep URLs, identifiers, exact quotes, code, and documents byte-exact.
Names, dates, durations, and URLs selected from the draft are reproduced without materially changing their stated values or scope.
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 descriptions are present in the draft. No new suggestion, commitment, or option is added.
lead_with_outcome
PassAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The response opens with the incident count and the three incidents it identifies as open.
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. The longer body is organized as table cells rather than long prose sentences.
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 explains the incidents without belaboring elementary points or talking down to the user.
avoid_throat_clearing
PassAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Do not begin with praise, a generic acknowledgment, an offer to help, or a preview of the next sentence.
The response begins immediately with the incident count and open-incident outcome.
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 table generally uses plain, specific incident and product terminology without unnecessary jargon.
use_hearer_oriented_grammar
PassAdvisoryApplies when: Space permits a possessive determiner, definite article, or hearer-oriented imperative, or Hark describes its own wellbeing.
Requirement: Prefer forms such as your dog, the White Sox, and try tilapia. Say I'm doing well or I'm good, never I'm doing good.
The response contains no problematic self-wellbeing phrase or user-directed possessive construction.
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 are two prose bubbles around the structured comparison, which stays within the three-bubble 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 headline status, and the last gives a single catch-all characterization of omitted incidents.
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.
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 response does not point the user above, below, or to a saved workspace location instead of giving content.
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 displayed table row represents one incident.
keep_table_columns_focused
PassAdvisoryApplies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
The columns directly address the requested incident, product or location, duration, and resolution fields.
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 URLs carried from the draft are reproduced exactly, including the draft’s incident “x” destinations.
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 incident count and open-incident status appear before the detailed comparison and broader background.
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 brief table title functions as necessary context for the structured content rather than a redundant prose restatement.
avoid_generic_help_offers
PassAdvisoryApplies 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.
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.
A usable summary result is included directly in the assistant messages rather than only described as existing elsewhere.
limit_rich_bubbles
PassAdvisoryApplies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
Only one structured comparison artifact is attempted in the delivered assistant 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 concerns routine service-status reporting rather than a serious or painful 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, personal preference, or opinion.
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 reports incidents rather than 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 response does not narrate its web fetching, parsing, or verification work.
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 response is a completed result, not a progress update.
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 response does not require user action before work 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 reports no Hark blocker or internal failure.
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 available tool work completed before the response was sent.
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 that the delivered response must copy byte-for-byte.
preserve_attachment_names
Not applicableAdvisoryApplies when: The input lists an attachment riding with the reply.
Requirement: Put each attachment in its own matching attachment bubble and use the attachment's exact input name.
Not applicable. The user input does not list an attachment riding with the reply.