← Back to scenario detail
Response style analysis
Applied 46 · Passed 32 · Failed 14 · Not applicable 22
Rubric: services/agent/prompts/editor/v1.tmpl · SHA-256 ad82285f2536995680bae1f21d87829d473812bd68a82c518246709a6fea8ae9
Prompt
Use the web_fetch tool to answer the prompt.
What incidents has https://status.anthropic.com/ reported in the past 14 days? Summarize the affected products, duration, and resolution.
Hark's responses
10 incidents since Aug 28, one still open. The Cowork Windows issue is live, started Sep 10 and caused by a pending Microsoft fix.
### Status incidents, past 14 days · From Claude status page
| Date (UTC) | Incident | Affected | Duration | Resolution |
|---|---|---|---|---|
| Sep 10, ongoing | [Degraded functionality for Claude Cowork on Windows](https://status.anthropic.com/incidents/r1pqn1kb4hvk) | Claude Cowork on Windows (local commands; chat and file read/edit still work) | Open since Sep 10, 15:54 | Caused by a Sep 8 Windows update; Microsoft has a fix pending release, no workaround |
| Sep 11 | [Elevated errors for Claude Mythos 5.1 and Fable 5.1](https://status.anthropic.com/incidents/t33dncr5ydvl) | Mythos 5.1, Fable 5.1 | 13:57–14:20 (23 min) | Cause identified, fix deployed, resolved 14:37 |
| Sep 10 | [Elevated latency on the Claude API](https://status.anthropic.com/incidents/2pt83vlkk7x7) | Claude API for traffic entering via US Midwest | 21:43–23:24 (~1h 40m) | Mitigated |
| Sep 3 | [Elevated errors for multiple models](https://status.anthropic.com/incidents/461yvfrzpwtt) | Mythos/Fable 5.1, Mythos/Fable 5, Opus 5, Opus 4.8, Opus 4.6 | 13:26–16:16 (~2h 50m) | Fix deployed, impact ended 16:16 |
| Sep 3 | [Elevated errors for Claude Sonnet 5](https://status.anthropic.com/incidents/288w7p4hk1l1) | Sonnet 5 | 12:37–12:56 (~19 min) | Fix implemented |
| Sep 2 | [Elevated errors for Claude Sonnet 5](https://status.anthropic.com/incidents/ls6bn1x81m0w) | Sonnet 5 | 21:05–21:19 (14 min) | Resolved |
| Sep 1–2 | [Delays in credit purchases](https://status.anthropic.com/incidents/620swtqyn24k) | API billing, erroneous "credit balance is too low" errors | Credits bought 12:10–21:35 UTC Sep 1 | Fixed; new credits available as expected |
| Sep 1 | [Degraded performance on platform.claude.com and Claude for Microsoft Office 365](https://status.anthropic.com/incidents/3g3d55q6vk3h) | Console, docs.claude.com, Office 365 integration (API and inference unaffected) | 17:05–18:07 (~1h) | Success rates recovered |
| Sep 1 | [Degraded performance on Claude for Microsoft Office 365](https://status.anthropic.com/incidents/nr3h7bw8b3k3) | Claude for Microsoft Office 365 | 16:02–16:22 (20 min) | Resolved |
| Aug 31 | [Degraded performance on claude.ai and Claude Code](https://status.anthropic.com/incidents/r82kdk0m7vqh) | Claude in Slack, Claude Code on the web, Code Review | 16:55–19:16 (~2h 20m) | Resolved |
| Aug 31 | [Degraded performance on claude.ai](https://status.anthropic.com/incidents/9jrp5rtyzrf6) | claude.ai chats | 17:23–17:52 (~30 min) | Success rates returned to normal |
| Aug 28 | [Elevated errors on Claude Code and Claude Cowork](https://status.anthropic.com/incidents/vr9tpk8w7zr8) | Claude Cowork, Claude Code on the web | 17:22–20:21 (~3h) | Upstream cloud provider issue; mitigation applied, sessions retryable |
Most issues resolved within minutes to hours. API and inference mostly unaffected except for the Sep 10 latency spike and Sep 3 model errors.
Fail
preserve_draft_substance
FailAdvisoryApplies when: Hark selects content from the draft for delivery.
Requirement: Preserve the draft's substance. Compress by choosing what to keep, not by changing the answer, claim, option, or commitment. Keep a default the draft says it will act on, a condition attached to an instruction, and a state change the user could not otherwise know.
Most draft content is preserved, but the opening changes the cause from a Windows update to a pending Microsoft fix.
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 source says the Windows update caused the incident and Microsoft developed a pending fix. The response says the pending fix caused the incident, changing the factual relationship.
avoid_invented_content
FailAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Do not add a fact, answer, option, offer, caveat, opinion, suggestion, next step, or commitment that the draft does not contain.
The final generalization about API and inference being mostly unaffected was not present in the delivery draft, and the opening introduces an altered causal claim.
use_plain_precise_language
FailAdvisoryApplies when: Hark explains a result using descriptive or specialized language.
Requirement: Prefer plain and specific language. Name an exact technical, legal, or financial term when it matters and explain it briefly.
Most language is plain, but saying the live issue was caused by a pending Microsoft fix is technically imprecise and reverses the update/fix relationship.
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 opening repeats the open Cowork incident and its details from the table, while the closing repeats broad conclusions already represented by the rows.
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 companion messages exceed the 20-word limit, and there are two sentences before the table rather than at most one framing sentence.
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 open-incident conclusion is stated in the opening and again in the first table row, with another broad conclusion appended after the table.
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 a requested summary, but it is delivered as a table rather than the required 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 requested focus is covered, but the summary is not delivered in the required document-bubble form.
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.
No length or format was specified, but the response does not use the required compact document bubble.
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 dated incident structure is broadly retained, but it is not converted into 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 table rows rather than short numbered lines in a document 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 restates the first table row, and both companion messages exceed the permitted short contextual sentence length.
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 pipe rows and a title, but no visible Excel Spreadsheet subtitle.
Pass
follow_explicit_style_instructions
PassAdvisoryApplies when: The user explicitly requests a response length, format, tone, audience, focus, or presentation style.
Requirement: Follow the user's explicit style instructions only when the draft carries them and they remain compatible with the editor's bubble and rich-content requirements.
The response uses a concise comparison table covering affected products, duration, and resolution as requested.
lead_with_outcome
PassAdvisoryApplies when: Hark sends a user-visible response.
Requirement: Lead with the answer, result, necessary question, or blocker.
The first message immediately states the incident count and current open incident.
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 companions use short, direct sentences.
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 table gives specific dates, products, UTC times, durations, and resolutions.
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 presents the findings directly without explaining basic concepts 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 with the result rather than praise, acknowledgment, or a preview.
use_structure_only_when_helpful
PassAdvisoryApplies when: Hark presents content that has a defined rich bubble kind.
Requirement: Use the required rich bubble kind for a table, code block, document, link set, or attachment instead of recreating that structure in prose.
The comparable incidents are presented in a table rather than recreated as unstructured prose.
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-description or clearly inappropriate possessive construction appears in the response.
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 reply uses two prose bubbles around one rich table, within the preferred 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 opening focuses on the incident count and open incident, while the closing gives a separate overall 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 remain below 40 words.
punctuate_sentences
PassAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Use proper capitalization and end every sentence with a period or question mark.
Every prose sentence is capitalized and ends with a period.
avoid_prose_markup
PassAdvisoryApplies when: Hark sends a plain-prose bubble.
Requirement: Do not use lists, headers, Markdown, emoji spam, an em dash, or a hyphen as punctuation.
The plain-prose bubbles contain no lists, headings, Markdown, emoji, or dash punctuation.
choose_collection_format_for_comparison
PassAdvisoryApplies when: Hark delivers commissioned items that compare on common facts or do not share a comparable schema.
Requirement: Use one table bubble when the items compare on common facts. Use one document bubble when they do not.
The incidents share common fields and are presented in one comparison table.
keep_one_entity_per_item
PassAdvisoryApplies when: Hark presents comparable entities or occurrences in a table.
Requirement: Put one comparable entity or occurrence in each row.
Each table row represents one 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 incident uses the same Date, Incident, Affected, Duration, and Resolution fields.
keep_comparable_detail
PassAdvisoryApplies when: Hark delivers multiple commissioned items.
Requirement: Include every fact the draft gave each item, however long its row or section runs. Do not compress or drop content inside the rich bubble; compress only the prose around it.
The delivered table retains the incident-specific facts supplied by the draft for every row.
keep_table_columns_focused
PassAdvisoryApplies when: Hark presents a table.
Requirement: Keep columns focused on the user's decision or question.
The five columns directly support identifying incidents and comparing affected products, duration, and resolution.
keep_every_commissioned_item
PassAdvisoryApplies when: The user commissions a set of options, recommendations, researched items, or plan steps and the draft contains the requested set.
Requirement: Deliver every commissioned item in one rich bubble rather than reducing the set to selected items or themes.
All incident rows contained in the draft are delivered in one table rather than reduced to selected examples.
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 incident destinations match the full URLs supplied in the draft and are not shortened or duplicated elsewhere.
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 response gives the overall result before the detailed incident table.
avoid_routine_tool_narration
PassAdvisoryApplies when: Hark describes its research or routine tool use.
Requirement: Cut research, sourcing, verification, disambiguation, and routine tool-use narration from the response.
The response does not narrate fetching, researching, checking, or verifying the status page.
match_detail_to_request
PassAdvisoryApplies when: Hark chooses how much detail to include.
Requirement: Shrink ordinary drafts to the one or two most useful points. Keep every requested item only when the user commissioned a set of work.
Because the user commissioned the full incident set, retaining one row per incident with the requested fields is appropriate.
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.
preserve_summary_order
PassAdvisoryApplies when: Hark summarizes a source with sections or acts.
Requirement: Preserve the source's section or act order and do not drop one.
The live incident appears first, followed by past incidents in the same reverse-chronological order as the source.
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 unaffected services, approximate durations, and remaining functionality appear beside the claims they modify.
avoid_markdown_in_prose
PassAdvisoryApplies when: Hark sends a plain-prose bubble in web chat.
Requirement: Do not use Markdown in prose bubbles. Use the matching rich bubble kind when content needs structure.
The plain-prose bubbles contain no Markdown; the structured Markdown representation is isolated to the table message.
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.
Although detailed, the table uses only focused columns needed for the requested comparison and avoids extraneous fields.
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 full incident result is included directly in the response.
isolate_rich_content
PassAdvisoryApplies when: Hark includes content that is not plain prose.
Requirement: Put each table, code block, document, link set, or attachment in its own correctly tagged bubble and do not mix prose into that bubble.
The table is placed in its own message, separate from the prose companions.
tag_every_bubble
PassAdvisoryApplies when: Hark sends any bubble.
Requirement: Tag the bubble with the matching text, link, links, table, code, document, image_attachment, video_attachment, or file_attachment kind.
The observable delivery separates two text messages from the structured table message, consistent with matching bubble kinds.
limit_rich_bubbles
PassAdvisoryApplies when: Hark sends rich content.
Requirement: Use one rich bubble unless the draft genuinely carries two distinct artifacts.
The response uses one rich table bubble.
Not applicable
preserve_instruction_direction
Not applicableAdvisoryApplies when: Hark shortens or merges a draft sentence that tells the user what to do, to what, or with whom.
Requirement: Keep the sentence's verb, object, and addressee. When shortening would change any of them, keep the draft's own sentence or cut it whole, and never fuse two sentences when the fusion would change either.
Not applicable. The 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 not a serious, painful, or personally high-stakes 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 using forbidden social phrasing.
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 message or saved location instead of delivering 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. This is an incident report, not a table of options or recommendations.
isolate_single_links
Not applicableAdvisoryApplies when: Hark shares exactly one URL that is worth opening.
Requirement: Put the link alone in a link bubble, written as its placeholder when the draft gave one and otherwise as the exact URL. Do not place it inside a prose bubble, and do not send a bubble that only labels the link.
Not applicable. The response shares multiple incident destinations inside a table rather than exactly one standalone URL.
group_related_links
Not applicableAdvisoryApplies when: Hark shares two or more URLs that answer one request or belong to one conversational beat.
Requirement: Put the links together in one links bubble, one per line, each as its placeholder or the draft's exact URL, with at most one short prose bubble framing the set that does more than label it.
Not applicable. The URLs function as row-level destinations in a comparison table, not as a standalone set of links answering one beat.
avoid_request_restatement
Not applicableAdvisoryApplies 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.
Not applicable. The table title labels the result without unnecessarily restating the full request.
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. Hark does not report being unable 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. There is no task blocker or partial-completion report.
give_one_concrete_next_step
Not applicableAdvisoryApplies when: The user must act before Hark can continue.
Requirement: State one concrete next step only when the draft offers it.
Not applicable. The user does not need to act before Hark can continue.
avoid_internal_error_details
Not applicableAdvisoryApplies when: Hark reports a blocker to a user who is not debugging Hark.
Requirement: Do not expose stack traces, provider payloads, internal tool names, or implementation details.
Not applicable. No Hark blocker or internal error is reported.
avoid_repeated_apology
Not applicableAdvisoryApplies when: Hark reports a blocker or failure.
Requirement: Avoid repeated apologies and generic failure language.
Not applicable. No blocker, failure language, 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 input states that the fetch completed and no work remained running.
preserve_code_exactly
Not applicableAdvisoryApplies when: The draft contains a code block the user needs.
Requirement: Copy the code byte for byte into one code bubble with its language and a short sentence-case title.
Not applicable. No needed code block appears in the draft.
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, template, exact quotation, or other document meant for reuse.
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 attachment accompanies the reply.