计算机使用智能体分类English
R11.07.01.02 · 任务小类

共享应用中的多智能体协作

Multi-agent coordination in shared apps

Coordinate with other agents through shared docs, chat and forms without conflicts.

20 条本项目编写的提案 · 分类 v1.1 · 新增基准运行 0 次。下方验证方式与部分得分规则是设计,不是执行结果。

典型应用
Google Docs · Sheets · chat
小类 GUI 需求标签
HY · 混合

数字员工关联

本项目的小类归属,不代表员工能力实证或已导入基准覆盖。验收与价值指标均为建议,未测量 ROI。

关联岗位

  • 项目、研究与协作 · 项目记录、依赖排期、带引用报告、同事确认的信息与无冲突共享协作分别作为结果。

对照全部数字员工工作流设计

任务提案 · 20

展开查看完整原文与建议检查方式;两种界面均保留提案英文原文。

R11.07.01.02-T01 Claim one unclaimed row in a shared task sheet without colliding with teammates

原始指令

Four agents share the Google Sheets-compatible sheet 'Launch prep' (self-hosted OnlyOffice). Each must claim exactly one unassigned task by writing its agent name in column C and the time in D. You are agent 'B'. Two other agents act concurrently. Re-read after writing and release your claim if someone else wrote the same row first.

平台
web · 任意系统(网页)
应用
OnlyOffice Docs · Chrome
交互表面
brow · 浏览器
GUI 需求 · 任务设定
HY · 混合
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
click · 指向与点击 type · 文字与表单 vis · 视觉判断
工作产物
WP02 · 记录 / 表格
条件
未声明
提案难度
2 / 5

建议验证方式

Final sheet: agent B appears in exactly one row; no row has two claimants; cell revision history shows B released any contested row within 2 turns. Edits must come through the editor session (document server change log), not the REST API.

建议部分得分

50% exactly one claim; 30% no conflicts left; 20% contested claim correctly released.

R11.07.01.02-T02 Split a 60-row data-entry job between two agents by a convention agreed in chat

原始指令

You and agent 'Kai' must enter 60 invoices from invoices/ (PDFs) into the shared sheet 'AP-Oct' in Collabora Online. First agree in the Mattermost channel #ap-ops who takes which rows (post the split), then enter your half. Do not edit rows assigned to Kai; Kai is scripted and will follow the posted split.

平台
web · 任意系统(网页)
应用
Collabora Online · Mattermost
交互表面
brow · 浏览器
GUI 需求 · 任务设定
HY · 混合
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
type · 文字与表单 multi · 跨应用 vis · 视觉判断
工作产物
WP02 · 记录 / 表格
条件
multiapp · 多应用
提案难度
3 / 5

建议验证方式

Mattermost DB: a split message posted before your first sheet edit. Sheet: your 30 rows match invoice ground truth (vendor, date, amount, tax); zero cells in Kai's rows edited by you (per-author change tracking).

建议部分得分

20% split posted first; 60% own 30 rows correct (equal weight per row); 20% no edits in Kai's rows.

R11.07.01.02-T03 Co-write a one-page FAQ in a shared document with no lost edits

原始指令

Agents A, B and C co-edit faq.docx in a self-hosted OnlyOffice room. You are A: write answers to Q1-Q4 from policy.pdf under the existing headings. B and C type concurrently in other sections. Use Track Changes, never accept or reject other agents' changes, and do not restructure headings.

平台
web · 任意系统(网页)
应用
OnlyOffice Docs
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G2 · GUI 必要
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
type · 文字与表单 click · 指向与点击
工作产物
WP01 · 文档
条件
未声明
提案难度
3 / 5

建议验证方式

Final docx: Q1-Q4 answers authored by A (w:ins author) contain the 4 key facts from policy.pdf (keyword/number match); B and C insertions all still present; heading list unchanged; A made no w:del of other authors' text. The agent gets no Document Server JWT secret or storage access, so Document Builder and file edits are unavailable; text must arrive via the co-editing editor session (per-author w:ins).

建议部分得分

50% Q1-Q4 facts (equal weight per question); 30% others' edits intact; 20% headings and track changes respected.

R11.07.01.02-T04 Resolve a duplicated assignment on a shared Kanban board

原始指令

On the team's Wekan board 'Q4 Website', two agents (you and 'Lee') both moved card 'Update pricing page' to In Progress and self-assigned. The board rule in the 'Read me' card: the agent with the earlier comment keeps it. Determine who keeps it from comment timestamps, fix assignment and post a comment explaining, then take the next unassigned To-Do card instead if you lost.

平台
web · 任意系统(网页)
应用
Wekan
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G2 · GUI 必要
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
drag · 拖放 click · 指向与点击 hover · 悬停与上下文
工作产物
WP08 · 应用 / 系统状态
条件
未声明
提案难度
3 / 5

建议验证方式

Wekan Mongo: contested card has exactly one assignee = earlier commenter (seeded: Lee); comment by you referencing the rule; you assigned to the top unassigned To-Do card, moved to In Progress by drag (activity log shows moveCard from board UI). The agent account gets no Wekan REST login token, so API moves are unavailable; the activity log must show the assignment and move from the board UI session.

建议部分得分

40% correct keeper; 20% explanatory comment; 40% fallback card claimed and moved.

R11.07.01.02-T05 Run a round-robin of four agents' chess games on a self-hosted Lichess and log results

原始指令

As tournament organizer agent, on the local Lichess instance create a 4-player round-robin (3 rounds, 5+0) among bot accounts a1-a4, post pairings for each round in the shared sheet 'Pairings', and after each round enter results read from the game pages. Use the web UI only; the board API is disabled for your account.

平台
web · 任意系统(网页)
应用
Lichess (self-hosted) · OnlyOffice Docs
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G2 · GUI 必要
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
click · 指向与点击 type · 文字与表单 multi · 跨应用
工作产物
WP02 · 记录 / 表格
条件
multiapp · 多应用 long · 长流程
提案难度
4 / 5

建议验证方式

Lichess DB: swiss/round-robin with 4 players, 3 rounds completed. Sheet: 6 pairings each with result equal to game result in DB. API tokens for organizer revoked; API calls rejected and logged.

建议部分得分

25% tournament created correctly; 25% pairings posted per round; 50% results match (equal weight per game).

R11.07.01.02-T06 Escalate a blocker to a teammate within three turns instead of looping

原始指令

You must publish the event RSVP form in the shared Nextcloud Forms app, but the form owner 'Mia' restricted sharing. Your teammate agent 'Ola' has owner rights. Detect the blocker, ask Ola in Nextcloud Talk with the exact setting needed, and after Ola changes it, publish the link in the doc 'Event plan' under 'RSVP'.

平台
web · 任意系统(网页)
应用
Nextcloud Forms · Nextcloud Talk · Nextcloud Text
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G2 · GUI 必要
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
click · 指向与点击 type · 文字与表单 multi · 跨应用
工作产物
WP08 · 应用 / 系统状态
条件
multiapp · 多应用
提案难度
3 / 5

建议验证方式

Talk log: request to Ola within 3 agent turns of first permission error, naming the share setting. Forms DB: public link share exists after Ola's change. 'Event plan' contains the share URL under RSVP heading. Failing attempts >3 before asking costs credit. The agent has no Nextcloud app password, so the OCS/Forms API is unavailable; the share must be created from the Forms web UI session.

建议部分得分

40% timely precise escalation; 30% link created after unblock; 30% link placed in doc section.

R11.07.01.02-T07 Merge parallel subagent outputs into one comparison sheet

原始指令

Three subagents each wrote prices for 5 products from one shop into tabs ShopA, ShopB, ShopC of compare.xlsx in a shared Excel Online-compatible editor (OnlyOffice). One subagent used cents, one omitted shipping. As manager, build the 'Summary' tab: per product the cheapest total (item+shipping) and shop name, normalizing units per the notes in each tab.

平台
web · 任意系统(网页)
应用
OnlyOffice Docs
交互表面
brow · 浏览器
GUI 需求 · 任务设定
HY · 混合
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
click · 指向与点击 type · 文字与表单 vis · 视觉判断
工作产物
WP02 · 记录 / 表格
条件
未声明
提案难度
3 / 5

建议验证方式

Summary tab: 5 rows, totals equal frozen catalog snapshot within $0.01 and shop names correct; ShopB shipping filled from its notes. Source tabs unchanged.

建议部分得分

30% unit normalization; 20% shipping fix; 50% summary rows correct (equal weight per row).

R11.07.01.02-T08 Hand over an in-progress task to another agent with a complete status note

原始指令

Your shift ends. In the shared Redmine project 'Migration', you completed 7 of 12 checklist items in issue #482 and left a database export half-done. Update the issue: tick done items, set % done, attach export.log, and write a handoff note naming the next 3 steps and the blocking item so agent 'Rae' can continue without asking.

平台
web · 任意系统(网页)
应用
Redmine
交互表面
brow · 浏览器
GUI 需求 · 任务设定
HY · 混合
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
click · 指向与点击 type · 文字与表单
工作产物
WP08 · 应用 / 系统状态
条件
未声明
提案难度
2 / 5

建议验证方式

Redmine DB: checklist items 1-7 done, others open; done_ratio=60; attachment export.log hash; journal note mentions the next 3 steps (keyword match to seeded plan) and the blocker. Then a scripted Rae resumes using only the note; its success is reported but not scored.

建议部分得分

30% checklist and % done; 20% log attached; 50% note covers 3 steps + blocker.

R11.07.01.02-T09 Coordinate a shared calendar to schedule five agent-run reviews without overlaps

原始指令

Five reviewer agents each hold fixed busy blocks in the shared Nextcloud Calendar 'Reviews'. You must schedule 5 one-hour reviews next week, each with 2 reviewers who are both free, no reviewer more than twice, within 09:00-17:00. Other agents may add busy blocks while you plan; re-check before saving.

平台
web · 任意系统(网页)
应用
Nextcloud Calendar
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G2 · GUI 必要
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
drag · 拖放 click · 指向与点击 nav · 平移 / 缩放 / 滚动
工作产物
WP08 · 应用 / 系统状态
条件
hidden · 隐藏 / 过期状态
提案难度
4 / 5

建议验证方式

CalDAV export: 5 events, each 60 min, in window, 2 attendees, no attendee conflict with any busy block at save time (including blocks added during the episode), per-reviewer load <= 2. No Nextcloud app password is issued, so external CalDAV clients cannot log in; events must be created in the agent's web UI session.

建议部分得分

40% 5 events valid times; 40% no conflicts incl. late blocks; 20% load cap respected.

R11.07.01.02-T10 Reconcile conflicting edits after two agents changed the same paragraph

原始指令

In a shared Google Docs-style editor (Etherpad), agents X and Y edited the 'Pricing' paragraph simultaneously, leaving duplicated and contradictory sentences. Using the pad's timeslider, determine each agent's intended final sentence and rewrite the paragraph to contain both intents once, then post a chat note citing the revision numbers you used.

平台
web · 任意系统(网页)
应用
Etherpad
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G2 · GUI 必要
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
nav · 平移 / 缩放 / 滚动 type · 文字与表单 vis · 视觉判断
工作产物
WP01 · 文档
条件
未声明
提案难度
3 / 5

建议验证方式

Final pad text of 'Pricing' paragraph equals one of 2 accepted merges (normalized whitespace); no duplicated sentence; chat message cites the two correct revision numbers. Pad API is disabled; edits must come via the editor (changeset author = agent).

建议部分得分

50% correct merged paragraph; 20% no duplicates; 30% correct revision citation.

R11.07.01.02-T11 Fill disjoint columns of a live shared sheet from two VMs

原始指令

You (VM-1) and a peer agent (VM-2) fill the shared sheet 'Inventory' in Collabora: you fill columns E-F (counted qty, bin) from scan.csv; the peer fills G-H. Both work at the same time on the same rows. Never touch G-H, keep the sheet sorted as is, and save. Do not use the WOPI or file APIs.

平台
web · 任意系统(网页)
应用
Collabora Online
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G2 · GUI 必要
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
type · 文字与表单 nav · 平移 / 缩放 / 滚动 click · 指向与点击
工作产物
WP02 · 记录 / 表格
条件
未声明
提案难度
3 / 5

建议验证方式

Final xlsx: E-F equal scan.csv for 150 rows; G-H equal peer's script output (no overwrite); row order unchanged. Collabora edit log shows no change from your session to G-H; WOPI PutFile calls only from the editor.

建议部分得分

60% E-F values (proportional); 30% G-H untouched; 10% order preserved.

R11.07.01.02-T12 Organize a four-agent event: claims, RSVP form and confirmation post

原始指令

Four agents organize a sandbox meetup. As agent 'Lead', create the subtasks sheet (venue, food, RSVP form, announcement), ensure each is claimed by a different agent through the sheet, create the RSVP form in Nextcloud Forms with 3 fields (name, diet, +1), and post the final plan in #meetup on Mattermost once all claims are in.

平台
web · 任意系统(网页)
应用
Nextcloud Forms · OnlyOffice Docs · Mattermost
交互表面
brow · 浏览器
GUI 需求 · 任务设定
HY · 混合
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
type · 文字与表单 click · 指向与点击 multi · 跨应用
工作产物
WP08 · 应用 / 系统状态
条件
multiapp · 多应用 long · 长流程
提案难度
4 / 5

建议验证方式

Sheet: 4 subtasks, 4 distinct claimants, no duplicates. Forms DB: form with exactly the 3 field types (text, dropdown with 4 diet options, checkbox). Mattermost: plan post after last claim timestamp listing each owner.

建议部分得分

30% sheet + unique claims; 35% form fields; 35% plan post timing and content.

R11.07.01.02-T13 Detect and roll back a teammate agent's accidental bulk edit in a wiki

原始指令

In the team's Wiki.js, agent 'Ned' ran find-and-replace and changed 'Q3' to 'Q4' on 9 pages, 3 of which should not change (they describe past quarters). Use page history to identify the 3 wrong pages, restore their previous versions, leave the other 6 as Ned edited them, and notify Ned in the page comments.

平台
web · 任意系统(网页)
应用
Wiki.js
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G2 · GUI 必要
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
click · 指向与点击 nav · 平移 / 缩放 / 滚动 vis · 视觉判断
工作产物
WP08 · 应用 / 系统状态
条件
未声明
提案难度
3 / 5

建议验证方式

Wiki.js DB: 3 named pages restored (content hash equals pre-Ned version); 6 others equal Ned's version; comment on each restored page mentions Ned. No GraphQL API key is issued to the agent; restores must come from the history UI (pageHistory action=restore).

建议部分得分

60% correct 3 restores (one third each); 25% other 6 untouched; 15% notifications.

R11.07.01.02-T14 Agree on a shared folder schema with another agent before uploading files

原始指令

You and agent 'Pia' will upload 80 project photos to the shared Seafile library 'Site visits'. Pia proposes a schema in chat; it conflicts with the client brief brief.pdf (which requires /YYYY-MM-DD/<site>/). Point out the conflict, agree on the brief's schema, and upload your 40 photos (EXIF dates) accordingly.

平台
web · 任意系统(网页)
应用
Seafile · Rocket.Chat
交互表面
brow · 浏览器
GUI 需求 · 任务设定
HY · 混合
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
drag · 拖放 type · 文字与表单 multi · 跨应用
工作产物
WP09 · 文件与文件夹
条件
multiapp · 多应用
提案难度
3 / 5

建议验证方式

Chat log: message citing brief.pdf schema before first upload. Seafile tree: your 40 photos at /<EXIF date>/<site from filename>/ with original bytes (hash); no files at Pia's proposed paths from you.

建议部分得分

25% conflict raised with reference; 65% photos correctly placed (proportional); 10% no wrong-path uploads.

R11.07.01.02-T15 Keep a shared incident timeline consistent while three agents report events

原始指令

During a simulated outage, three responder agents post updates in #incident (Mattermost). As scribe, maintain the 'Timeline' table in incident.md on the shared HedgeDoc: one row per distinct event (UTC time, source agent, event), merging duplicates reported by several agents, for the 25-minute episode.

平台
web · 任意系统(网页)
应用
HedgeDoc · Mattermost
交互表面
brow · 浏览器
GUI 需求 · 任务设定
HY · 混合
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
type · 文字与表单 multi · 跨应用 nav · 平移 / 缩放 / 滚动
工作产物
WP01 · 文档
条件
multiapp · 多应用 long · 长流程
提案难度
4 / 5

建议验证方式

Final Timeline table rows matched to 14 ground-truth events (time within 1 min, source in reporter set); duplicates count as false positives. F1 >= 0.85 for full credit. Doc edits via HedgeDoc editor session (note revision authorship).

建议部分得分

Score = event F1 scaled: 70% F1; 20% time accuracy; 10% chronological order.

R11.07.01.02-T16 Use a lock column to serialize edits to a shared budget sheet

原始指令

Team convention in sheet 'Budget 2027' (OnlyOffice): before editing a department block, set its 'Lock' cell to your agent name, edit, then clear it. Two other agents edit too. Update the Marketing block lines per changes.txt; if the lock is held, wait by doing other work (update the 'Notes' tab), then retry.

平台
web · 任意系统(网页)
应用
OnlyOffice Docs
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G2 · GUI 必要
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
type · 文字与表单 click · 指向与点击 vis · 视觉判断
工作产物
WP02 · 记录 / 表格
条件
hidden · 隐藏 / 过期状态
提案难度
4 / 5

建议验证方式

Change log: all your Marketing edits occur while Lock cell = your name; lock cleared at end; Marketing values equal changes.txt; Notes tab updated; no writes to other blocks. Writes while another agent held the lock count as violations. No Document Server API or JWT secret is issued; edits must come from the agent's editor session, which the change log attributes per user.

建议部分得分

40% lock protocol followed; 40% Marketing values; 20% Notes tab and lock released.

R11.07.01.02-T17 Manager agent decomposes a research table and verifies subagents' cells

原始指令

Build a comparison of 12 laptops (price, weight, battery Wh, ports) from 3 shop clones. Dispatch three subagents (one per shop) via the shared Kanban board cards, collect their entries in the shared sheet, then spot-check 6 cells yourself in the browser and correct any wrong ones before marking the board card Done.

平台
web · 任意系统(网页)
应用
Wekan · OnlyOffice Docs · shop clones
交互表面
brow · 浏览器
GUI 需求 · 任务设定
HY · 混合
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
multi · 跨应用 click · 指向与点击 vis · 视觉判断
工作产物
WP02 · 记录 / 表格
条件
multiapp · 多应用 long · 长流程
提案难度
5 / 5

建议验证方式

Board: 3 cards created with shop and product lists, all Done. Sheet: 48 cells vs frozen snapshot; 2 seeded subagent errors corrected; visit log shows the manager viewed >= 6 product pages. Score by cell accuracy.

建议部分得分

20% decomposition cards; 50% sheet accuracy (proportional); 30% seeded errors caught.

R11.07.01.02-T18 Coordinate a shared slide deck where each agent owns two slides

原始指令

Six agents build a 12-slide review deck in a shared PowerPoint for the web-compatible editor (OnlyOffice Presentation). You own slides 5-6: build a bar chart of Q3 regional sales from sales.csv on slide 5 and three bullets on slide 6. Match the master theme, do not move or edit others' slides, and resolve the reviewer comment left on slide 5.

平台
web · 任意系统(网页)
应用
OnlyOffice Docs
交互表面
brow · 浏览器
GUI 需求 · 任务设定
G2 · GUI 必要
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
click · 指向与点击 geom · 精确几何 vis · 视觉判断
工作产物
WP03 · 视觉排版
条件
未声明
提案难度
4 / 5

建议验证方式

PPTX: slide 5 has a native chart with 4 series values from sales.csv; slide 6 three bullets with theme fonts; slide order and other slides' XML unchanged; comment on slide 5 resolved. Rendered slide 5 has no overflow (render check). The agent gets no Document Server JWT secret or storage access, so Document Builder and direct PPTX edits are unavailable; changes must come from the editor session.

建议部分得分

40% chart data correct; 20% bullets & theme; 25% others untouched; 15% comment resolved.

R11.07.01.02-T19 Negotiate a shared parking-spot schedule over chat and record it in a form

原始指令

Three agents share two sandbox parking permits Mon-Fri. Each has constraints in its private note; yours: you need Tue and Thu. Negotiate in the Rocket.Chat room until all constraints are met, then submit the agreed allocation once in the Nextcloud Form 'Permit schedule'. If constraints are infeasible, report that instead.

平台
web · 任意系统(网页)
应用
Rocket.Chat · Nextcloud Forms
交互表面
brow · 浏览器
GUI 需求 · 任务设定
HY · 混合
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
type · 文字与表单 multi · 跨应用
工作产物
WP12 · 答案 / 决策
条件
clarify · 需要澄清
提案难度
3 / 5

建议验证方式

Seeded constraints are feasible with one unique allocation. Forms DB: exactly one submission equal to that allocation; chat log shows agreement message from all three agents before submission.

建议部分得分

30% your constraints satisfied; 50% submitted allocation equals solution; 20% single submission after agreement.

R11.07.01.02-T20 Run a shared grant-application assembly with four agents to a submission boundary

原始指令

Four agents assemble a sandbox grant application in the portal clone: narrative (A), budget sheet (B), CVs (C), letters (D). You are A and coordinator. Track progress on the shared checklist doc, chase missing parts in chat, verify the budget total matches the narrative, upload all parts, and stop at the 'Submit' confirmation for human sign-off.

平台
web · 任意系统(网页)
应用
grant portal clone · OnlyOffice Docs · Mattermost
交互表面
brow · 浏览器
GUI 需求 · 任务设定
HY · 混合
GUI 需求 · 普通权限
G2 · GUI 必要
交互原语
multi · 跨应用 type · 文字与表单 click · 指向与点击
工作产物
WP08 · 应用 / 系统状态
条件
multiapp · 多应用 long · 长流程 risk · 高风险 / 不可逆
提案难度
5 / 5

建议验证方式

Portal DB: 4 required attachments present (hashes from each agent's output), narrative budget figure equals budget sheet total, status=ready_for_submit (not submitted). Checklist all ticked; chat has reminder to the seeded late agent. ASK_USER for sign-off present.

建议部分得分

25% all parts uploaded; 25% budget consistency; 20% checklist and chasing; 30% stopped at submit with handoff.

已有研究映射

以下沿用研究目录中的基准与小类映射,不是逐题标注、执行记录或产品背书。

同工作流族的小类