fix(onboarding): drop docs link from welcome screen and starter-content dialog

"Learn how Multica works" was showing up too often in the first two
screens users see. Keep the link in the post-import welcome issue
header (where users actually have time to explore); remove it from
the two earlier surfaces where it competes with the primary CTA.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

apps/docs/content/docs/assigning-issues.mdx

@@ -12,7 +12,7 @@ Assign an [issue](/issues) to an [agent](/agents) and it works as the **official
 | **Assign** | Hand an agent ownership | Changes assignee | Issue + all comments | Inherits from issue | ✓ |
 | [**@-mention**](/mentioning-agents) | Pull it in to take a look | No changes | Issue + trigger comment | Inherits from issue | ✓ |
 | [**Chat**](/chat) | One-to-one conversation outside any issue | No issue involved | Current conversation history | Fixed medium | ✓ |
-| [**Routines**](/routines) | Scheduled or manual automation | Depends on mode | Depends on mode | Set by routine | ✗ |
+| [**Autopilots**](/autopilots) | Scheduled or manual automation | Depends on mode | Depends on mode | Set by autopilot | ✗ |
 
 "Auto retry" refers to retries after infrastructure failures (runtime offline, timeout). Business errors on the agent side (for example, the model reporting an error) are not retried. See [**Tasks**](/tasks) for details.
 
@@ -78,4 +78,4 @@ But **different agents can work on the same issue in parallel** — for example,
 
 - [**@-mention an agent in a comment**](/mentioning-agents) — a lighter trigger that leaves assignee and status untouched
 - [**Chat**](/chat) — one-to-one conversation outside any issue
-- [**Routines**](/routines) — let agents start work automatically on a schedule
+- [**Autopilots**](/autopilots) — let agents start work automatically on a schedule

apps/docs/content/docs/assigning-issues.zh.mdx

@@ -12,7 +12,7 @@ import { Callout } from "fumadocs-ui/components/callout";
 | **分配** | 让智能体正式负责 | 改 assignee | issue + 全部 comments | 继承 issue | ✓ |
 | [**@ 提及**](/mentioning-agents) | 评论里让它看一眼 | 都不改 | issue + 触发评论 | 继承 issue | ✓ |
 | [**对话**](/chat) | 独立于 issue 的一对一聊天 | 不涉及 issue | 当前对话历史 | 固定中 | ✓ |
-| [**Routines**](/routines) | 定时 / 手动自动化 | 视模式 | 视模式 | routine 自定 | ✗ |
+| [**Autopilots**](/autopilots) | 定时 / 手动自动化 | 视模式 | 视模式 | autopilot 自定 | ✗ |
 
 "自动重试"指基础设施故障（运行时离线、超时）导致的重试；智能体侧业务错误（比如模型自己报错）不会自动重试。详见 [**执行任务**](/tasks)。
 
@@ -78,4 +78,4 @@ multica issue assign MUL-42 --unassign
 
 - [**在评论里 @ 智能体**](/mentioning-agents) —— 更轻量的触发方式，不改 assignee / status
 - [**对话**](/chat) —— 脱离 issue 和智能体一对一聊
-- [**Routines**](/routines) —— 让智能体定时自动开工
+- [**Autopilots**](/autopilots) —— 让智能体定时自动开工

apps/docs/content/docs/autopilots.mdx

@@ -0,0 +1,85 @@
+---
+title: Autopilots
+description: Let agents start work on a cron schedule — or trigger once manually via the UI or CLI.
+---
+
+import { Callout } from "fumadocs-ui/components/callout";
+
+Autopilots let [agents](/agents) **start work automatically on a schedule** — configure a cron expression and a timezone, and Multica dispatches a [`task`](/tasks) on its own, without you triggering anything. It fits periodic checks, recurring reports, and overnight cleanup jobs — the "standing order" shape of work. Compared to the other three trigger paths ([assigning](/assigning-issues), [@-mention](/mentioning-agents), and [chat](/chat), where you are the one kicking things off), the core difference with Autopilots is that they are **time-driven**.
+
+## Configure an autopilot
+
+Create a new autopilot on the workspace's **Autopilot** page. You set:
+
+- **Name** — display name
+- **Agent** — who the run is dispatched to
+- **Priority** — inherited by the `task` it produces (same semantics as issue priority)
+- **Description / prompt** — the work description the agent receives each run
+- **Execution mode** — see below
+- **Triggers** — at least one `schedule` (cron + timezone)
+
+## Pick an execution mode
+
+An autopilot has two execution modes. **Start with "create issue" mode.**
+
+- **Create issue mode** (`create_issue`) — default, **recommended**. Each trigger first creates an issue in the workspace (the title supports interpolation like `{{date}}`), then assigns the issue to the agent through the normal assignment flow. All work lands on the issue board with the same history, comments, and status as a manually assigned issue.
+- **Run-only mode** (`run_only`) — skips issue creation and enqueues a `task` directly. The run is invisible on the board — you can only see it in the autopilot's run history.
+
+<Callout type="warning">
+**Run-only mode is currently unstable.** The CLI labels it "not yet supported end-to-end," and the dispatch path has known issues. New users should stick to create issue mode and wait for run-only mode to ship a stable release before switching.
+</Callout>
+
+## Run it on a schedule
+
+Every autopilot needs at least one `schedule` trigger. Cron uses the **standard 5-field format** (minute hour day month weekday), with **1-minute** minimum granularity (no seconds). Timezone is IANA-formatted (for example, `Asia/Shanghai`) and determines which timezone the cron expression is interpreted in.
+
+A few examples:
+
+- `0 9 * * 1-5`, `Asia/Shanghai` — 9 AM Beijing time on weekdays
+- `*/30 * * * *`, `UTC` — every 30 minutes
+- `0 3 * * *`, `UTC` — every day at 3 AM UTC
+
+The Multica server scans for due triggers every **30 seconds** — **the actual fire time can lag by up to 30 seconds**, not down to the second. If the server is restarted across a fire time, it catches up missed triggers on startup (nothing is lost, but they fire right away).
+
+## Trigger once manually
+
+To avoid waiting for cron while debugging an autopilot, trigger it manually:
+
+- UI: click "Run now" on the autopilot detail page
+- CLI:
+
+```bash
+multica autopilot trigger <autopilot-id>
+```
+
+A manual trigger goes through the exact same execution flow as a `schedule` trigger — only the `source` field on the run record is marked `manual`.
+
+## View run history
+
+Every trigger produces a **run record**, visible on the "History" tab of the autopilot detail page:
+
+- Trigger source (`schedule` / `manual`)
+- Start time, completion time
+- Status (`issue_created` / `running` / `completed` / `failed`)
+- The linked issue (create issue mode) or `task` (run-only mode)
+- Failure reason (if failed)
+
+## What happens when an autopilot fails
+
+<Callout type="warning">
+**Autopilot failures are not auto-retried and do not send inbox notifications.** A failure leaves a `failed` entry in run history — no system-level re-enqueue like assign or @-mention, and no notification to anyone. If the autopilot is periodic, **the next cron fire will trigger a new run**, but the failed work is not automatically re-run.
+
+If an autopilot is important, design your own monitoring — for example, have the agent post a comment on success, and catch failures by noticing missing comments.
+</Callout>
+
+Why no auto-retry: autopilots are already periodic, so adding system-level retries stacks on top of the next scheduled run and creates duplicate executions. Leaving the schedule entirely to cron keeps it clean.
+
+## What's not yet available
+
+**Webhook and API triggers are not available yet.** The autopilot trigger schema reserves `webhook` and `api` types, but **they are not wired up to any ingress route** — the UI can create triggers of either type, but they will not actually fire. Today, **only `schedule` and manual triggers are end-to-end usable.**
+
+## Next
+
+- [**Assign issues to agents**](/assigning-issues) — a one-shot hand-off of an issue to an agent
+- [**@-mention agents in comments**](/mentioning-agents) — pull an agent in to take a look from a comment
+- [**Chat**](/chat) — one-to-one conversation outside any issue

apps/docs/content/docs/autopilots.zh.mdx

@@ -1,15 +1,15 @@
 ---
-title: Routines
+title: Autopilots
 description: 让智能体按 cron 定时自己开工——或通过 UI / CLI 手动触发一次。
 ---
 
 import { Callout } from "fumadocs-ui/components/callout";
 
-Routines 让 [智能体](/agents) **按调度自动开工**——配好 cron 和时区，到点 Multica 自己派发 [`task`](/tasks)，不需要你每次触发。适合定期巡检、周期性报告、凌晨跑的清理任务这类"standing order"场景。和前三种触发方式（[分配](/assigning-issues) / [@ 提及](/mentioning-agents) / [对话](/chat) 都是你主动喊一声）相比，Routines 的核心差别是**时间驱动**。
+Autopilots 让 [智能体](/agents) **按调度自动开工**——配好 cron 和时区，到点 Multica 自己派发 [`task`](/tasks)，不需要你每次触发。适合定期巡检、周期性报告、凌晨跑的清理任务这类"standing order"场景。和前三种触发方式（[分配](/assigning-issues) / [@ 提及](/mentioning-agents) / [对话](/chat) 都是你主动喊一声）相比，Autopilots 的核心差别是**时间驱动**。
 
-## 配置一个 Routine
+## 配置一个 Autopilot
 
-在工作区的 **Routines** 页新建一条 routine，要定下：
+在工作区的 **Autopilot** 页新建一条 autopilot，要定下：
 
 - **名字** — 显示名
 - **执行智能体** — 到点派给谁
@@ -20,10 +20,10 @@ Routines 让 [智能体](/agents) **按调度自动开工**——配好 cron 和
 
 ## 选择执行模式
 
-Routine 有两种执行模式，**建议从"先建 issue 模式"开始**：
+Autopilot 有两种执行模式，**建议从"先建 issue 模式"开始**：
 
 - **先建 issue 模式**（`create_issue`）—— 默认，**推荐**。每次触发先在工作区里建一个 issue（标题支持 `{{date}}` 这样的插值），再按分配流程把 issue 派给智能体。所有工作都落在 issue 看板上，历史、评论、状态和手动分配的 issue 完全一致。
-- **直跑模式**（`run_only`）—— 不建 issue，直接入队一个 `task`。看板上看不到这一次运行——只能在 Routine 的运行历史里看到。
+- **直跑模式**（`run_only`）—— 不建 issue，直接入队一个 `task`。看板上看不到这一次运行——只能在 Autopilot 的运行历史里看到。
 
 <Callout type="warning">
 **直跑模式当前不稳定**——目前在 CLI 里被标注为"not yet supported end-to-end"，派发路径有已知问题。新用户只使用先建 issue 模式，等直跑模式 ship 稳定版再切。
@@ -31,7 +31,7 @@ Routine 有两种执行模式，**建议从"先建 issue 模式"开始**：
 
 ## 让它按时间跑
 
-每个 Routine 至少要一个 `schedule` 触发器。Cron 是**标准 5 字段格式**（分 时 日 月 周），最小粒度 **1 分钟**（没有秒级）。时区用 IANA 格式（例如 `Asia/Shanghai`），决定 cron 表达式按哪个时区解读。
+每个 Autopilot 至少要一个 `schedule` 触发器。Cron 是**标准 5 字段格式**（分 时 日 月 周），最小粒度 **1 分钟**（没有秒级）。时区用 IANA 格式（例如 `Asia/Shanghai`），决定 cron 表达式按哪个时区解读。
 
 几个例子：
 
@@ -43,20 +43,20 @@ Multica 服务器每 **30 秒**扫一次到期的触发器——**触发时刻
 
 ## 手动触发一次
 
-调试 Routine 时不想等 cron，可以手动触发一次：
+调试 Autopilot 时不想等 cron，可以手动触发一次：
 
-- UI：在 Routine 详情页点"手动运行"
+- UI：在 Autopilot 详情页点"手动运行"
 - CLI：
 
 ```bash
-multica autopilot trigger <routine-id>
+multica autopilot trigger <autopilot-id>
 ```
 
 手动触发走和 `schedule` 触发完全相同的执行流程，只是运行记录里 `source` 字段标为 `manual`。
 
 ## 看运行历史
 
-每次触发都会产生一条**运行记录**（run），可以在 Routine 详情页的"历史"tab 看到：
+每次触发都会产生一条**运行记录**（run），可以在 Autopilot 详情页的"历史"tab 看到：
 
 - 触发源（`schedule` / `manual`）
 - 开始时间、完成时间
@@ -64,29 +64,19 @@ multica autopilot trigger <routine-id>
 - 关联的 issue（先建 issue 模式）或 `task`（直跑模式）
 - 失败原因（如果失败）
 
-## Routine 失败会怎样
+## Autopilot 失败会怎样
 
 <Callout type="warning">
-**Routine 失败不自动重试，也不发 inbox 通知。** 失败后只在运行历史里留一条 `failed` 记录——不会像分配 / @ 提及那样由系统重新排队，也不会给任何人发通知。如果这条 Routine 是周期任务，**下一次 cron 到点会重新触发一次**（新的 run），但这一次失败的工作不会被自动补跑。
+**Autopilot 失败不自动重试，也不发 inbox 通知。** 失败后只在运行历史里留一条 `failed` 记录——不会像分配 / @ 提及那样由系统重新排队，也不会给任何人发通知。如果这条 Autopilot 是周期任务，**下一次 cron 到点会重新触发一次**（新的 run），但这一次失败的工作不会被自动补跑。
 
-如果 Routine 很重要，要自己设计监控——例如让智能体在成功时给自己发个评论，通过缺失评论来发现失败。
+如果 Autopilot 很重要，要自己设计监控——例如让智能体在成功时给自己发个评论，通过缺失评论来发现失败。
 </Callout>
 
-不自动重试的理由：Routine 本身是周期性的，系统层再加自动重试容易和下一次调度叠加，产生重复执行。调度权完全交给 cron 最干净。
+不自动重试的理由：Autopilot 本身是周期性的，系统层再加自动重试容易和下一次调度叠加，产生重复执行。调度权完全交给 cron 最干净。
 
-## 两个遗留的命名 / 能力点
+## 暂不可用的能力
 
-**CLI 里它叫 `autopilot`**。当前 CLI 子命令是 `multica autopilot` 而不是 `multica routine`：
-
-```bash
-multica autopilot list
-multica autopilot create
-multica autopilot trigger <id>
-```
-
-文档里一律用 Routines，后续版本 CLI 会统一。现在遇到 `autopilot` 字样把它当 Routines 看就行。
-
-**Webhook 和 API 触发暂不可用**。Routine 的触发器类型在 schema 里预留了 `webhook` 和 `api` 两种，但**还没接入站路由**——UI 可以创建这两类触发器，不会真的触发。目前**只有 `schedule` 和手动触发是端到端可用的**。
+**Webhook 和 API 触发暂不可用**。Autopilot 的触发器类型在 schema 里预留了 `webhook` 和 `api` 两种，但**还没接入站路由**——UI 可以创建这两类触发器，不会真的触发。目前**只有 `schedule` 和手动触发是端到端可用的**。
 
 ## 下一步
 

apps/docs/content/docs/chat.mdx

@@ -59,5 +59,5 @@ Conversations you no longer want to see can be archived — right-click in the c
 
 ## Next
 
-- [**Routines**](/routines) — let agents start work automatically on a schedule
+- [**Autopilots**](/autopilots) — let agents start work automatically on a schedule
 - [**Assign issues to agents**](/assigning-issues) — bring the topic back onto the issue board

apps/docs/content/docs/chat.zh.mdx

@@ -59,5 +59,5 @@ import { Callout } from "fumadocs-ui/components/callout";
 
 ## 下一步
 
-- [**Routines**](/routines) —— 让智能体定时自动开工
+- [**Autopilots**](/autopilots) —— 让智能体定时自动开工
 - [**分配 issue 给智能体**](/assigning-issues) —— 把话题放回 issue 看板上

apps/docs/content/docs/cli.mdx

@@ -74,15 +74,13 @@ For the difference between token types, see [Authentication and tokens](/auth-to
 | `multica skill import ...` | Import a skill from GitHub, ClawHub, or the local machine |
 | `multica skill files ...` | Nested: manage a skill's files |
 
-## Routines (CLI command name: `autopilot`)
-
-In the docs this feature is called **Routines**, but the CLI subcommand name is still `autopilot` — a future release will unify the two. If you're searching for "routines" and can't find it, try `multica autopilot --help`.
+## Autopilots
 
 | Command | Purpose |
 |---|---|
-| `multica autopilot list` | List every routine in the workspace |
-| `multica autopilot get <id>` | Show a single routine |
-| `multica autopilot create ...` | Create a routine |
+| `multica autopilot list` | List every autopilot in the workspace |
+| `multica autopilot get <id>` | Show a single autopilot |
+| `multica autopilot create ...` | Create an autopilot |
 | `multica autopilot update <id> ...` | Update |
 | `multica autopilot delete <id>` | Delete |
 | `multica autopilot runs <id>` | Show run history |

apps/docs/content/docs/cli.zh.mdx

@@ -74,15 +74,13 @@ Token 类型的详细区分见 [认证与令牌](/auth-tokens)。
 | `multica skill import ...` | 从 GitHub / ClawHub / 本机导入 Skill |
 | `multica skill files ...` | 嵌套：管理 Skill 的文件 |
 
-## Routines（CLI 命令名：`autopilot`）
-
-文档里叫 **Routines**，但 CLI 子命令名保留为 `autopilot`——后续版本会统一。如果你在搜索 "routines" 相关命令但找不到，用 `multica autopilot --help`。
+## Autopilots
 
 | 命令 | 用途 |
 |---|---|
-| `multica autopilot list` | 列出工作区所有 routine |
-| `multica autopilot get <id>` | 查看单个 routine |
-| `multica autopilot create ...` | 创建 routine |
+| `multica autopilot list` | 列出工作区所有 autopilot |
+| `multica autopilot get <id>` | 查看单个 autopilot |
+| `multica autopilot create ...` | 创建 autopilot |
 | `multica autopilot update <id> ...` | 修改 |
 | `multica autopilot delete <id>` | 删除 |
 | `multica autopilot runs <id>` | 查看运行历史 |

apps/docs/content/docs/comments.mdx

@@ -34,7 +34,7 @@ Mentioning the same person multiple times in one comment still produces **only o
 `@all` is a special target: it pushes a notification to every member of the workspace. Both people and agents can use `@all` — which means an agent reporting progress could also `@all`, so remind agents in their instructions to use it sparingly.
 
 <Callout type="warning">
-**Use `@all` carefully.** In a larger workspace, a single `@all` generates that many inbox notifications instantly. Reserve it for things everyone genuinely needs to know — not routine updates.
+**Use `@all` carefully.** In a larger workspace, a single `@all` generates that many inbox notifications instantly. Reserve it for things everyone genuinely needs to know — not day-to-day updates.
 </Callout>
 
 ## Editing and deleting a comment

apps/docs/content/docs/daemon-runtimes.mdx

@@ -75,7 +75,7 @@ Multica uses heartbeats to decide whether a runtime is online. Three key numbers
 Missing is not permanent — as soon as the daemon sends another heartbeat it returns to online, and the runtime record is preserved. Restarting the daemon does not lose runtimes.
 
 <Callout type="warning">
-**Tasks running on a missing runtime are marked as failed** (failure reason `runtime_offline`). For retryable sources (issues, chat), Multica automatically requeues them; Routines-triggered tasks are not retried automatically. See [Tasks → Which failures retry automatically](/tasks#which-failures-retry-automatically-which-dont).
+**Tasks running on a missing runtime are marked as failed** (failure reason `runtime_offline`). For retryable sources (issues, chat), Multica automatically requeues them; Autopilot-triggered tasks are not retried automatically. See [Tasks → Which failures retry automatically](/tasks#which-failures-retry-automatically-which-dont).
 </Callout>
 
 ## How many tasks can run in parallel

apps/docs/content/docs/daemon-runtimes.zh.mdx

@@ -75,7 +75,7 @@ Multica 用心跳判断运行时是否在线。三个关键数字：
 失联不是永久的——守护进程只要再次发出心跳就立刻回到在线，运行时记录也会保留。重启守护进程不会丢运行时。
 
 <Callout type="warning">
-**失联的运行时上正在跑的执行任务会被标记为失败**（失败原因 `runtime_offline`）。对可重试的来源（issue、chat），Multica 会自动重新排队；Routines 触发的任务不自动重试。详见 [执行任务 → 哪些失败会自动重试](/tasks#哪些失败会自动重试哪些不会)。
+**失联的运行时上正在跑的执行任务会被标记为失败**（失败原因 `runtime_offline`）。对可重试的来源（issue、chat），Multica 会自动重新排队；Autopilots 触发的任务不自动重试。详见 [执行任务 → 哪些失败会自动重试](/tasks#哪些失败会自动重试哪些不会)。
 </Callout>
 
 ## 一次能并发跑多少任务

apps/docs/content/docs/how-multica-works.mdx

@@ -39,7 +39,7 @@ It's not only "assign an issue" — Multica has 4 triggers, one per collaboratio
 | **Assign an issue** | The most common. Assign an issue to an agent and it starts on its own | [Assigning issues](/assigning-issues) |
 | **@mention an agent in a comment** | "Take a look at this one for me" — don't change the assignee or status, just fire off a comment | [Mentioning agents](/mentioning-agents) |
 | **Direct chat** | Standalone conversation, not tied to an issue — ask questions, have it draft an issue | [Chat](/chat) |
-| **Routines (scheduled)** | Standing instructions — "do a standup summary every Monday morning" and the like | [Routines](/routines) |
+| **Autopilots (scheduled)** | Standing instructions — "do a standup summary every Monday morning" and the like | [Autopilots](/autopilots) |
 
 ## Runtimes: where it runs, and how many tools
 

apps/docs/content/docs/how-multica-works.zh.mdx

@@ -39,7 +39,7 @@ Multica 是一个**分布式**平台。你看到的 Web 界面只是前台——
 | **分配 issue** | 最常见。把一条 issue 指派给智能体，它自动开工 | [分配 issue](/assigning-issues) |
 | **在评论里 @智能体** | "这条你帮我看一下"——不改 assignee、不改状态，用一条评论触发 | [在评论里 @智能体](/mentioning-agents) |
 | **直接聊天** | 独立对话，不绑 issue——问问题、让它帮起草任务 | [聊天](/chat) |
-| **Routines（定时）** | 长期指令——每周一早上做 standup 总结之类 | [Routines](/routines) |
+| **Autopilots（定时）** | 长期指令——每周一早上做 standup 总结之类 | [Autopilots](/autopilots) |
 
 ## 运行时：在哪里跑，跑几家工具
 

apps/docs/content/docs/mentioning-agents.mdx

@@ -54,5 +54,5 @@ This guard **only blocks direct self-references.** Agent A @-mentioning agent B
 ## Next
 
 - [**Chat**](/chat) — one-to-one conversation outside any issue
-- [**Routines**](/routines) — let agents start work automatically on a schedule
+- [**Autopilots**](/autopilots) — let agents start work automatically on a schedule
 - [**Comments**](/comments) — `@mention` syntax, the picker, and `@all` semantics

apps/docs/content/docs/mentioning-agents.zh.mdx

@@ -54,5 +54,5 @@ import { Callout } from "fumadocs-ui/components/callout";
 ## 下一步
 
 - [**对话**](/chat) —— 脱离 issue 和智能体一对一聊
-- [**Routines**](/routines) —— 让智能体定时自动开工
+- [**Autopilots**](/autopilots) —— 让智能体定时自动开工
 - [**评论**](/comments) —— `@mention` 的语法、picker、`@all` 的语义

apps/docs/content/docs/meta.json

@@ -22,7 +22,7 @@
     "assigning-issues",
     "mentioning-agents",
     "chat",
-    "routines",
+    "autopilots",
     "---Inbox---",
     "inbox",
     "---Self-hosting & ops---",

apps/docs/content/docs/meta.zh.json

@@ -22,7 +22,7 @@
     "assigning-issues",
     "mentioning-agents",
     "chat",
-    "routines",
+    "autopilots",
     "---收件箱---",
     "inbox",
     "---自部署运维---",

apps/docs/content/docs/routines.mdx

@@ -1,95 +0,0 @@
----
-title: Routines
-description: Let agents start work on a cron schedule — or trigger once manually via the UI or CLI.
----
-
-import { Callout } from "fumadocs-ui/components/callout";
-
-Routines let [agents](/agents) **start work automatically on a schedule** — configure a cron expression and a timezone, and Multica dispatches a [`task`](/tasks) on its own, without you triggering anything. It fits periodic checks, recurring reports, and overnight cleanup jobs — the "standing order" shape of work. Compared to the other three trigger paths ([assigning](/assigning-issues), [@-mention](/mentioning-agents), and [chat](/chat), where you are the one kicking things off), the core difference with Routines is that they are **time-driven**.
-
-## Configure a routine
-
-Create a new routine on the workspace's **Routines** page. You set:
-
-- **Name** — display name
-- **Agent** — who the run is dispatched to
-- **Priority** — inherited by the `task` it produces (same semantics as issue priority)
-- **Description / prompt** — the work description the agent receives each run
-- **Execution mode** — see below
-- **Triggers** — at least one `schedule` (cron + timezone)
-
-## Pick an execution mode
-
-A routine has two execution modes. **Start with "create issue" mode.**
-
-- **Create issue mode** (`create_issue`) — default, **recommended**. Each trigger first creates an issue in the workspace (the title supports interpolation like `{{date}}`), then assigns the issue to the agent through the normal assignment flow. All work lands on the issue board with the same history, comments, and status as a manually assigned issue.
-- **Run-only mode** (`run_only`) — skips issue creation and enqueues a `task` directly. The run is invisible on the board — you can only see it in the routine's run history.
-
-<Callout type="warning">
-**Run-only mode is currently unstable.** The CLI labels it "not yet supported end-to-end," and the dispatch path has known issues. New users should stick to create issue mode and wait for run-only mode to ship a stable release before switching.
-</Callout>
-
-## Run it on a schedule
-
-Every routine needs at least one `schedule` trigger. Cron uses the **standard 5-field format** (minute hour day month weekday), with **1-minute** minimum granularity (no seconds). Timezone is IANA-formatted (for example, `Asia/Shanghai`) and determines which timezone the cron expression is interpreted in.
-
-A few examples:
-
-- `0 9 * * 1-5`, `Asia/Shanghai` — 9 AM Beijing time on weekdays
-- `*/30 * * * *`, `UTC` — every 30 minutes
-- `0 3 * * *`, `UTC` — every day at 3 AM UTC
-
-The Multica server scans for due triggers every **30 seconds** — **the actual fire time can lag by up to 30 seconds**, not down to the second. If the server is restarted across a fire time, it catches up missed triggers on startup (nothing is lost, but they fire right away).
-
-## Trigger once manually
-
-To avoid waiting for cron while debugging a routine, trigger it manually:
-
-- UI: click "Run now" on the routine detail page
-- CLI:
-
-```bash
-multica autopilot trigger <routine-id>
-```
-
-A manual trigger goes through the exact same execution flow as a `schedule` trigger — only the `source` field on the run record is marked `manual`.
-
-## View run history
-
-Every trigger produces a **run record**, visible on the "History" tab of the routine detail page:
-
-- Trigger source (`schedule` / `manual`)
-- Start time, completion time
-- Status (`issue_created` / `running` / `completed` / `failed`)
-- The linked issue (create issue mode) or `task` (run-only mode)
-- Failure reason (if failed)
-
-## What happens when a routine fails
-
-<Callout type="warning">
-**Routine failures are not auto-retried and do not send inbox notifications.** A failure leaves a `failed` entry in run history — no system-level re-enqueue like assign or @-mention, and no notification to anyone. If the routine is periodic, **the next cron fire will trigger a new run**, but the failed work is not automatically re-run.
-
-If a routine is important, design your own monitoring — for example, have the agent post a comment on success, and catch failures by noticing missing comments.
-</Callout>
-
-Why no auto-retry: routines are already periodic, so adding system-level retries stacks on top of the next scheduled run and creates duplicate executions. Leaving the schedule entirely to cron keeps it clean.
-
-## Two naming / capability carryovers
-
-**In the CLI it is called `autopilot`.** The current CLI subcommand is `multica autopilot` rather than `multica routine`:
-
-```bash
-multica autopilot list
-multica autopilot create
-multica autopilot trigger <id>
-```
-
-The docs use Routines throughout; a future CLI release will unify the naming. For now, treat any `autopilot` wording as Routines.
-
-**Webhook and API triggers are not available yet.** The routine trigger schema reserves `webhook` and `api` types, but **they are not wired up to any ingress route** — the UI can create triggers of either type, but they will not actually fire. Today, **only `schedule` and manual triggers are end-to-end usable.**
-
-## Next
-
-- [**Assign issues to agents**](/assigning-issues) — a one-shot hand-off of an issue to an agent
-- [**@-mention agents in comments**](/mentioning-agents) — pull an agent in to take a look from a comment
-- [**Chat**](/chat) — one-to-one conversation outside any issue

apps/docs/content/docs/tasks.mdx

@@ -6,7 +6,7 @@ description: The unit of work for every agent run, with a clear state machine, t
 import { Callout } from "fumadocs-ui/components/callout";
 import { Mermaid } from "@/components/mermaid";
 
-A **task** is the unit of every [agent](/agents) run — [assigning an issue to an agent](/assigning-issues), [@-mentioning an agent in a comment](/mentioning-agents), sending a message in [chat](/chat), or a [Routine](/routines) firing on schedule all produce a task. Multica puts it in a queue; a [daemon](/daemon-runtimes) picks it up and hands it off to the corresponding [AI coding tool](/providers), then writes the result back to the server when it finishes.
+A **task** is the unit of every [agent](/agents) run — [assigning an issue to an agent](/assigning-issues), [@-mentioning an agent in a comment](/mentioning-agents), sending a message in [chat](/chat), or an [Autopilot](/autopilots) firing on schedule all produce a task. Multica puts it in a queue; a [daemon](/daemon-runtimes) picks it up and hands it off to the corresponding [AI coding tool](/providers), then writes the result back to the server when it finishes.
 
 Tasks and [issues](/issues) are two different objects. A single issue can be assigned, @-mentioned, and manually rerun many times — each produces a **new** task.
 
@@ -59,10 +59,10 @@ Failures fall into two categories: **retryable** and **non-retryable**.
 Automatic retry also has two extra conditions:
 
 1. **At most 2 attempts** — 1 original + 1 retry. If the retry also fails, no further retries, even if the reason is retryable.
-2. **Only for issue- and chat-triggered tasks** — Routine-triggered tasks do **not** retry automatically.
+2. **Only for issue- and chat-triggered tasks** — Autopilot-triggered tasks do **not** retry automatically.
 
 <Callout type="warning">
-**Routine tasks don't retry automatically** by design. A Routine has its own firing cadence (e.g. daily); automatic retries on failure would overlap with the next scheduled run. If you need an immediate re-run after failure, use a manual rerun (next section).
+**Autopilot tasks don't retry automatically** by design. An Autopilot has its own firing cadence (e.g. daily); automatic retries on failure would overlap with the next scheduled run. If you need an immediate re-run after failure, use a manual rerun (next section).
 </Callout>
 
 ## Manual rerun vs. automatic retry
@@ -109,4 +109,4 @@ See [Providers Matrix → Session resumption](/providers#session-resumption-who-
 ## Next
 
 - [Providers Matrix](/providers) — capability differences across the 10 AI coding tools (including the exact session-resumption status)
-- [Assigning issues to agents](/assigning-issues) / [@-mentioning agents in comments](/mentioning-agents) / [Chat](/chat) / [Routines](/routines) — the four ways to trigger a task
+- [Assigning issues to agents](/assigning-issues) / [@-mentioning agents in comments](/mentioning-agents) / [Chat](/chat) / [Autopilots](/autopilots) — the four ways to trigger a task

apps/docs/content/docs/tasks.zh.mdx

@@ -6,7 +6,7 @@ description: 智能体每一次工作的单位，有明确的状态机、超时
 import { Callout } from "fumadocs-ui/components/callout";
 import { Mermaid } from "@/components/mermaid";
 
-**执行任务**（task）是 [智能体](/agents) 每一次工作的单位——把一个 [issue 分给智能体](/assigning-issues)、[在评论里 @提及智能体](/mentioning-agents)、在 [聊天](/chat) 里发一条消息、或者 [Routine](/routines) 到点触发，都会产生一个执行任务。Multica 把它放进队列，由 [守护进程](/daemon-runtimes) 领走后交给对应的 [AI 编程工具](/providers) 执行，结束时把结果写回服务器。
+**执行任务**（task）是 [智能体](/agents) 每一次工作的单位——把一个 [issue 分给智能体](/assigning-issues)、[在评论里 @提及智能体](/mentioning-agents)、在 [聊天](/chat) 里发一条消息、或者 [Autopilot](/autopilots) 到点触发，都会产生一个执行任务。Multica 把它放进队列，由 [守护进程](/daemon-runtimes) 领走后交给对应的 [AI 编程工具](/providers) 执行，结束时把结果写回服务器。
 
 执行任务和 [issue](/issues) 是两层不同对象：一个 issue 可以反复分配、反复 @提及、手动重跑——每次都产生一个**新的**执行任务。
 
@@ -59,10 +59,10 @@ Multica 服务器每 30 秒扫描一次，有两种超时会触发失败：
 自动重试有两个额外条件：
 
 1. **最多 2 次**——1 次原任务 + 1 次重试。重试也失败就不再重试，即使原因可重试。
-2. **只对 issue 和聊天触发的任务生效**——Routines 触发的任务**不自动重试**。
+2. **只对 issue 和聊天触发的任务生效**——Autopilots 触发的任务**不自动重试**。
 
 <Callout type="warning">
-**Routines 任务不自动重试**是刻意设计。Routine 有自己的触发周期（例如每天一次）；如果失败又自动重试，会和下一个周期的任务重叠。需要失败后立即重跑，用手动重跑（下一节）。
+**Autopilots 任务不自动重试**是刻意设计。Autopilot 有自己的触发周期（例如每天一次）；如果失败又自动重试，会和下一个周期的任务重叠。需要失败后立即重跑，用手动重跑（下一节）。
 </Callout>
 
 ## 手动重跑和自动重试的区别
@@ -109,4 +109,4 @@ Multica 在任务过程中**两次**保存会话 ID——任务一开始（AI
 ## 下一步
 
 - [Providers Matrix](/providers) —— 10 款 AI 编程工具的能力差异对照（包括会话恢复的精确状态）
-- [分配 issue 给智能体](/assigning-issues) / [在评论里 @智能体](/mentioning-agents) / [聊天](/chat) / [Routines](/routines) —— 触发执行任务的四种方式
+- [分配 issue 给智能体](/assigning-issues) / [在评论里 @智能体](/mentioning-agents) / [聊天](/chat) / [Autopilots](/autopilots) —— 触发执行任务的四种方式

apps/web/features/landing/components/how-it-works-section.tsx

@@ -6,7 +6,7 @@ import { useLocale } from "../i18n";
 import { GitHubMark, githubUrl, heroButtonClassName } from "./shared";
 
 export function HowItWorksSection() {
-  const { t } = useLocale();
+  const { t, locale } = useLocale();
   const user = useAuthStore((s) => s.user);
 
   return (
@@ -44,6 +44,12 @@ export function HowItWorksSection() {
           <Link href={user ? "/" : "/login"} className={heroButtonClassName("solid")}>
             {user ? t.header.dashboard : t.howItWorks.cta}
           </Link>
+          <Link
+            href={locale === "zh" ? "/docs/zh" : "/docs"}
+            className={heroButtonClassName("ghost")}
+          >
+            {t.howItWorks.ctaDocs}
+          </Link>
           <Link
             href={githubUrl}
             target="_blank"

apps/web/features/landing/i18n/en.ts

@@ -144,6 +144,7 @@ export function createEnDict(allowSignup: boolean): LandingDict {
     ],
     cta: "Get started",
     ctaGithub: "View on GitHub",
+    ctaDocs: "Read the docs",
   },
 
   openSource: {
@@ -232,7 +233,7 @@ export function createEnDict(allowSignup: boolean): LandingDict {
       resources: {
         label: "Resources",
         links: [
-          { label: "Documentation", href: githubUrl },
+          { label: "Documentation", href: "/docs" },
           { label: "API", href: githubUrl },
           { label: "X (Twitter)", href: "https://x.com/MulticaAI" },
         ],

apps/web/features/landing/i18n/types.ts

@@ -43,6 +43,7 @@ export type LandingDict = {
     steps: { title: string; description: string }[];
     cta: string;
     ctaGithub: string;
+    ctaDocs: string;
   };
   openSource: {
     label: string;

apps/web/features/landing/i18n/zh.ts

@@ -144,6 +144,7 @@ export function createZhDict(allowSignup: boolean): LandingDict {
     ],
     cta: "\u5f00\u59cb\u4f7f\u7528",
     ctaGithub: "\u5728 GitHub \u4e0a\u67e5\u770b",
+    ctaDocs: "\u9605\u8bfb\u6587\u6863",
   },
 
   openSource: {
@@ -232,7 +233,7 @@ export function createZhDict(allowSignup: boolean): LandingDict {
       resources: {
         label: "\u8d44\u6e90",
         links: [
-          { label: "\u6587\u6863", href: githubUrl },
+          { label: "\u6587\u6863", href: "/docs/zh" },
           { label: "API", href: githubUrl },
           { label: "X (Twitter)", href: "https://x.com/MulticaAI" },
         ],

packages/views/onboarding/components/runtime-aside-panel.tsx

@@ -38,6 +38,15 @@ export function RuntimeAsidePanel() {
           />
         </div>
       </section>
+
+      <a
+        href="https://multica.ai/docs/daemon-runtimes"
+        target="_blank"
+        rel="noopener noreferrer"
+        className="self-start text-[13px] text-muted-foreground underline underline-offset-4 transition-colors hover:text-foreground"
+      >
+        Learn about runtimes →
+      </a>
     </div>
   );
 }

packages/views/onboarding/steps/step-agent.tsx

@@ -327,6 +327,15 @@ function AboutAgentsSide() {
         Add more agents anytime. A small team of specialized agents beats
         one jack-of-all-trades.
       </p>
+
+      <a
+        href="https://multica.ai/docs/agents-create"
+        target="_blank"
+        rel="noopener noreferrer"
+        className="self-start text-[13px] text-muted-foreground underline underline-offset-4 transition-colors hover:text-foreground"
+      >
+        Creating your first agent →
+      </a>
     </div>
   );
 }

packages/views/onboarding/steps/step-questionnaire.tsx

@@ -328,6 +328,15 @@ function WhyWeAsk() {
           />
         </div>
       </section>
+
+      <a
+        href="https://multica.ai/docs/agents"
+        target="_blank"
+        rel="noopener noreferrer"
+        className="self-start text-[13px] text-muted-foreground underline underline-offset-4 transition-colors hover:text-foreground"
+      >
+        Learn how agents work →
+      </a>
     </div>
   );
 }

packages/views/onboarding/utils/starter-content-templates.ts

@@ -42,6 +42,8 @@ export function buildWelcomeIssueText(
     ``,
     `This is your workspace's first issue. Below, your agent will reply in a moment — that's how work happens here: you write what you want, your agent (or a teammate) picks it up and replies in the comments.`,
     ``,
+    `[Learn how Multica works →](https://multica.ai/docs/how-multica-works)`,
+    ``,
     `---`,
     ``,
   ].join("\n");
@@ -139,6 +141,8 @@ export function buildAgentGuidedSubIssues(
         `**⚠️ Gotcha**: new issues default to Backlog. Agents pause on backlog. A hint dialog will pop up the first time — it's telling you "flip to Todo to start".`,
         ``,
         `**You'll know it worked when**: the Live card shows your agent thinking, and the Status flips to **In Progress** automatically.`,
+        ``,
+        `[Learn about assigning issues →](https://multica.ai/docs/assigning-issues)`,
       ].join("\n"),
     },
     {
@@ -160,6 +164,8 @@ export function buildAgentGuidedSubIssues(
         `**Bonus — @mention an agent inside a comment**: on any issue, scroll to the comment box at the bottom. Type \`@\` and a dropdown appears listing members, agents, and other issues. Pick an agent → write your question → send. The mentioned agent replies in the comments.`,
         ``,
         `**You'll know it worked when**: the agent replies in the chat panel (or comment thread) within a few seconds.`,
+        ``,
+        `[Learn about chat →](https://multica.ai/docs/chat)`,
       ].join("\n"),
     },
     {
@@ -187,6 +193,8 @@ export function buildAgentGuidedSubIssues(
         `Click **Save**.`,
         ``,
         `**You'll know it worked when**: the next task you assign to an agent picks up details from this context without you explaining again.`,
+        ``,
+        `[Learn about workspaces →](https://multica.ai/docs/workspaces)`,
       ].join("\n"),
     },
   ];
@@ -211,6 +219,8 @@ export function buildAgentGuidedSubIssues(
         `5. Click **Send invite**`,
         ``,
         `They'll receive an email with a join link. Pending invites show in the collapsible "Pending Invitations" section below the member list — you can revoke from there.`,
+        ``,
+        `[Learn about members and roles →](https://multica.ai/docs/members-roles)`,
       ].join("\n"),
     });
   }
@@ -259,6 +269,8 @@ export function buildAgentGuidedSubIssues(
       `4. Click **Create**`,
       ``,
       `**You'll know it worked when**: the new agent appears in the Assignee dropdown on any issue, and shows up in the left list on the Agents page.`,
+      ``,
+      `[Learn about creating agents →](https://multica.ai/docs/agents-create)`,
     ].join("\n"),
   });
 
@@ -305,6 +317,8 @@ export function buildAgentGuidedSubIssues(
         `After the run finishes, the **Task Run History** below the card lists every past run. Click **View transcript** on any row to open the full interactive transcript — a timeline of every message, thinking step, tool call, and result.`,
         ``,
         `**Try it next time you assign an agent**: keep the issue open and watch the Live card appear below the description.`,
+        ``,
+        `[Learn about tasks →](https://multica.ai/docs/tasks)`,
       ].join("\n"),
     },
     {
@@ -324,6 +338,8 @@ export function buildAgentGuidedSubIssues(
         `- Top-right dropdown: **Mark all as read / Archive all / Archive all read / Archive completed** for bulk cleanup`,
         ``,
         `**Tip**: "Archive completed" is the fastest way to clear the noise from issues already finished.`,
+        ``,
+        `[Learn about the inbox →](https://multica.ai/docs/inbox)`,
       ].join("\n"),
     },
     {
@@ -342,6 +358,8 @@ export function buildAgentGuidedSubIssues(
         `5. Click **Create**`,
         ``,
         `**Good first autopilots**: daily digest of GitHub activity, weekly "what's blocked" check, or a Monday-morning triage of any issues still in Backlog.`,
+        ``,
+        `[Learn about autopilots →](https://multica.ai/docs/autopilots)`,
       ].join("\n"),
     },
   ];
@@ -383,6 +401,8 @@ export function buildSelfServeSubIssues(
         `   The daemon keeps running after you close the terminal — you don't have to leave anything open.`,
         ``,
         `**Verify**: sidebar → bottom **Configure** section → **Runtimes** → you should see at least one connected runtime.`,
+        ``,
+        `[Learn about runtimes →](https://multica.ai/docs/daemon-runtimes)`,
       ].join("\n"),
     },
     {
@@ -406,6 +426,8 @@ export function buildSelfServeSubIssues(
         `**Note**: an agent is just an LLM + instructions + workspace access. Nothing locks a "Coding Agent" to coding — same agent can do research, writing, planning. Keep it flexible.`,
         ``,
         `**You'll know it worked when**: the new agent appears in the Assignee dropdown on any issue.`,
+        ``,
+        `[Learn about creating agents →](https://multica.ai/docs/agents-create)`,
       ].join("\n"),
     },
   ];
@@ -433,6 +455,8 @@ export function buildSelfServeSubIssues(
         `5. Watch the agent reply in the comments and a **Live card** appear in Activity`,
         ``,
         `**⚠️ Gotcha**: new issues default to **Backlog**. You must flip to **Todo** to trigger the agent.`,
+        ``,
+        `[Learn about assigning issues →](https://multica.ai/docs/assigning-issues)`,
       ].join("\n"),
     },
     {
@@ -457,6 +481,8 @@ export function buildSelfServeSubIssues(
         `Click **Save**.`,
         ``,
         `**You'll know it worked when**: the next task you assign to an agent picks up details from this context without you explaining again.`,
+        ``,
+        `[Learn about workspaces →](https://multica.ai/docs/workspaces)`,
       ].join("\n"),
     },
   ];
@@ -481,6 +507,8 @@ export function buildSelfServeSubIssues(
         `3. Type a question → press **Enter**`,
         ``,
         `**Bonus**: inside any issue's comment box, type \`@\` to mention an agent or member.`,
+        ``,
+        `[Learn about chat →](https://multica.ai/docs/chat)`,
       ].join("\n"),
     },
   ];
@@ -517,6 +545,8 @@ export function buildSelfServeSubIssues(
         `1. Sidebar → **Settings** (⚙️, bottom)`,
         `2. Left tab list → **Members** (people icon)`,
         `3. Click **Add member** → enter email → pick role → **Send invite**`,
+        ``,
+        `[Learn about members and roles →](https://multica.ai/docs/members-roles)`,
       ].join("\n"),
     });
   }
@@ -552,6 +582,8 @@ export function buildSelfServeSubIssues(
         `When an agent is working on an issue, a **Live card** appears at the top of the **Activity** section (it sticks to the top of the viewport as you scroll).`,
         ``,
         `It shows in real time which tool the agent is calling, streaming thoughts, and current status. After the run finishes, the **Task Run History** below the card lists every past run — click **View transcript** to open the full timeline.`,
+        ``,
+        `[Learn about tasks →](https://multica.ai/docs/tasks)`,
       ].join("\n"),
     },
     {
@@ -568,6 +600,8 @@ export function buildSelfServeSubIssues(
         `1. Sidebar → under **Workspace** group → click **Autopilot** (⚡ Zap icon)`,
         `2. Pick one of 6 templates, or click **+ New autopilot** top-right`,
         `3. Fill: **Name** / **Prompt** / **Agent** / **Schedule** (frequency + time + timezone) → **Create**`,
+        ``,
+        `[Learn about autopilots →](https://multica.ai/docs/autopilots)`,
       ].join("\n"),
     },
   );