diff --git a/app/ai/browser_plug/__init__.py b/app/ai/browser_plug/__init__.py
new file mode 100644
index 0000000..8b13789
--- /dev/null
+++ b/app/ai/browser_plug/__init__.py
@@ -0,0 +1 @@
+
diff --git a/app/ai/browser_plug/form_filler.py b/app/ai/browser_plug/form_filler.py
new file mode 100644
index 0000000..2a456be
--- /dev/null
+++ b/app/ai/browser_plug/form_filler.py
@@ -0,0 +1,35 @@
+"""表单填写 AI 生成模块
+
+根据用户简历、岗位信息和表单字段，调 LLM 生成填写内容。
+依赖：LLM 枚举、browser_plug/prompts
+"""
+
+from app.ai.browser_plug.prompts import FORM_FILL_SYSTEM_PROMPT
+from app.ai.models import LLM
+from app.core.logger import log
+
+
+async def generate_form_answer(resume_text: str, job_text: str, agent_config_text: str,
+                               label: str, reference: str | None, field_type: str) -> str:
+    """生成表单字段的填写内容"""
+    system_content = FORM_FILL_SYSTEM_PROMPT.format(
+        resume_text=resume_text,
+        job_text=job_text,
+        agent_config_text=agent_config_text,
+    )
+
+    # 构造用户消息
+    user_parts = [f"表单字段：{label}", f"字段类型：{field_type}"]
+    if reference:
+        user_parts.append(f"参考信息：{reference}")
+    user_message = "\n".join(user_parts)
+
+    messages = [("system", system_content), ("human", user_message)]
+
+    try:
+        llm = LLM.DOUBAO_PRO_32K.create(temperature=0.3)
+        result = await llm.ainvoke(messages)
+        return result.content.strip()
+    except Exception as e:
+        log.error(f"表单填写AI调用失败: {e}")
+        raise ValueError("AI生成回答失败，请稍后重试")
diff --git a/app/ai/browser_plug/prompts.py b/app/ai/browser_plug/prompts.py
new file mode 100644
index 0000000..2e96f76
--- /dev/null
+++ b/app/ai/browser_plug/prompts.py
@@ -0,0 +1,20 @@
+"""浏览器插件 AI Prompt 模板"""
+
+FORM_FILL_SYSTEM_PROMPT = """你是一个求职表单填写助手。根据用户的简历信息和岗位信息，为招聘网站的表单字段生成合适的填写内容。
+
+【用户简历】
+{resume_text}
+
+【岗位信息】
+{job_text}
+
+【网申预设配置】
+{agent_config_text}
+
+【规则】
+1. 根据表单字段的标签和类型，生成最合适的填写内容
+2. 如果是选择题（select/radio/checkbox），必须从提供的选项中选择，返回选项原文
+3. 如果是文本题（input/textarea），根据简历内容生成简洁、真实的回答
+4. 不要编造简历中没有的信息
+5. 回答要专业、得体，符合求职场景
+6. 直接输出填写内容，不要任何解释、前缀或格式包裹"""
diff --git a/app/api/browser_plug.py b/app/api/browser_plug.py
new file mode 100644
index 0000000..a37c913
--- /dev/null
+++ b/app/api/browser_plug.py
@@ -0,0 +1,21 @@
+"""浏览器插件接口"""
+
+from fastapi import APIRouter
+
+from app.core.context import RequestContext
+from app.core.database import get_db
+from app.schemas.browser_plug import FormFillAnswerParam, FormFillAnswerDto
+from app.services.browser_plug_service import BrowserPlugService
+
+router = APIRouter(prefix="/browser-plug", tags=["浏览器插件"])
+
+
+@router.post("/form-fill-answer", summary="表单填写AI生成答案", response_model=FormFillAnswerDto)
+async def form_fill_answer(param: FormFillAnswerParam):
+    """插件端规则匹配不上的表单字段，调AI根据用户简历和岗位信息生成填写内容"""
+    user_id = RequestContext.user_id.get()
+    async for session in get_db():
+        service = BrowserPlugService(session)
+        value = await service.form_fill_answer(
+            user_id, param.job_id, param.label, param.reference, param.type)
+    return FormFillAnswerDto(value=value)
diff --git a/app/main.py b/app/main.py
index fd2f7e8..f728857 100644
--- a/app/main.py
+++ b/app/main.py
@@ -37,6 +37,7 @@ from app.api.skill_gap import router as skill_gap_router
 from app.api.customize_resume import router as customize_resume_router
 from app.api.job_agent_chat import router as job_agent_chat_router
 from app.api.nova_chat import router as nova_chat_router
+from app.api.browser_plug import router as browser_plug_router
 
 app.include_router(health_router)
 app.include_router(resume_router)
@@ -45,6 +46,7 @@ app.include_router(skill_gap_router)
 app.include_router(customize_resume_router)
 app.include_router(job_agent_chat_router)
 app.include_router(nova_chat_router)
+app.include_router(browser_plug_router)
 # ==============================
 
 if __name__ == "__main__":
diff --git a/app/schemas/browser_plug.py b/app/schemas/browser_plug.py
new file mode 100644
index 0000000..021c9cc
--- /dev/null
+++ b/app/schemas/browser_plug.py
@@ -0,0 +1,22 @@
+"""浏览器插件相关 Schema
+
+请求参数 Param、响应 Dto。
+字段命名使用 camelCase alias，与前端 JSON 对齐。
+"""
+
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class FormFillAnswerParam(BaseModel):
+    """表单填写AI生成答案 请求参数"""
+    job_id: int = Field(default=0, alias="jobId", description="岗位ID，不传默认0")
+    label: str = Field(..., description="表单字段标签文本")
+    reference: Optional[str] = Field(default=None, description="回答参考（选项列表、字数限制等）")
+    type: str = Field(..., description="表单类型：input/textarea/select/radio/checkbox")
+
+
+class FormFillAnswerDto(BaseModel):
+    """表单填写AI生成答案 响应"""
+    value: str = Field(..., description="AI生成的填写内容")
diff --git a/app/services/browser_plug_service.py b/app/services/browser_plug_service.py
new file mode 100644
index 0000000..7fab37a
--- /dev/null
+++ b/app/services/browser_plug_service.py
@@ -0,0 +1,111 @@
+"""浏览器插件 Service
+
+表单填写AI生成：查简历 + 岗位 + agent_config → 调 AI 生成答案。
+"""
+
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.ai.browser_plug.form_filler import generate_form_answer
+from app.models.job import Job
+from app.models.job_agent_config import JobAgentConfig
+from app.services import customize_resume_store
+
+
+class BrowserPlugService:
+
+    def __init__(self, session: AsyncSession):
+        self.session = session
+
+    async def form_fill_answer(self, user_id: int, job_id: int, label: str, reference: str | None, field_type: str) -> str:
+        """生成表单字段的填写内容"""
+        # 1. 获取简历数据（有定制简历用定制，没有自动走默认）
+        resume_data = await customize_resume_store.get(user_id, job_id)
+        resume_text = self._serialize_resume(resume_data)
+
+        # 2. 获取岗位信息
+        job_text = await self._get_job_text(job_id)
+
+        # 3. 获取 agent_config
+        agent_config_text = await self._get_agent_config_text(user_id)
+
+        # 4. 调 AI 生成
+        return await generate_form_answer(resume_text, job_text, agent_config_text, label, reference, field_type)
+
+    async def _get_job_text(self, job_id: int) -> str:
+        """获取岗位信息文本"""
+        if job_id == 0:
+            return "未指定岗位"
+        result = await self.session.execute(select(Job).where(Job.id == job_id))
+        job = result.scalar_one_or_none()
+        if not job:
+            return "未指定岗位"
+        parts = []
+        if job.title:
+            parts.append(f"岗位名称：{job.title}")
+        if job.description:
+            parts.append(f"岗位描述：{job.description}")
+        if job.requirement:
+            parts.append(f"岗位要求：{job.requirement}")
+        return "\n".join(parts) if parts else "未指定岗位"
+
+    async def _get_agent_config_text(self, user_id: int) -> str:
+        """获取 agent_config 预设答案文本"""
+        result = await self.session.execute(
+            select(JobAgentConfig).where(JobAgentConfig.user_id == user_id))
+        config = result.scalar_one_or_none()
+        if not config:
+            return "无预设配置"
+        parts = []
+        if config.accept_dept_transfer:
+            parts.append(f"是否接受部门调剂：{config.accept_dept_transfer}")
+        if config.accept_location_transfer:
+            parts.append(f"是否接受地点调剂：{config.accept_location_transfer}")
+        if config.interview_type:
+            parts.append(f"可参加面试方式：{'、'.join(config.interview_type)}")
+        if config.languages:
+            lang_strs = [f"{l.get('language', '')}({l.get('proficiency', '')})" for l in config.languages]
+            parts.append(f"语言能力：{'、'.join(lang_strs)}")
+        if config.available_date:
+            parts.append(f"预计到岗时间：{config.available_date}")
+        if config.intern_days_per_week:
+            parts.append(f"每周实习天数：{config.intern_days_per_week}")
+        if config.intern_duration:
+            parts.append(f"预计实习时长：{config.intern_duration}")
+        return "\n".join(parts) if parts else "无预设配置"
+
+    @staticmethod
+    def _serialize_resume(data: dict) -> str:
+        """将简历 dict 序列化为文本"""
+        if not data:
+            return "暂无简历信息"
+        parts = []
+        resume = data.get("resume", {})
+        if resume.get("name"):
+            parts.append(f"姓名：{resume['name']}")
+        if resume.get("email"):
+            parts.append(f"邮箱：{resume['email']}")
+        if resume.get("mobileNumber"):
+            parts.append(f"手机：{resume['mobileNumber']}")
+        if resume.get("city"):
+            parts.append(f"城市：{resume['city']}")
+        if resume.get("skills"):
+            parts.append(f"技能：{'、'.join(resume['skills'])}")
+        if resume.get("certificates"):
+            parts.append(f"证书：{'、'.join(resume['certificates'])}")
+        if resume.get("summary"):
+            parts.append(f"个人概述：{resume['summary']}")
+        for section, title in [("education", "教育经历"), ("work", "工作经历"), ("internship", "实习经历"), ("project", "项目经历"), ("competition", "竞赛经历")]:
+            items = data.get(section, [])
+            if items:
+                parts.append(f"{title}：")
+                for item in items:
+                    if section == "education":
+                        parts.append(f"  - {item.get('school', '')} {item.get('major', '')} {item.get('degree', '')}")
+                    elif section in ("work", "internship"):
+                        parts.append(f"  - {item.get('companyName', '')} {item.get('position', '')}")
+                    elif section == "project":
+                        parts.append(f"  - {item.get('projectName', '')} {item.get('role', '')}")
+                    elif section == "competition":
+                        parts.append(f"  - {item.get('competitionName', '')} {item.get('award', '')}")
+        return "\n".join(parts) if parts else "暂无简历信息"