Back to Details

research-ops

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Research Ops

Research Ops

Use this when the user asks to research something current, compare options, enrich people or companies, or turn repeated lookups into a monitored workflow.
This is the operator wrapper around the repo's research stack. It is not a replacement for 
deep-research
, 
exa-search
, or 
market-research
; it tells you when and how to use them together.
当用户要求调研当前事件、对比可选方案、补全人员或公司信息，或是将重复查询转化为可监控的工作流时使用本模块。
这是代码库调研技术栈的操作封装层，并非
deep-research
、
exa-search
或
market-research
的替代品；它用于指导你何时以及如何搭配使用这些工具。

Skill Stack

技能栈

Pull these ECC-native skills into the workflow when relevant:
  • exa-search
    for fast current-web discovery
  • deep-research
    for multi-source synthesis with citations
  • market-research
    when the end result should be a recommendation or ranked decision
  • lead-intelligence
    when the task is people/company targeting instead of generic research
  • knowledge-ops
    when the result should be stored in durable context afterward
相关场景下可将以下ECC原生技能引入工作流：
  • exa-search
    用于快速的当前网页信息发现
  • deep-research
    用于带引用的多源信息整合
  • market-research
    适用于最终需要输出建议或排名决策的场景
  • lead-intelligence
    适用于人员/公司定向挖掘而非通用调研的任务
  • knowledge-ops
    适用于后续需要将结果持久化存储到上下文的场景

When to Use

适用场景

  • user says "research", "look up", "compare", "who should I talk to", or "what's the latest"
  • the answer depends on current public information
  • the user already supplied evidence and wants it factored into a fresh recommendation
  • the task may be recurring enough that it should become a monitor instead of a one-off lookup
  • 用户提及「调研」、「查询」、「对比」、「我应该联系谁」或「最新进展是什么」
  • 答案依赖于当前公开信息
  • 用户已经提供了证据，希望将其纳入最新建议的参考依据
  • 任务重复性较高，适合设置为监控任务而非一次性查询

Guardrails

使用规则

  • do not answer current questions from stale memory when fresh search is cheap
  • separate:
    • sourced fact
    • user-provided evidence
    • inference
    • recommendation
  • do not spin up a heavyweight research pass if the answer is already in local code or docs
  • 当低成本即可获取最新搜索结果时，不要使用过时的记忆内容回答时效性问题
  • 明确区分以下几类内容：
    • 有来源的事实
    • 用户提供的证据
    • 推论
    • 建议
  • 如果本地代码或文档中已经有答案，不要启动重量级调研流程

Workflow

工作流

1. Start from what the user already gave you

1. 从用户已提供的内容出发

Normalize any supplied material into:
  • already-evidenced facts
  • needs verification
  • open questions
Do not restart the analysis from zero if the user already built part of the model.
将所有提交的材料标准化分类为：
  • 已有证据支撑的事实
  • 待验证内容
  • 待解决问题
如果用户已经完成了部分分析建模，不要从零重启分析。

2. Classify the ask

2. 对需求进行分类

Choose the right lane before searching:
  • quick factual answer
  • comparison or decision memo
  • lead/enrichment pass
  • recurring monitoring candidate
搜索前先选择正确的处理路径：
  • 快速事实回答
  • 对比或决策备忘录
  • 线索/信息补全流程
  • 可设置为定期监控的候选任务

3. Take the lightest useful evidence path first

3. 优先采用最轻量的有效证据获取路径

  • use 
    exa-search
    for fast discovery
  • escalate to 
    deep-research
    when synthesis or multiple sources matter
  • use 
    market-research
    when the outcome should end in a recommendation
  • hand off to 
    lead-intelligence
    when the real ask is target ranking or warm-path discovery
  • 使用
    exa-search
    实现快速信息发现
  • 需要多源整合时升级使用
    deep-research
  • 最终需要输出建议时使用
    market-research
  • 实际需求是目标排名或暖链挖掘时，转交
    lead-intelligence
    处理

4. Report with explicit evidence boundaries

4. 输出报告时明确标注证据边界

For important claims, say whether they are:
  • sourced facts
  • user-supplied context
  • inference
  • recommendation
Freshness-sensitive answers should include concrete dates.
重要声明需要标注所属类别：
  • 有来源的事实
  • 用户提供的上下文
  • 推论
  • 建议
对时效性敏感的答案需要包含具体日期。

5. Decide whether the task should stay manual

5. 判断任务是否需要保留手动处理模式

If the user is likely to ask the same research question repeatedly, say so explicitly and recommend a monitoring or workflow layer instead of repeating the same manual search forever.
如果用户可能会反复询问同一调研问题，需明确说明并建议搭建监控或工作流层，避免永远重复手动搜索。

Output Format

输出格式

text
QUESTION TYPE
- factual / comparison / enrichment / monitoring

EVIDENCE
- sourced facts
- user-provided context

INFERENCE
- what follows from the evidence

RECOMMENDATION
- answer or next move
- whether this should become a monitor
text
QUESTION TYPE
- factual / comparison / enrichment / monitoring

EVIDENCE
- sourced facts
- user-provided context

INFERENCE
- what follows from the evidence

RECOMMENDATION
- answer or next move
- whether this should become a monitor

Pitfalls

常见误区

  • do not mix inference into sourced facts without labeling it
  • do not ignore user-provided evidence
  • do not use a heavy research lane for a question local repo context can answer
  • do not give freshness-sensitive answers without dates
  • 不要在未标注的情况下将推论混入有来源的事实中
  • 不要忽略用户提供的证据
  • 本地代码库上下文可回答的问题不要使用重量级调研路径
  • 不要输出不带日期的时效性敏感答案

Verification

验证要求

  • important claims are labeled by evidence type
  • freshness-sensitive outputs include dates
  • the final recommendation matches the actual research mode used
  • 重要声明都标注了证据类型
  • 时效性敏感的输出包含日期
  • 最终建议与实际使用的调研模式匹配