Plan Customer Reach
Create a research recruitment plan that separates who to learn from, why their experience matters, and what requires human approval.
Inputs
Require:
- a research question;
- candidate segment hypotheses;
- inclusion and exclusion criteria;
- channel and capacity constraints;
- consent, privacy, incentive, and retention policies.
If the research question asks which feature people want, restate it around a past behavior or unresolved decision before planning recruitment.
Workflow
- Define the decision the research will inform.
- Describe candidate segments by recent behavior, context, and role. Do not define a segment only by demographics.
- Separate B2B buyer, user, approver, and administrator roles when they can experience different jobs.
- State inclusion, exclusion, and sampling-bias risks.
- Choose channels based on where the target behavior is observable.
- Draft a short invitation that states purpose, time, incentive, data use, and voluntary participation.
- Create a recruitment log with status, consent state, and no unnecessary personal data.
- Stop at drafts. Ask for explicit approval before any email, direct message, form submission, or public post.
Boundaries
- Let the model propose segments, channels, and wording.
- Use deterministic checks for required consent fields, duplicated candidates, private-data patterns, and
external_send=false.
- Require a person to approve targets, incentives, channel rules, and every external send.
- Do not invent response-rate benchmarks or treat a participant count as universal evidence sufficiency.
- Do not scrape or enrich private contact information.
Outputs
Create:
reach-plan.jsoncontact-drafts.mdrecruitment-log.csv
Read references/output-contract.md before writing them.
Stop conditions
Stop and report the missing decision when:
- consent or retention policy is absent;
- the segment cannot be connected to the research question;
- recruitment depends on restricted data;
- an invitation makes a product or payment promise;
- the user asks to send without naming targets and approving the final draft.
Verification
Run:
python3 scripts/stg.py scan-privacy contact-drafts.md
Confirm that every external action remains a draft and that observed facts, assumptions, and recommendations are labeled separately.
1---2name: plan-customer-reach3description: Plan consent-aware customer research recruitment and draft-only outreach without sending messages. Use when defining interview segments, recruiting participants, selecting channels, or preparing 고객 인터뷰 대상자·모집·컨택 초안. Do not use for sending the outreach, running the interview, or synthesizing completed transcripts.4---56# Plan Customer Reach78Create a research recruitment plan that separates who to learn from, why their experience matters, and what requires human approval.910## Inputs1112Require:1314- a research question;15- candidate segment hypotheses;16- inclusion and exclusion criteria;17- channel and capacity constraints;18- consent, privacy, incentive, and retention policies.1920If the research question asks which feature people want, restate it around a past behavior or unresolved decision before planning recruitment.2122## Workflow23241. Define the decision the research will inform.252. Describe candidate segments by recent behavior, context, and role. Do not define a segment only by demographics.263. Separate B2B buyer, user, approver, and administrator roles when they can experience different jobs.274. State inclusion, exclusion, and sampling-bias risks.285. Choose channels based on where the target behavior is observable.296. Draft a short invitation that states purpose, time, incentive, data use, and voluntary participation.307. Create a recruitment log with status, consent state, and no unnecessary personal data.318. Stop at drafts. Ask for explicit approval before any email, direct message, form submission, or public post.3233## Boundaries3435- Let the model propose segments, channels, and wording.36- Use deterministic checks for required consent fields, duplicated candidates, private-data patterns, and `external_send=false`.37- Require a person to approve targets, incentives, channel rules, and every external send.38- Do not invent response-rate benchmarks or treat a participant count as universal evidence sufficiency.39- Do not scrape or enrich private contact information.4041## Outputs4243Create:4445- `reach-plan.json`46- `contact-drafts.md`47- `recruitment-log.csv`4849Read [references/output-contract.md](references/output-contract.md) before writing them.5051## Stop conditions5253Stop and report the missing decision when:5455- consent or retention policy is absent;56- the segment cannot be connected to the research question;57- recruitment depends on restricted data;58- an invitation makes a product or payment promise;59- the user asks to send without naming targets and approving the final draft.6061## Verification6263Run:6465```bash66python3 scripts/stg.py scan-privacy contact-drafts.md67```6869Confirm that every external action remains a draft and that observed facts, assumptions, and recommendations are labeled separately.
kimsanguine