Build spec 01: interview-to-content engine

Bellhaven Wealth Advisors · Audit · Deliverable 03
Demonstration document. Bellhaven Wealth Advisors is a fictional firm created to show the format. Written the way a real spec is written: detailed enough that any competent developer could build this without talking to me.
Purpose

Turn one recorded expert interview into a compliant blog post, a four-post social series, and a three-email sequence, with compliance problems caught before a human reviewer sees the draft.

Summary

Hours returnedApproximately 9.5 per week, from the time map
Build effortSmall. Estimated 3 to 4 weeks including review cycles
Runs inA Claude workspace under Bellhaven billing
Ongoing costPer-seat subscription paid directly to the vendor, plus usage. No license to me
Owner after handoffBellhaven marketing team

Inputs

The compliance rule set

This is the part that makes the build worth doing, and the part most implementations get wrong by keeping rules in prompts where they get dropped. Rules live in a file every agent reads before drafting. At minimum:

  1. No named clients. Any person or firm named in the source as a client gets replaced with an anonymized composite plus a privacy disclosure line.
  2. No performance claims. Return figures, benchmark comparisons, and any phrasing implying a predictable outcome get removed, replaced with process language and the standard disclosure.
  3. No specific advice. Universal instructions about allocations, contributions, or timing get reframed as education, with a direction to consult an advisor about the reader's own situation.
  4. Required disclosure block appended to every asset that discusses markets or performance.

Processing steps

  1. Ingest the transcript. Segment by topic and speaker.
  2. Run the compliance screen. Every flagged span gets recorded with a timestamp, a rule ID, and the proposed replacement. This log is the audit trail and is retained with the run.
  3. Draft each asset from the cleaned material, reading the voice guide before generation, never after.
  4. Re-run the compliance screen against the drafts. A draft that fails twice gets held and escalated rather than auto-corrected.
  5. Write the run record: source, assets produced, flags caught, and status per asset.

Outputs

Blog post900 to 1,400 words, with the disclosure block
Social series4 posts, sequenced for weekly publication
Email sequence3 emails with subject and preview text
Run recordAsset list, compliance flags caught, per-asset status

Acceptance criteria

The build is done when all of the following hold on three consecutive real interviews:

Explicitly out of scope

How you'd know it stopped working

Written to be executable by any competent developer, including one who has never spoken to ScaleUp Sidekicks. That is the point of this document.