Interview Records Schema
A primary-source record of interviews with GZ.
What it stores
A primary-source record of interviews with GZ. The journalist agent pressure-tests a position and saves the exact exchange; other agents then read these records as source material instead of re-interviewing. Verbatim answers in, a short synthesis attached.
Owned by the Journalist & Brand Voice agents. Lives in the Internal Tools database · public schema.
The tables
Friendly names first, with the real table name underneath. Key fields only.
Interview Recordscontent_interviews
One row per interview — the verbatim questions and answers, plus a short synthesis written at the close for future context.
| Column | Type |
|---|---|
content_typeblog, thought-leadership, newsletter, investigative… | Choice |
topic | Text |
roundsEach round: the question and GZ's verbatim answer | Structured |
decision_summaryThe agent's synthesis at close | Text |
research_linksSources captured during research | List |
statuscomplete, in-progress, abandoned | Choice |
You don't need all of this to start
Most of what these agents rely on has a simpler equivalent. Anywhere we use a database, you can usually start with a spreadsheet or a document — whatever you're comfortable with. Anywhere we built a custom MCP server, you can reach for a prebuilt AI connector instead of building your own.
We go further because it's where our experience pays off. Years of hands-on database work make a custom data layer feasible for us, and purpose-built MCP servers let us hand each agent a short, sharp instruction file and exactly the tools it needs — custom descriptions, only the endpoints we want, and the occasional extra gate — instead of a long manifesto or playbook. Nothing more, nothing less.
Ready to build technology that works for your mission?
Tell us where your organisation is and what's slowing your team down. We respond personally.