← Business Operations

Brightline: Biz Ops short screener

v1.39 Nov 2026Business OperationsHiring step 1
Download the case foldergops-short-screener-1.3.zip

Brightline runs TikTok Shop affiliate programs for five consumer brands. Every day, creators message us about samples, commission and what to film. We're an AI-first team. An agent drafts every reply by running skill files. The GOPS runs the agent, checks what comes back and makes the calls the agent shouldn't make alone.

This short screener is 12 messages from one pod's Monday affiliate inbox. The data is made up, and all names, brands and numbers are fictional.

It's the same screener our Growth Operations Manager candidates take, so inside the folder you're the pod's GOPS. Biz Ops runs work like this, and then fixes the system behind it.

You need an agent that works on files

Plain chat won't get you through this. Use an agent that can open this folder, follow the skill files and write its results back.

  • Claude Cowork is the minimum. Claude Code is ideal. Codex or similar is fine too.
  • If you don't have a paid plan for one, tell us and we'll send you access.

Setup isn't timed. Get your agent open in this folder first.

The rules

  • 20 minutes once your agent is set up. Stop at 30 at the latest.
  • Point your agent at tasks.csv and let it run. Doing 12 messages well by hand in 20 minutes isn't possible, and that's on purpose.
  • You own every reply that goes out. Some drafts will be wrong. Fix them, then find where each mistake came from: the data, a skill file or the AI making something up.
  • Every client is different. Each one has its own preferences. Your replies and actions should follow them.
  • Decide or escalate. pod.md says what's yours to decide and which expert handles what. Escalate only what truly needs someone else, and give them what they need to act fast. Every escalation costs that person time.
  • Don't edit the skill files. Ops owns them. Write what should change in requests.md.

What's in the folder

  • CLAUDE.md: how the agent works in this folder. Claude Code reads it on its own. Tell any other agent to read it first.
  • pod.md: who's who, the experts you can escalate to, what you can decide, and a map of every file. Start here.
  • tasks.csv: the 12 messages to handle.
  • skills/: the skill files the agent runs:
    • the reply skill
    • how we take care of creators
    • how Brightline sounds
    • each client's preferences
  • brands/: one brief per brand. The briefs are the source of truth for rates, sample rules and claims.
  • data/: the messages, creators, samples and client notes.

What to send back

  1. out/: one file per task, named by task ID. Each holds the action and the reply, ready to send.
  2. status.csv: one row per task, with:
    • the status: done, escalated, held or skipped
    • how it got done: the agent as is, the agent plus your fix, or by hand
    • who you escalated to, if anyone
  3. escalations.md: one short note per person you escalate to, as you'd post it on Slack. For each item, cover what happened, what you need from them and by when.
  4. requests.md: each mistake you found, where it came from (data, skill or AI), the evidence, and the change you'd ask for.
  5. At the bottom of requests.md: 2 or 3 sentences of your own on the call you were least sure about, and why you made it.
  6. The session export, if your agent has one (in Claude Code, /export).

Share it all as one link, either a Drive folder or a GitHub repo, that anyone with the link can view.