In partnership with
“Create a campaign performance report” sounds like a clear task.
It isn't.
ChatGPT could analyse the data correctly, write a detailed report, add charts, and produce a polished deck, and still give you something you can't use.
Maybe you need every number reconciled against the source data. Maybe the report needs to explain why performance changed, not just what changed. Maybe your CMO needs a clear recommendation on where to move budget next.
Those aren't finishing touches. They're part of the brief.
Before delegating a substantial task to ChatGPT, define the criteria the finished work needs to meet.
For a campaign report, that might be:
All figures match the supplied source data.
The biggest performance changes are explained.
Recommendations are linked to evidence.
Unknowns or weak evidence are clearly flagged.
The report ends with the decisions the team needs to make.
The final deliverable is an editable PowerPoint.
If you're not sure what those criteria should be, get ChatGPT to help:
You are helping me brief an AI task properly.
Task: [describe the task]
The final output will be used by: [audience]
They need it to: [decision, action, or purpose]
Available inputs: [files, data, context]
Required deliverable: [report, deck, spreadsheet, etc.]
Before starting the task, help me define up to 6 criteria the finished work should meet.
Focus on what would make the output accurate, useful, evidence-based, and ready to use. Avoid arbitrary requirements such as word counts unless they genuinely matter.
For each criterion, explain briefly how I can check whether it has been met.
Wait for my approval before starting the task.
Once the work is finished, check the final output against the approved criteria and flag anything that is still incomplete.
Review those criteria before you let ChatGPT start. Add anything it missed and remove anything that doesn't matter.
Then use the same criteria at the end to review the work.
The clearer you are about what good looks like, the better ChatGPT can work towards it.
Happy prompting!
How Jennifer Aniston’s LolaVie brand grew sales 40% with CTV ads
For its first CTV campaign, Jennifer Aniston’s DTC haircare brand LolaVie had a few non-negotiables. The campaign had to be simple. It had to demonstrate measurable impact. And it had to be full-funnel.
LolaVie used Roku Ads Manager to test and optimize creatives — reaching millions of potential customers at all stages of their purchase journeys. Roku Ads Manager helped the brand convey LolaVie’s playful voice while helping drive omnichannel sales across both ecommerce and retail touchpoints.
The campaign included an Action Ad overlay that let viewers shop directly from their TVs by clicking OK on their Roku remote. This guided them to the website to buy LolaVie products.
Discover how Roku Ads Manager helped LolaVie drive big sales and customer growth with self-serve TV ads.
The DTC beauty category is crowded. To break through, Jennifer Aniston’s brand LolaVie, worked with Roku Ads Manager to easily set up, test, and optimize CTV ad creatives. The campaign helped drive a big lift in sales and customer growth, helping LolaVie break through in the crowded beauty category.
Build or buy your support agent? Both skip the number.
Buying or building your customer service agent both carry a cost the pitch skips: maintenance if you build, flexibility if you buy. Running Agents in Customer Work is four conversations on agentic AI in customer ops, this one on build vs. buy. Register now, four Tuesdays, 10 a.m. PT.