AndreiBot-3000
2 min read
Aspiration secretly pioneered AI content testing in 2020 using GPT-2, with a system trained on approved marketing to expand A/B testing.
On this page
Did you know Aspiration was at the forefront of AI-powered content testing? They didn't either.
Context
I started building a custom content testing system at Aspiration in early 2020, right after OpenAI released GPT-2. AI was a novelty then, treated more as a boondoggle than a threat. A few trusted leaders found the idea interesting but couldn't picture a use case. The CEO was a wildcard. ChatGPT was still two years away.
No green light, no firm no. I built it in stealth. AndreiBot started as a skunkworks project on public GPT-2 models, moved from Hugging Face notebooks to Google Colab for tighter control over training data. Each generation needed source material chosen on purpose, with themes, keywords, and structure pulled out as the outline for new variants.
How it worked
The training set was the unlock: more than 1,000 high-performing, compliance-approved marketing emails. Pre-approved input meant generated output landed inside our voice and inside compliance the first time, even if the bigger test volume added review hours. The system learned from our best work, from climate impact messaging to financial product launches.
AndreiBot was strictly an accelerator. Every AI-generated variant became another option in an A/B test, sitting next to human-written copy. Early variants got rejected often; the success rate climbed as I tuned prompts and training data. Every piece went through the standard review pipeline, bundled into Google Docs as just another test variant.
The workflow: analyze successful emails, break them into components, then play with different emphasis patterns. The value was variant volume on top of proven content, not replacement. Eventually, AI-generated variants performed comparably to human-written copy.
The performance data fed back into the system. Segment-level message analysis sharpened targeting across every email flow: lifecycle sequences, winback, promotional. Every touchpoint became a testing opportunity.
Results
Late 2020 to June 2021, AndreiBot quietly upgraded the testing program. Internal skepticism around AI made it hard to talk about openly. The project shut down when I left, and testing went back to manual. A few months after that, the broader market caught on to AI-assisted content testing.
The landscape has changed since. AI is in every part of product development. Design teams use DALL-E and Midjourney, developers use Copilot and Claude, copy teams use GPT-4. Compliance review is faster too.
The bigger shift is in how the tools get used. GPT-2 prompting wanted explicit structure, parameters, and examples. Modern LLMs handle natural language without coaxing. The principles haven't changed: clear context, specific requirements, defined constraints. AI works best as an accelerator. The teams that treat it that way move faster than the teams that don't.