Quality Assurance (QA) is an intensive endeavour that feels very repetitive to humans. In this article, we explore the potential of using Agentic AI to automate this process. In particular, we’ll apply this methodology to a real-world example: ensuring that parallellm.com (the “target website”) runs smoothly, round the clock. Any issues that do arise will be flagged very quickly.

The application of Agentic AI to QA has great potential, since traditional website scanning is notoriously difficult. Their HTML layouts are liable to change at any moment. AI Agents, when set up in the right way, can tolerate such changes, whereas traditional heuristic rules are hard-coded and brittle against this effect.

Large Language Model (LLM) tools, such as ChatGPT and DeepSeek, have become a key part of people’s workflow, in professional and everyday usage. However, there are dozens of different providers now offering a myriad of options all at different price points; even a single provider has a multitude of models to choose from.

So where do you begin? The Parallellm Pump offers developers a power tool for making response comparisons, asynchronously, to let you be the judge of which provider returns the best result. Still not sure? You can even ask the LLMs themselves to make the decision for you!

In this post, I will share my experiences of running one of the DeepSeek open-weights models (DeepSeek-R1-Distill-Qwen-32B) directly on AWS hardware in the cloud - no need for API tokens.

The good news is that it’s easier than you think - modern libraries, such as PyTorch and the Hugging Face (🤗) transformers package, facilitate much of the heavy lifting. I found some extra tips and tricks along the way to speed things up and I will share these with you in this post.