← All posts
Morgan Willis
Principal Developer Advocate, AWS
Morgan Willis is a Principal Developer Advocate at AWS working on agents.
2 posts
We ran 94,000 trials to measure the cost of harness choice
We analyzed 94,000 benchmark trials to measure how harness choice affects token usage, estimated costs, and accuracy with Claude, GPT, and open-weight models.
Albert ZhaoFabio Nonato de PaulaAriel NabavianOwen KaplanMorgan WillisChris Smith
Bidi Agents now GA
The easiest way to create voice agents with direct support for Amazon Nova Sonic, OpenAI, and Gemini models.
Albert ZhaoMorgan WillisRachit MehtaPatrick Gray