We built what should have been the dream team of AI agents—eight specialists covering the entire development lifecycle. But give them an open-ended project and they'd spin in circles asking the same questions. The solution wasn't in the models, but in how humans work best: with clear finish lines. After watching our agents flounder for months, we realized they needed the same thing effective teams do: concrete goals with defined boundaries. When we stopped saying "build an e-commerce site" and started assigning specific deliverables with measurable completion criteria, they transformed from constantly confused assistants into capable, autonomous specialists. The same systems with the same capabilities suddenly performed at an entirely different level, simply because we changed how we structured their work.
This is relatable. IMO the next layer of practical intelligence will be suites of purpose built agents backed by LLMs/SLMs. Context is precious when dealing with stateless tools like language models.