The most successful implementations weren't using complex frameworks or specialized libraries.
We recommend finding the simplest solution possible, and only increasing complexity when needed.
Workflows offer predictability and consistency for well-defined tasks, whereas agents are the better option when flexibility and model-driven decision-making are needed at scale.
Frameworks make it easy to get started but can also obscure the underlying prompts and responses.
Prompt chaining decomposes a task into a sequence of steps, where each LLM call processes the output of the previous one.
Agents begin their work with either a command from, or interactive discussion with, the human user.
It's crucial for the agents to gain 'ground truth' from the environment at each step to assess its progress.
Success in the LLM space isn't about building the most sophisticated system.
Start with simple prompts, optimize them, and add multi-step agentic systems only when simpler solutions fall short.
Agents can now solve real GitHub issues in the SWE-bench Verified benchmark based on the pull request description alone.