Do you still need an AI agent framework?
Choose a framework when its orchestration and state-management features solve problems your agent actually has. In his Chain of Thought interview, LlamaIndex co-founder Jerry Liu argues that stable abstractions leave more room to differentiate through production context. That is a reason to evaluate what a framework adds, not a rule that every team should abandon one.
What Jerry Liu argues
Liu describes LlamaIndex’s move toward deeper work on document understanding and production context. In the interview at 38:28, he explains that abstractions were stabilizing while the need for high-quality context continued to evolve. This is his account of where his company could add value, rather than evidence that frameworks have become unnecessary for every team.
Questions to test in your own project
Our practical recommendation is to compare a framework with a small direct implementation of the same workflow:
- Can you inspect tool calls and state when the agent fails?
- Can you resume interrupted work without repeating an action?
- Does the framework simplify the branching or coordination your application needs?
- Can you change retrieval and evaluate the resulting answers without fighting its abstractions?
Use the comparison to decide whether the saved implementation work justifies the dependency and its constraints. A simple workflow may need little orchestration; a complex one may benefit from a framework. Neither choice removes the need to test the data supplied to the model.
For another perspective, compare the agent-stack and context arguments. They address different parts of building a production system and can both be useful.
From the conversation
This explainer is drawn from these episodes — each carries its full transcript.
