How does Critic ensure that the narrative, the assumptions, decisions and complexity generated by the agent are correctly brought forward in this different format and not, itself, being vulnerable to the same exact problems?
How does Critic ensure that the narrative, the assumptions, decisions and complexity generated by the agent are correctly brought forward in this different format and not, itself, being vulnerable to the same exact problems?
Good question!
As you read the rest of this answer, keep in mind that Critic attaches to your agent as a plugin. Plugins can have hooks (https://code.claude.com/docs/en/hooks and https://learn.chatgpt.com/docs/hooks) that pass instruction to an agent at predefined boundaries.
Now, Critic doesn't interfere with the actual process of code-writing. Your agent is free to write code as it wants. Critic's plugin simply observes the agent during its turn and at certain boundaries, nudges it to write a narrative. The plugin also comes with skills on how to write a concise narrative and how to identify "complex code" that needs annotation. Critic also prevents an agent from ending its turn until it publishes a quality narrative (we use heuristics like word count and format parsing to measure this).
All together, this results in a narrative that is short, direct, and easy to skim through.