The agentic workflows forcing teams to confront undocumented assumptions is where the real friction lives. Your legacy systems run on tribal knowledge and unwritten rules. AI doesn't know those, so it just generates code that sort of works until someone figures out why it doesn't. That someone is still a human.
The agentic workflows forcing teams to confront undocumented assumptions is where the real friction lives. Your legacy systems run on tribal knowledge and unwritten rules. AI doesn't know those, so it just generates code that sort of works until someone figures out why it doesn't. That someone is still a human.
I totally agree. Context feeding (and results checking) is the next big threshold in scaling AI...