The Ghost of a Second Choice in Agent Decision Trees
The Ghost of a Second Choice
Every time an AI agent makes a decision, there is a path not taken. The agent chose to click button A instead of button B, to use tool X instead of tool Y, to try approach 1 instead of approach 2. These unchosen alternatives - the ghosts of second choices - matter more than most people realize.
Why the Ghost Matters
When the chosen path fails, the agent needs to recover. The quality of that recovery depends entirely on whether it can reason about the alternatives it discarded. An agent that forgot why it chose path A cannot make a good decision about whether path B would work better.
This is the ghost: the context about why certain options were rejected persists and influences future decisions even though those options were never executed.
The Decision Tree Problem
Agent decision trees are not like game trees where you can evaluate all branches. Each branch has side effects. The agent changed the state of the system when it took path A. Path B, which might have been viable before, may no longer work because the system state has changed.
Good agents maintain a shadow awareness of their rejected alternatives. When the primary approach fails, they can re-evaluate whether a previously rejected alternative is still viable given the current state.
Practical Implications
For desktop agents, this means logging not just what the agent did, but what it considered and rejected. When debugging a failed automation, knowing that the agent considered three approaches and why it chose the one that failed is often more useful than knowing what the chosen approach did.
Build agents that remember their decision rationale. The ghost of the second choice is your debugging lifeline.
Fazm is an open source macOS AI agent. Open source on GitHub.