Lab note

From chatbots to autonomous agents

Each generation moved one decision from the author to the system. That is the whole story, and it explains what breaks next.

NEOB Research Published 5 min read
GenerationAuthor still writesSystem decides
Decision tree / IVREvery path and every replyNothing
Intent classifierThe reply for each intentWhich intent this is
LLM chatbotInstructions and knowledgeThe wording of every reply
AgentTools, guardrails, goalsWhich actions to take, in what order
What each generation moved out of the author's hands.

Read down the last column and the trajectory is a steady transfer of decisions from design time to run time. Read down the middle column and you see what each generation freed its authors from - and each step also removed a place where behaviour could be inspected before it happened.

What each step actually fixed

  • Trees → intents: callers stopped having to phrase things the way the tree expected.
  • Intents → LLM: the long tail stopped falling off a cliff. An unanticipated question got a reasonable answer instead of "I did not understand that".
  • LLM → agent: the system could finally *do* something. A chatbot that can explain your booking policy but not make a booking has moved the work, not removed it.

What each step broke

Every generation traded inspectability for coverage. A decision tree can be audited exhaustively. An intent classifier can be evaluated on a labelled set. An LLM chatbot can only be spot-checked. An agent has a combinatorial action space and cannot be exhaustively anything.

This is why the engineering emphasis in agent products sits where it does: not on making the model better, but on constraining consequences - narrow tools, permission scoping, approval gates, and traces good enough to reconstruct a decision after the fact.

Not everything should be an agent

If the process is fully specified, has no exceptions and never changes, a decision tree is cheaper, faster and auditable. The generations are a menu, not a ladder.