Before the paint was dry on my first WSF agent build, I realized why Google was transitioning to Conversational Agents: LLMs can handle intents naturally, eliminating the often complex task of training phrase mapping. Why not let AI do the heavy lifting?

V2 runs entirely on large language models with a single orchestration Playbook handling intents. Native entity support wasn’t available yet, so I had Python manage terminal synonyms while micro prompts capture time expressions like ‘now,’ ‘ASAP,’ and ‘first available’.

This approach works well for an experimental build, with room to grow as Google’s conversational tools continue to evlove.

Feel free to interact with the live agent below. To start, try any of these four ways to ask for the exact same ferry going in the same direction. The agent should handle each one smoothly, while a Python function interjects to autocomplete your destination:

“Next Bainbridge ferry ….”
“Next ferry to Seattle …”
“When does the ferry leave Bainbridge?”
“Bainbridge departures.”