Skip to the work

Chamber of commerce chatbot

A chatbot that answers from the Chamber’s own material and hands harder questions to staff.

cfcc.orgCentral Fairfax Chamber of Commerce, opens in a new tab

Visitors to the Central Fairfax Chamber of Commerce, a group for local businesses, need clear answers about membership, events and who to contact. I built a chatbot from the director’s knowledge, with answers staff can edit in a spreadsheet.

Tools. Google Sheets, Pinecone, Gemini, OpenRouter, Vercel, WordPress.

Ask the Chamber a question.Sample

  1. Staff keep the answersThe Chamber’s own questions and answers live in a sheet staff can edit any time.Google Sheets
  2. Find the closest answerEach question is matched by meaning to the staff’s answers.Pinecone
  3. Write the reply from itAI words a reply using only the matched answer.Gemini
  4. No good match? Ask a personIf nothing fits, it hands the question to staff instead of guessing.Staff contact
  1. Hi. I answer questions about the Chamber from the staff’s own answers. Pick a question or type one.

Source matchWaiting for a question

Answer from the source. Or bring in a person.

How it was built

What the Chamber got

  • Answers from Chamber material. The director’s knowledge became a website chatbot.
  • Staff can keep it current. They edit the source answers in Google Sheets.
  • A route to a person. Questions needing staff get the right contact details.

How I built it

  1. Start with the director’s knowledge

    I collected her answers about membership, events and referrals and organized them around what visitors ask: 156 entries in six topics.

  2. Make answers editable

    The answers live in a Google Sheet. When staff edit a row, it updates the chatbot without touching website code.

  3. Find, then write

    Pinecone finds the closest answers by meaning. A Gemini model writes the reply from them. Each reply gets a confidence score from two signals: how close the match was, and the model’s own check.

  4. Test, correct, deliver

    I ran a set of real visitor questions and scored each answer. After the demo, corrections went into the answers. Then the chat went onto the Chamber’s WordPress site.