SiteGPTStart free trial

10 Support Analytics Questions You Can Ask Claude About Your Chatbot

Ten support analytics questions a support lead can ask Claude about a SiteGPT chatbot over MCP: the exact prompt for each, which tool Claude reaches for, what comes back, and the follow-up action.

Sai Dheeraj

SiteGPT Team

· Updated September 28, 2026

Chatbot Analytics with Claude

SiteGPTBest AI chatbot for customer service

SiteGPT's analytics dashboard is live on every plan. Every plan gets period totals. Growth and above adds trend charts, the engagement funnel, and knowledge gaps, and Scale and above adds AI conversation insights.

This list covers two situations the dashboard cannot help with. Sometimes your plan does not include the view you want yet. Other times the number is on screen, but reading the transcripts, drafting the fix, and shipping it is still your job. Connect Claude to SiteGPT over the Model Context Protocol (MCP) and you can ask for both.

Each question below has the exact prompt to paste, the connector tool Claude reaches for, what comes back, and the follow-up action. Copy the prompts as written.

iShort answer

Connect Claude to SiteGPT from Claude's connector directory and ask it support analytics questions in plain language. Claude works through three tools. search finds the right operation, execute_read pulls data read-only, and execute_write changes things only with confirmation. This helps in two ways. On Starter and Growth, Claude's own analysis of your raw data reaches answers the dashboard reserves for higher tiers, like topic clustering. On any plan, Claude takes the step after the number: drafting the missing help article, saving the fix, triggering the re-sync, writing the Monday summary in your format.

The analytics you have, and the analytics you can ask for

The dashboard is live and tiered. Claude reads the same data through your own permissions and does the step after the number.

The dashboard shows you (live today)

  • Every plan: the analytics page with totals for the period
  • Growth and above: daily trends, the widget-to-conversation-to-lead funnel, CSV export, knowledge gaps, and the Monday digest email
  • Scale and above: AI-classified topics, conversation outcomes, and top questions grouped by meaning
  • By design, no separate ticket-deflection, satisfaction, or resolution-time metrics

Ask Claude when

  • Your plan does not include the view: Claude classifies raw transcripts itself on any tier
  • You want a cut the dashboard does not offer: by page, by period, by lead quality, charted in the chat
  • You want the next step done: draft the missing article, save the fix, trigger the re-sync
  • You want it in your format: a Monday summary written for your Slack channel, not a fixed email

The MCP chatbot guide walks through connecting Claude, and the connector directory post covers the two-click version. Every prompt below runs under the connecting user's permissions, so Claude sees what your login sees and nothing more.

1. Which questions did the bot fail to answer this week?

On Growth and above, the dashboard identifies knowledge gaps and the weekly digest email samples questions the bot could not answer. On any plan, Claude can pull the full, current list:

Pull my SiteGPT conversations from the last 7 days. List every question the bot
failed to answer well: fallback answers, visitor downvotes, or the visitor
rephrasing the same question more than once. Group similar questions and rank
groups by frequency.

Claude uses search to find the conversation operations, then execute_read to pull them. What comes back is a ranked list of failure clusters with example transcripts. The follow-up action is question 8: pick the top cluster and draft the fix.

2. What topics keep repeating, and chart them

AI-classified topics are part of AI conversation insights on Scale and above. On Starter or Growth, Claude does the classification itself from raw transcripts:

Pull the last 30 days of conversations and classify each one into topics by
meaning, not keywords. Give me the top 10 topics with counts, and render a bar
chart. Note which topics are new versus 30 days ago.

Claude renders the chart in the conversation, and SiteGPT does not generate or store it. This is Claude's own analysis, separate from the dashboard feature. It works on every tier and takes any cut you ask for, and it is only as current as the data Claude pulled.

3. Which conversations ended with a request for a human, and why?

Conversation outcomes on Scale show the handed-off share. The reasons behind that share are in the transcripts:

Find conversations from the last 14 days where the visitor asked for a human or
the chat was escalated. Read them and group the reasons: missing information,
policy exceptions, frustration with answers, or something else. Quote one
example per group.

The answer tells you what to fix in training content or escalation setup. Missing content needs a knowledge fix, and policy exceptions need an instructions fix. Frustration clusters call for a human review of tone. To see how other platforms route these conversations to a person, compare AI chatbots with human handoff.

4. How many conversations became leads, and where is the drop-off?

The engagement funnel is part of advanced analytics on Growth and above: widget opens, then conversations started, then leads collected, each stage showing its share. Claude adds the cuts on any plan:

Pull conversations and leads for the last 30 days. What share of conversations
produced a lead? Break it down by week and flag the days that underperform.
Then look at 10 conversations that did not convert and tell me the most common
point where the visitor dropped off.

Claude uses execute_read only. The dashboard gives you the ratio. The transcripts show whether the lead form asks too early, too late, or for too much.

5. What changed since last month?

Trend charts are Growth and above, and the digest reports week-over-week. For any other window, name it:

Compare this month to last month for my chatbot: conversations, AI replies,
leads, and downvote rate. Show the deltas, then tell me the likeliest drivers
of the biggest change by sampling conversations from both periods.

Any tool can compute the delta. The driver analysis from sampled conversations is what an assistant adds.

6. How much of my plan am I actually using?

Message limits are a range. The headline quota assumes the cheaper model, and both the question and the reply count as messages, so check usage mid-month:

Check my SiteGPT usage: messages, pages, chatbots, and team seats against my
plan limits. Project message usage to end of month at the current rate, and
tell me if I am on track to hit a limit.

Claude pulls live usage through execute_read. If the projection says you will run out, the options are the model split in billing settings, the extra-messages add-on, or the next plan up.

7. What are people asking that the knowledge base does not cover?

The dashboard's knowledge gap identification (Growth and above) surfaces gaps with one-click Q&A fixes. Claude's version works on any plan and also checks the reverse: trained content that nobody asks about.

Pull the last 30 days of conversations and my chatbot's list of trained
documents. Which recurring questions have no matching document or custom
response? Which trained documents answer questions nobody asks? Rank the gaps
by frequency.

The second half shows which trained documents go unused, so you know where re-training effort is wasted.

8. Draft the missing help article for the biggest gap

No dashboard drafts the fix for you. Here Claude acts on your workspace as an agent, which the SiteGPT agents page covers in full:

Take the biggest knowledge gap from the last analysis. Draft a help article
that answers it, in the same tone as my existing trained content, using real
visitor phrasings from the conversations as section headings. Then save the
top question and its answer as a custom response in SiteGPT.

Drafting happens in the conversation. The save at the end goes through execute_write, which is marked destructive, so Claude asks for confirmation before anything lands in your workspace. Nothing ships without you approving it.

9. Which answers lean on stale content, and what should be re-synced?

Auto-sync keeps trained content fresh on a schedule (monthly on Growth, weekly with daily scan on Scale). Between syncs, or on Starter, ask:

List my chatbot's trained documents with their last sync dates. Flag anything
older than 30 days that visitors are actively asking about, and tell me which
documents to re-sync first. Then trigger the re-sync for the ones you flagged.

The listing and cross-referencing are reads. The re-sync trigger is a write, so it runs after your confirmation. Stale pricing and policy pages are the classic case, because the bot answers from whatever it last saw. How outdated content turns into wrong answers is covered in why chatbots hallucinate.

10. Give me a Monday morning summary I can paste into Slack

Growth and above already gets a Monday digest email with last week's numbers, week-over-week changes, and up to 3 unanswered questions. It goes to managers and admins, and Scale and above adds the top topics. The format is fixed, and Claude writes one in yours:

Write my Monday chatbot summary for Slack. Last week vs the week before:
conversations, leads, downvote rate. Then the top 3 topics, the top 3
unanswered questions, and one recommended action for the week. Keep it under
150 words, no fluff, bold the numbers.

This works on any plan. Paste it into your channel, and when someone asks a follow-up, the answer is one more question away.

What does the SiteGPT dashboard not measure?

SiteGPT's analytics docs list no separate ticket-deflection, satisfaction-score, or resolution-time metrics beyond the conversation outcomes on Scale. Claude can build proxies for all three from raw conversations:

  • Share of conversations resolved without handoff, as a deflection proxy
  • Downvote rate, as a satisfaction proxy
  • Messages to resolution, as an effort proxy

Label them as proxies when you report them. They are estimates built from transcripts, and SiteGPT does not instrument them.

Try SiteGPT free for 7 days

Frequently asked questions

Do I need the Scale plan to get topic analysis for my chatbot? In the dashboard, yes. AI conversation insights (AI-classified topics, conversation outcomes, and top questions grouped by meaning) is part of Scale and above. On Starter or Growth, connect Claude over MCP, pull the raw conversations with execute_read, and let Claude do the classification. The result is Claude's own analysis of your data, so you can also ask for cuts the dashboard does not offer.

How do I connect Claude to SiteGPT? Two ways. Find SiteGPT in Claude's connector directory and click Connect, or add https://sitegpt.ai/mcp as a custom connector. Either way, approval happens over OAuth in the browser: you sign in to SiteGPT and choose whether the grant covers all chatbots or only selected ones. The full setup walkthrough is at the MCP chatbot guide.

Is it safe to let Claude read my support conversations? The permission model is the answer to evaluate. The grant is scoped to the connecting user: the client cannot receive permissions or chatbot access your dashboard user does not have, so Claude sees exactly what your own login sees and nothing more. Approval is per-user over OAuth, can be limited to selected chatbots, and ends when the connector is disconnected. No API keys are pasted into chat.

Can Claude change my chatbot, or only read from it? Both, through separate tools. Reads go through execute_read, and that tool is marked read-only. Anything that creates, updates, or deletes goes through execute_write. It is marked destructive, so the client asks for confirmation before running it. That is why the drafting workflow in this list saves a custom response only after you approve it.

Does SiteGPT store or render the charts Claude makes? No. Claude renders charts in the conversation from the data it pulled, and SiteGPT does not generate or store them. The dashboard's own charts (stat tiles, funnel, trends, and insights) live on the Analytics page and are described in the analytics docs.

What analytics does the SiteGPT dashboard include without Claude? Every plan gets the analytics page with totals for the period (the pricing page calls this basic analytics: message volume, ratings, and quota tracking). Growth and above adds advanced analytics: daily trend charts, the engagement funnel from widget opens to conversations to leads, knowledge gaps with one-click Q&A fixes, CSV export, and the Monday weekly digest email. Scale and above adds AI conversation insights: AI-classified topics, sentiment, conversation outcomes, and top questions grouped by meaning. The docs list no separate ticket-deflection, satisfaction-score, or resolution-time metrics.

Sources

Related reading