Analytics Overview
Analytics combines organization data fetched from OpenAI with detailed conversation rows stored locally in WordPress.
The Analytics area combines two different evidence sources. OpenAI organization endpoints provide usage, token, and cost data when an Admin API key is available. The WordPress smartsite_logs table provides conversations, response timing, device/channel details, security flags, and confidence information. Understanding the source and date filter behind each card prevents misleading comparisons.
Begin by open charts and choose day, month, or year. The work pays off when you turn findings into one controlled knowledge/instruction/tool improvement and retest; that final observation is more meaningful than a saved notice because it shows what an administrator or visitor actually receives.
What this feature does and when to use it
Section titled “What this feature does and when to use it”Use it to observe usage, cost, response behavior, devices, conversations, and low-confidence information-seeking questions.
Use this feature in the following situations:
- You need a high-level view of demand, cost, performance, device mix, and answer quality.
- You are deciding whether to investigate a traffic, model, knowledge, tool, or security change.
- You need to move from an aggregate chart to the exact conversation evidence behind it.
Where to find it
Section titled “Where to find it”Before you begin
Section titled “Before you begin”- SmartSite Assistant is installed and activated.
- You are signed in with an account that can manage WordPress options.
Set it up step by step
Section titled “Set it up step by step”- Open Charts and choose Day, Month, or Year.
- Review OpenAI usage/cost cards only if an Admin API key is configured.
- Review local response performance and device data.
- Open Chat History and filter to a small date range.
- Inspect representative success, error, blocked, web, and WhatsApp turns.
- Open Knowledge Gaps and select a confidence threshold.
- Turn findings into one controlled knowledge/instruction/tool improvement and retest.
Fields, controls, and important values
Section titled “Fields, controls, and important values”Analytics do not improve a reply automatically; they show where improvement work is worth spending time. Usage and performance reveal cost or delay, conversation records show what visitors actually ask, and knowledge gaps highlight weak retrieval. The useful outcome comes from tracing a pattern back to the relevant source, instruction, tool, or interface setting and then testing the change.
| Field, control, or status | What SmartSite Assistant does with it | How to use it and why it matters |
|---|---|---|
| Charts | OpenAI requests/tokens/cost plus locally logged response/device information. | “Charts” narrows or reorganizes the evidence on screen without changing stored conversations or future AI behavior. Begin with a small scope, then open the underlying record before deciding which source, instruction, or setting deserves attention. |
| Chat History | Searchable local prompts, responses, errors, routing, tool, knowledge, device, and security details. | Changing “Chat History” only changes the administrator’s view. Keep the selection focused enough to compare similar conversations, and avoid treating a visible pattern as proof until individual rows support it. |
| Knowledge Gaps | Heuristic confidence analysis for successful information-seeking turns. | Use “Knowledge Gaps” to isolate the activity relevant to one question. The result can reveal where an answer failed, but the filter itself does not fix anything; improvement comes from the configuration change made after reviewing the evidence. |
| Period | Day, Month, or Year; OpenAI chart headings may still say “Monthly” in other period modes. | “Period” is meaningful only with its stated unit and the behavior it triggers. Compare representative traffic before and after a change, because a lower threshold often acts sooner without making the AI itself more accurate. |
How to confirm it is working
Section titled “How to confirm it is working”For Analytics Overview, a saved notice is only the beginning. Confirm the outcome from a fresh session and compare it with the success description above so cached pages or earlier conversation context do not create a false positive.
Practical example
Section titled “Practical example”A cost spike with stable local turn count may point to model/token changes rather than traffic alone.
Recommended practice
Section titled “Recommended practice”- Change one part of Analytics Overview at a time and keep a short record of the previous value and test result.
- Turn one observed pattern into one controlled configuration change, then compare new conversations with the earlier evidence.
Important warnings
Section titled “Important warnings”Common problems and focused checks
Section titled “Common problems and focused checks”| Problem | What to check and what to do next |
|---|---|
| Analytics Overview is missing or does not match this guide. | Confirm the plugin is active and the account can manage WordPress options. Narrow the date and filter scope, then open source records instead of relying on an empty chart or summary alone. |
| A change on Analytics Overview does not produce the expected result. | Keep the exact notice and test case, then review the browser console and WordPress/PHP log. Narrow the date and filter scope, then open source records instead of relying on an empty chart or summary alone. |
Screen reference
Section titled “Screen reference”- Capture
- Show the Analytics Charts tab with sanitized totals, period selector, usage chart, performance, and device sections.
- Show
- Charts/Chat History/Knowledge Gaps tabs, period, cost/token cards, charts
- Viewport
- Desktop, 1440 × 900
- Annotate
- Use numbered callouts only for controls referenced in the procedure.
- Redact
- OpenAI keys, tokens, secrets, personal information, private URLs, IP addresses, and conversation text