WebChatAgent chatbot configuration fully explained
A field-by-field guide to the settings that control answer quality, speed, security and behavior.
The Configuration tab determines which model answers, how the assistant behaves and where the widget may run. This guide explains the operational effect of every setting instead of merely listing field names.
Model availability changes over time, so the live dropdown remains authoritative. The safe workflow is to record a baseline, change one setting and re-run the same evaluation questions.
What you will have at the end
- A documented provider and model choice
- Secure allowed-domain settings
- A focused system prompt and repeatable test
Before you start
- An existing chatbot
- A list of allowed website domains
- Five representative customer questions
How configuration affects every answer
Provider and model shape quality, latency, quota usage and processing location. Temperature changes variation, streaming changes how quickly text appears, while language, timezone and the system prompt add behavioral context.
Changing the provider also changes the embedding space. Existing data sources then require re-indexing before grounded answers work again.
01–05
Set it up step by step
Open the Configuration tab
Start with the settings of the correct assistant.
Open the chatbot from the dashboard and select Configuration. Confirm the chatbot name before editing so a multi-bot account does not receive changes in the wrong assistant.
Choose provider and model
Balance quality, latency, quota and data location.
Select a provider, then compare the model speed hint and quota multiplier. Start with the default fast model for FAQ retrieval; move to a smarter model only when the same evaluation set demonstrates a useful gain. Select an EU-based option when processing location is a requirement.
- Provider changes require source re-indexing
- Model names and availability can change
- Quota multiplier affects message allowance
Set temperature, streaming and language
Control variation and perceived response speed.
Use a low temperature for support answers that should remain consistent. Keep streaming enabled when visitors should see the answer as it is generated. Set the primary language and timezone so greetings, dates, business hours and appointment references are interpreted correctly.
Set identity, timezone and allowed domains
Prevent unauthorized widget embeds.
Enter the public service name and exact domains that may load the widget, including required subdomains. Do not use broad domains you do not control. A missing subdomain is a common reason for an otherwise valid widget not appearing.
Write and test the system prompt
Define role, tone, boundaries and escalation.
Write a concise role with the company context, permitted topics, answer style and a clear handoff rule. Save, open a fresh test conversation and check normal questions, missing information and an escalation request.
Example & result
See the practical test and its result
Every tutorial includes a fixed input, the expected outcome and a transparent record of what was actually verified locally.
Practical example: WebChatAgent chatbot configuration fully explained
This exact scenario was completed with the temporary tutorial account.
Exact test input
What is the verification code in the uploaded tutorial PDF? Answer in one sentence and name the source.
Expected result
One concise sentence containing NORDSTERN-42 and the source document name.
What was actually verified
The live assistant answered: “The verification code is NORDSTERN-42, as stated in the Northstar Services Fictional Demo Knowledge Base.”
Tips & tricks
Make the setup reliable
Test with realistic examples, record your baseline and change one setting at a time. That makes real improvements visible.
Use Model Arena for comparisons
Compare models with identical questions and source content instead of relying on a single impressive answer.
Keep prompts operational
State what the bot should do when evidence is missing; do not hide missing knowledge behind personality instructions.
When something does not work
Troubleshooting
Check status, permissions and test data systematically before changing the model or prompt.
Sources show “Re-indexing required”
The provider changed. Re-index all sources before evaluating grounded answers.
Widget does not load on the site
Add the exact hostname, including its subdomain, to Allowed Domains and clear the site cache.
Ready for a production-style test
Save a short configuration record with the chosen model, prompt version and five baseline answers. Re-run it after every major model, source or prompt change.