Coming Soon! - Join the free early access programme

Realtime question answering

Powered by artificial intelligence

Search on steroids. Viko doesn't just return matching documents or snippets, it actually answers stakeholder questions directly.

Benefits

Realtime question answering

Viko takes FAQs to the next level by answering questions on the fly

Viko for the web

Laser like targeting

Viko treats each of your visitors as an individual, answering their specific questions in milliseconds.

Reduced costs

By answering ad-hoc questions on the fly, Viko significantly reduces the number of inbound queries.

Automatic FAQs

FAQs are a great sales tool. Viko can automatically generate high performing, product or page specific FAQs.

Automated question answering for websites
Features

Natural language text mining

Viko's artificial intelligence finds answers in your existing content. See our developer features for more information

Surfacing information

Unlike FAQs and chatbot flows which are pre-defined, Viko answers questions on the fly, using your existing content for context.

Automatic FAQs

Since Viko sees the questions and accepted answers, we can generate SEO compliant FAQs, which are published after approval.

Fallback routes

Webhooks allow developers to integrate chat and helpdesk systems for those occasions where Viko can't answer questions.

Self learning

The true power of artificial intelligence is the ability to learn and improve based on feedback. That's exatly what Viko does.

Screenshots

Dialog widget

Simple popup style dialog box. Best suited to simple flows

Dialog widget
How it works

Data ingestion

Data is ingested via API calls or by our web scraper. It's then processed, optimised and stored in a specialised full text database.

1

Document ingestion

Document ingestion

Documents are ingested by our web crawler or through the API and placed in a redundant, persistent queue

2

Parsing & pre-processing

Parsing & pre-processing

The documents are split into smaller chunks, then pre-processed by our natural language processing models

3

Indexing

Indexing

The chunks of text are stored in an optimised, tree like structure for fast retrieval at query time

Querying

Questions are parsed by our natural languages models to understand the true semantic meaning. They are then passed down through a chain of handlers.

1

Prior answer search

Prior answer search

First we check if the question is semantically similar to a prior question/answer pair

2

Answer generation

Answer generation

If a prior answer cannot be found we extract or generate an answer, using the ingested documents for context

3

Forwarding

Forward to agent

Finally if no suitable answer can be generated, or the answer is rejected by the user, we forward it to an agent

Try Viko

Want to see Viko in action? Try our interactive demo