FAQ
Q: Who is Clevertar?
A: Clevertar is an Australian Conversational AI company that designs, builds, and operates AI agents that help retailers and service brands sell more and support customers smarter across digital and in-store channels.
Q: Where is Clevertar based?
A: Clevertar is based in Adelaide, South Australia, with customers across Australia and beyond.
Q: How long has Clevertar been operating?
A: Clevertar has been developing AI solutions for over 10 years.
Q: What does Clevertar do, in plain English?
A: We build AI agents that can answer questions, guide customers to the right products or services, and reduce support workload by resolving common enquiries automatically. We also provide analytics and ongoing optimisation so performance improves over time.
Q: What makes Clevertar different from a typical chatbot vendor?
A: Clevertar combines conversational design, AI engineering, and operational delivery. We focus on brand-safe, high-quality customer interactions, measurable performance outcomes, and ongoing improvement, not just “install and forget.”
Q: Do you only build chatbots?
A: No. Depending on the use case, we build sales agents, support agents, and hybrid agents across web and other channels. We can also support optional virtual characters and speech AI where it makes sense.
Q: Who are Clevertar’s customers?
A: Clevertar has delivered conversational AI for major public-sector and enterprise organisations (including national and state-level deployments) and for high-growth commerce brands and Shopify merchants.
Q: What industries do you specialise in?
A: Retail and eCommerce, telecommunications, government and public sector, education, healthcare, and services. If your business has high volumes of repeat questions or complex purchase decisions, we can usually help.
Q: Do you offer an off-the-shelf product, or only custom projects?
A: Both. We have an AI platform that can be rapidly deployed and integrated into your existing systems. We also work on custom builds: tailored AI agents for websites, service brands, enterprises, and special requirements.
Q: What are “Custom Builds”?
A: Custom Builds are bespoke AI agents designed around your goals, systems, channels, and governance requirements. This is ideal when you need deeper integrations, specific workflows, enterprise controls, or legacy platforms.
Q: What solutions does Clevertar offer?
A: We deploy AI agents across three main outcomes:
1) AI Sales Agents: guide shoppers, recommend products, handle objections, and increase conversion and average order value.
2) AI Support Agents: resolve common enquiries, reduce ticket volume, and triage complex cases to humans.
3) Omnichannel and in-store agents: bring the same guidance into physical environments using QR codes, tablets, kiosks, or store-assisted experiences.
Q: What are typical sales use cases?
A: Product discovery, comparisons, sizing/fit guidance, compatibility checks, bundles and upsells, promotions guidance, store and delivery questions, and purchase reassurance.
Q: What are typical support use cases?
A: Order tracking, shipping and delivery queries, returns and exchanges, warranty and troubleshooting, account questions, plan selection (telco), and escalation to human support when needed.
Q: Can we start with support first and add sales later?
A: Yes. Many teams start with support deflection and expand into sales guidance once the AI has strong coverage of policies, product knowledge, and user intent patterns.
Q: Can you support seasonal peaks like Black Friday?
A: Yes. AI agents are designed to handle demand surges without adding headcount, as long as your content, policies, and product information are up to date.
Q: Can your agents work for both B2C and B2B?
A: Yes. The core difference is the content, the qualification flow, and the integration into your CRM or lead workflows.
Q: Do you support internal staff use cases (not customer-facing)?
A: Yes. Many organisations deploy internal AI assistants for staff knowledge, SOP guidance, policy lookup, and triage. (Custom Builds are typically best for this.)
Q: Do you offer multilingual support?
A: Yes. Our platform supports multilingual customer interactions, and Custom Builds can support multilingual deployments as well.
Q: How do Clevertar’s AI agents differ from old-school chatbots?
A: Traditional chatbots rely heavily on rigid rules and decision trees. Clevertar uses modern language AI with structured guardrails, approved knowledge, and performance monitoring so conversations feel natural while staying on brand and accurate.
Q: Is this “generative AI”?
A: Yes. We use modern language models, combined with your approved content and guardrails, to generate helpful responses.
Q: Are you locked into one AI model provider?
A: No. Clevertar can be model-agnostic for Custom Builds, selecting models and infrastructure that fit your requirements for speed, cost, privacy, and governance.
Q: How do you prevent wrong answers or “hallucinations”?
A: We reduce risk through a combination of:
- Using approved sources (your site, policies, knowledge base, product catalog)
- Retrieval-based answering where appropriate
- Guardrails and response constraints (including “only answer from these sources” policies)
- Clear fallback behaviour when the AI is uncertain (ask a clarifying question, offer next steps, or escalate)
Q: What happens when the AI doesn’t know the answer?
A: It should not guess. The agent should either ask a clarifying question, direct the customer to the most relevant official page, collect details for follow-up, or hand off to a human support path.
Q: Can we define what the AI is allowed to talk about?
A: Yes. We can tightly scope topics, tone, and allowed sources. With our AI platform, you can also tighten instructions so it only responds about your store and product range.
Q: Can the AI speak in our brand voice?
A: Yes. We incorporate brand language, style guidance, and tone rules so responses are consistent with your brand.
Q: Can the AI recommend products and do comparisons?
A: Yes. For retail, this is one of the primary strengths. The AI can ask a few questions, narrow down options, and explain recommendations in plain language.
Q: Can the AI handle stock and product availability?
A: Yes. Product availability logic is based on store stock numbers. If your store uses pre-order logic, you can add instructions so the AI explains pre-order availability correctly.
Q: Can the AI track orders?
A: Yes. Our platform can provide order status updates when the customer provides the correct order number and the email address associated with the order.
Q: Can the AI complete actions like refunds or account changes?
A: Typically, not by default. Most deployments start with answering and guiding. If you want action-taking workflows, that is usually handled via Custom Builds with explicit safeguards, authentication, and approvals.
Q: Can the AI capture leads?
A: Yes. If a customer provides contact details for follow-up, our platform can surface this for your team so you can respond.
Q: Can the AI escalate or hand off to humans?
A: Yes. You can keep human support available and the AI can direct customers to human help when required. Human handover can take place with live chat integrations, CRM integrations, or simply via phone and email to your team.
Q: Can the AI work in-store via QR codes?
A: Yes. QR-based access is a common pattern for in-store guidance, product education, and assisted selling.
Q: Do you offer AI voice agents (phone agents), or only web chat?
A: We offer both. Clevertar builds AI agents for web chat and for telephony, including inbound call answering and outbound calling use cases.
Q: Can your voice agent handle outbound calls like reminders, surveys, and booking prompts?
A: Yes. Common outbound use cases include CSI surveys, appointment reminders, service booking prompts, and follow-up calls. We design the talk track, handle common objections, and route or escalate when needed.
Q: How “human” does your voice sound?
A: Voice quality is a core focus. The biggest factors are the voice model used, response latency (avoiding awkward pauses), turn-taking (handling interruptions cleanly), and conversation design (how it starts, how it recovers, how it confirms details). We can share voice samples early so you can assess fit.
Q: Can your voice agent use an Australian accent?
A: Yes. Many of our customers specifically require Australian accents and delivery style.
Q: What about New Zealand voices or accents?
A: Yes. We can support different accents depending on your audience and brand preference.
Q: Can the voice agent handle interruptions and “talk over” moments naturally?
A: Yes. We can enable interruption handling and natural turn-taking behaviours so conversations feel less scripted and more like a real call.
Q: Can you reduce “dead air” while the AI looks things up?
A: Yes. We design for fast responses and can implement natural fillers when the system needs to fetch data, for example short acknowledgement phrases. For some experiences we can also add optional ambient cues (like subtle office sounds) if appropriate for your brand.
Q: Does the caller have to “press 1 for sales, press 2 for support” like an IVR?
A: No. The goal is natural conversation. The AI can route the conversation based on what the caller says, rather than requiring keypad navigation.
Q: Can the AI transfer a caller to a human?
A: Yes. If the caller requests a human, or the AI detects it should escalate, it can transfer the call.
Q: When transferring a call, can the AI brief the human first?
A: Yes. We can provide a short summary of what the caller is asking and what has already been captured, so your team does not need to start from scratch.
Q: Can the AI handle inbound calls like a receptionist (for example medical or service reception)?
A: Yes. Inbound “front desk” call answering is a common pattern. The AI can answer FAQs, capture details, and escalate to the right person when required.
Q: Can the AI book appointments over the phone?
A: Yes, when integrated with your booking or calendar system. The agent can capture required details and either complete the booking or hand off cleanly.
Q: Will people know it’s an AI?
A: It depends on your disclosure preference and how the interaction is designed. Some organisations choose explicit disclosure. Others focus on service outcomes. We can implement whichever approach best aligns with your brand and risk profile.
Q: Can your agents integrate with our CRM (for example HubSpot)?
A: Yes. We can integrate with CRMs for lead capture, handoff, and workflow triggers, and we can also ingest knowledge base content where relevant.
Q: Can you integrate with calendars and appointment scheduling?
A: Yes. We can integrate with common calendar and scheduling systems so the agent can help customers schedule or request appointments.
Q: Can you integrate with our custom systems (for example a dealer management system or custom scheduling platform)?
A: Yes. We integrate via APIs and can build custom integrations where needed, including looking up customer/order details, availability, booking slots, or other operational data.
Q: Can the agent pull answers from multiple sources, not just one FAQ page?
A: Yes. We can combine your website content with approved documents, knowledge base articles, and live system integrations so the agent can answer accurately and contextually.
Q: Can the AI look up real-time status (for example an order, job, or booking)?
A: Yes, with the right integration. The agent can ask for the appropriate identifier (for example email and order number) and then query your system.
Q: Are you a CRM or ticketing system?
A: No. We integrate with your existing stack. Our AI agents sit on top to handle conversations, answer questions, capture intent, and route outcomes back into your tools.
Q: How do we get started?
A: A typical build follows five phases:
1) Configure and discovery
2) Content transformation
3) Acceptance testing
4) Launch and deployment
5) Optimisation and iteration
Q: How long does a pilot take?
A: Many pilots can be deployed in 1-2 weeks, depending on complexity, integrations, and how ready your content is. If voice is required, we often recommend validating the knowledge and flows in text first, then enabling voice once accuracy and behaviour are proven.
Q: How much time do you need from our team to launch?
A: We aim to minimise client lift. Typically we need:
Q: What do you need from us to get a great outcome?
A: Usually:
- Your goals and success criteria
- Your key policies (shipping, returns, warranty, support)
- Your product/service content (catalog, FAQs, guides, comparisons)
- Your brand voice guidance
- Access to relevant systems if integrations are required (Custom Builds)
- A subject matter expert for review and sign-off
Q: Do we need to write everything from scratch?
A: No. We typically transform what you already have (FAQs, policy pages, product pages, knowledge articles) into conversational coverage, then expand based on real customer questions.
Q: How do you test accuracy before going live?
A: We create a benchmark set of real questions your team receives and test the agent’s answers against that set. We then iterate until you’re comfortable with accuracy, tone, and escalation behaviour. Additionally, we run secondary AIs which monitor all conversations for quality purposes.
Q: Can we soft-launch first, without heavily promoting the chatbot?
A: Yes. Some clients start with organic usage to observe real questions and improve coverage before making the agent more prominent.
Q: How do you ensure the AI improves over time?
A: We use conversation analytics to find gaps, identify new intents, and continuously refine content and behaviour based on what customers actually ask.
Q: Can the AI be embedded on specific pages like FAQs or Contact Us?
A: Yes. A common approach is to embed the agent directly on FAQ and Contact pages to intercept questions before a customer emails or calls.
Q: Can the AI be embedded on product pages and “know what page it’s on”?
A: Yes. We can make the agent context-aware so it understands the product or page the customer is viewing and answers accordingly.
Q: Can the AI replace or complement site search?
A: Yes. Some retailers position the agent as a conversational search and recommendation layer, especially when product ranges are large or hard to navigate.
Q: We have thousands of SKUs. Can the AI still help customers find the right product?
A: Yes. Large catalogs are often where conversational guidance is most valuable, because customers can describe what they need in plain language and the agent can narrow options.
Q: Can the AI increase conversion rates?
A: The goal of AI Sales Agents is to reduce friction and answer questions at the moment of intent. Results depend on placement, product complexity, and content readiness. We track assisted conversion and continuously optimise based on real conversations.
Q: How fast do we see results after launch?
A: You can see activity immediately once the agent is live, but performance typically improves over the first weeks as we close gaps found in real conversations and optimise placement and prompts.
Q: Can the AI help with cross-sell and upsell?
A: Yes. The agent can recommend complementary products or higher-fit options based on the customer’s use case, budget, and preferences.
Q: We mainly want after-hours coverage. Can the AI handle support when our team is offline?
A: Yes. After-hours support is a common starting point. The AI can answer FAQs, capture details for follow-up, and escalate urgent cases based on your rules.
Q: Can the AI hand off to a consultant or specialist for technical questions?
A: Yes. We can design escalation paths so the AI handles the basics, then hands off for advanced or specialist enquiries.
Q: Can the AI create a clean summary when it escalates?
A: Yes. For escalations, we can provide structured summaries so your team can respond faster and with full context.
Q: How do you measure ROI?
A: ROI is typically measured using:
- Support deflection and resolution rates
- Conversion uplift, assisted conversion rate, and assisted revenue
- Average order value changes
- Customer satisfaction metrics
- Containment rates and escalation rates
We align these to your objectives during discovery.
Q: What kind of real-world scale have you supported?
A: Clevertar has supported high-volume public and enterprise deployments, including handling major traffic spikes and large numbers of user interactions. We’ve provided successful coverage over huge peak usage periods for clients such as Australian Red Cross and Australian Bureau of Statistics on census night!
Q: What results have you seen in public case studies?
A: Results vary by industry and readiness, but examples include:
- High volumes of customer interactions entirely handled by AI agents (between 50-80%)
- Strong customer satisfaction ratings
- Significant after-hours usage for service availability
For more information, see our <case studies>
Q: How does pricing work?
A: Pricing is typically usage-based, aligned to the number of customer conversations and channels, plus any setup and managed service requirements.
Q: Do you charge per token or per message?
A: No. A common model is pricing per conversation, which makes forecasting simpler than token-based billing.
Q: What counts as a “conversation”?
A: A conversation usually refers to a single customer session with back-and-forth messages during that session. We define this clearly in your proposal so usage is predictable.
Q: Can we cap costs so we never exceed budget?
A: Yes. We can configure hard caps (the agent pauses or becomes unavailable after a quota) or enable overages (the agent continues and you pay per additional conversation). You choose what fits your finance preference.
Q: Can we do a pilot before committing long term?
A: Yes. Many clients start with a pilot to validate quality, integrations, and ROI before scaling.
Q: Do you offer custom pricing or enterprise plans?
A: Yes. In addition to our usage-based pricing, for custom requirements,we also provide Custom Builds for broader and deeper needs.
Q: How much do Custom Builds cost?
A: Pricing depends on channels, integrations, governance requirements, conversation volume, and managed service scope. We typically provide a scoped proposal after discovery.
Q: Is Clevertar compliant with Australian privacy law?
A: Clevertar’s privacy policy describes how personal information is collected and handled, and references compliance obligations under Australian privacy law and notifiable data breach requirements.
Q: What information is collected and stored, and where?
A: We collect and store chat transcripts, recent order information, user IP addresses, and anonymous service telemetry such as network requests. This information is stored securely on our infrastructure. Service telemetry may be retained for up to 12 months.
Q: Do you process personal data about customers?
A: We only collect customer data that is provided to the chatbot voluntarily by the customer.
Q: Is your platform GDPR compliant?
A: Yes. Clevertar complies with GDPR requirements.
Q: Do you use our conversations to train public AI models?
A: By default, we focus on using conversation data to improve your outcomes and maintain quality. If any broader training or reuse is ever required, it should be governed by your agreement and policies.
Q: Can we control data retention and deletion (Custom Builds)?
A: Yes. Data retention, access controls, and deletion requirements can be agreed as part of the solution design, especially for regulated environments.
Q: Can the AI be configured to avoid sensitive topics?
A: Yes. We can scope topics, add guardrails, and implement escalation flows so sensitive topics are handled safely and appropriately.
Q: What support do you provide?
A: We provide full platform support: ongoing monitoring, optimisation, performance reporting, and operational support. We don’t just throw software over the fence at you!
Q: What is the support email?
A: You’ll have a solutions team member working with you.
Q: Do you provide ongoing optimisation?
A: Yes. Optimisation is a core part of achieving strong outcomes. We use conversation analytics to continually improve coverage, accuracy, and conversion support.
Q: Can you work with our agency or internal team?
A: Yes. We regularly collaborate with internal teams and partners, especially where brand, content, and customer experience are shared responsibilities.
Q: Where is your team located?
A: Clevertar is entirely Adelaide-based, with all delivery and support based in Australia.
Q: Do you provide ongoing support, or is it “software only”?
A: We provide managed service options including monitoring, performance reviews, retraining, and continuous improvement. We also support clients who prefer more self-managed operation, depending on the deployment.
Q: We’ve dealt with vendors who only offer email support or offshore teams. How do you handle support?
A: We prioritise responsive, local delivery and clear operational processes. Support structure and SLAs are agreed based on your needs.
Q: Does an AI agent affect our site speed?
A: Our agents are designed for minimal impact on site speed by loading assets after the page is loaded.
Q: Can we integrate our AI agent with WhatsApp or our live chat tool?
A: Clevertar does not currently integrate with WhatsApp or live chat services - but it’s in our pipeline. If this interests you, join our waitlist
Q: How do we tighten guardrails so our AI agent only answers questions about us?
A: We work with you to confirm scope and topics you want the agent to include. By default, our platform ensures that there’s tight adherence for the agent to decline unrelated topics and focus only on your site and product/service range.
Q: What is Pulse?
A: Pulse is Clevertar’s insights assistant that flags important conversations, such as answer confidence and quality, unanswered questions, content gap analysis, follow-up lead details, and customer compliments. You can configure Pulse email notifications in settings.
Q: Can I get emails about important conversations?
A: Yes. Pulse can forward support requests or “needs human help” conversations to an email address when detected.
Q: Can our AI agent track orders?
A: Yes. Customers need to provide the correct order number and the email address associated with the order. We have numerous integrations with existing logistics suppliers and can rapidly build more.
More Questions ?
Let’s put AI to work for your business.
