WhatsApp AI Agent for Product Recommendation

Go to the AiSensy Signup Page. Create your account using either:

• Your Google account, or

• Your business email address by filling out the sign-up form.

Once signed up, Log in to AiSensy using the same Google account or email credentials.

Once you are logged in, navigate to and click on AI Agent available on the navbar on the left.

Fill in the details given below:

• Website (mandatory)

• Business type

• Anything special it should know? (optional)

• Business context (optional)

Once you fill these details correctly, proceed to hit '✨ Create agent' button. AiSensy automatically builds an agent trained on your business.

When you add your website, AiSensy AI engine auto-generates your business description. Set your agent's name, greeting, and a few ground rules it must always follow.

Fill the details given below:

• Website (fetched automatically)

• Agent/business name

• Greeting message (optional)

• Store currency

• Business type

• What the business does

• Ground rules

In this step, you have to tell the agent about your business website. While adding knowledge to your agent, you must include buying guides, sizing advice, compatibility rules, product differences, usage instructions, and relevant FAQs. This will help the agent answer properly.

You can submit this information in the form of PDF, DOC, TXT, or CSV files. The WhatsApp AI agent for eCommerce entirely relies on the kind of information you submit. Hence it always responds according to it and never gives generic replies.

Every source shows "Ready" once learned.

Perform the below mentioned steps:

• Crawl a page (website URL)

• Upload files (PDF, DOC, TXT, CSV - up to 50MB each)

• Paste text (policies, scripts, price lists)

It is an optional step but helps users become sure about the product. You can upload images of size charts, comparison guides, and visuals of products that can help customers decide. Product images may already come from the connected catalog.

When you add your website, the product recommendation WhatsApp AI Agent automatically fetches the images from it. You can control the visuals the agent can share inside the WhatsApp chat.

Untick any image it shouldn't send.

You can:

• Create Image library (enable/disable per image)

• Search images

In this step, you first need to enable two prebuilt skills that help the agent understand your customers and recommend the right products. You must enable the already defined Sales and Lead Qualification skills before proceeding with this WhatsApp Product Recommendation AI Agent.

In order to do so, navigate to Add Skills, then click Add on Sales (guided selling) and Lead Qualification. Click Done, and both required skills will be enabled.

The next step is to configure both skills based on your requirements. Expand each one and define how your business recommends and sells products. The counter should read 2 enabled. You’ll build your Product Recommendation skill on top of these in the next step.

Sales (guided selling) fields you must fill:

Sales (guided selling) fields you must fill:

• Sales motion

• Why this motion

• What "closing" means here

• Cross-sell / upsell when it genuinely fits

• Price posture

• Do's & Don'ts

• Objections & responses → + Add objection

Lead Qualification - fields you must fill:

• Suggest questions

• Question to ask + contact attribute

• Required

• + Add question

• Add tag(s)

• Set contact attribute(s)

• Hand off to a human

• Push qualified leads to your CRM

In this step, navigate to and click on Add Skills. Check the prebuilt skills list first. If the skill you need isn't already available, then navigate to and hit 'Create custom' button. You can name it Product queries, and pick Task skill as the type.

• What kind of skill is this? (Task skill)

• Icon & name: Product queries

• When should the agent use it?

• Instructions

• Add skills

Now, you must make sure that the instructions fed to the agent are clear and easy to understand. The agent behaves according to the instructions given to it.

One such template example is:

"When a customer asks ‘Which headphones should I buy?’, ask about their budget, intended use, and preferred features, one question at a time. Recommend two or three suitable options from the connected catalog, with images, current prices, and clear reasons for each recommendation. Help them compare the differences and share the product link for their preferred option. Never invent features, prices, or availability."

The product AI agent for E-commerce then uses your instructions and connected catalog to help customers find and buy their desired products.

For more info, tap here to learn how to create a custom skill

Now that you have created the skill you need, it starts to appear in the Skills list. You can now switch it on, expand it to set your cut-off and where a qualified applicant should go, then hit Done.

All you have to go through is:

• Skills list

• Enable the product skill

• Expand to configure its variables, templates & ads

• Skills enabled counter

For example, you can train the E-commerce WhatsApp AI agent to recommend two or three suitable options, explain why each fits, and highlight meaningful differences. If nothing matches, say so and ask whether the customer wants to adjust a preference.

Now your agent is well taught and it knows how it should respond.

Adding your products is one of the most crucial steps while building a product WhatsApp AI agent. The AI agent needs your catalog to recommend actual products based on features, variants, and prices. Detailed product descriptions help it make better matches.

Choose which catalog items the agent can recommend - so every suggestion comes from your actual range.

• Catalog products (select what the agent may recommend)

• Add products by hand (for bundles or items not in your store)

• Sync from Shopify

• Sync from WooCommerce

• Import CSV/XLS

Running Click-to-WhatsApp ads turns useful when customers arrive from ads for a particular product or collection, giving the agent context for its recommendations.

You can map each ad to a custom greeting & context, so the agent knows exactly which ad brought the customer in.

• Add ad (map ad → custom greeting & context)

• Ad ID

• Label

• Greeting (first message to user)

• Context (extra context for the agent)

• Discount honoured at checkout (optional)

• Products featured in this ad

This step decides what happens when the agent can’t recommend a suitable product or answer a product question. Write the fallback message, switch on Hand off to a human, and add the phrases that should bring a person into the WhatsApp chat.

Fallback message: Write a reply for when the agent cannot find suitable product recommendations or retrieve details such as pricing, availability, features, or specifications.

Human handoff: Enable handoff for personalised recommendations the agent cannot provide, complex product comparisons, specific product requirements, or requests to speak with a team member.

What you must fill:

• Fallback message

• Where your agent runs: up to 3 test numbers

• Hand off to a human: toggle

• Trigger phrases

• Handoff message

This step is entirely optional for recommendations based on catalog information but essential for live inventory, purchase history, or compatibility data that the existing catalog connection doesn’t provide.

Actions let your agent fetch live information or complete tasks using connected tools and APIs - checking an order status, creating a CRM lead or booking an appointment.

Hit Add custom API action, tell it when to call it, then paste your cURL - the request fills itself in.

• Action name

• When should the agent call it?

• Paste cURL

• Request: method + endpoint URL

• Headers

• Params

• Body

• Auth

• Test call

Click on - Next: variables

In this step, you can test your agent before going live. Test different budgets, conflicting preferences, product comparisons, and cases with no suitable match.

You must ensure that the agent doesn’t invent features, reviews, discounts, or stock availability.

You can chat with your agent before your customers do with AiSensy's 500 free AI messages for trial.

Publish, switch the AI on & you're live.

• Test your Agent panel (Train/Live modes)

• Publish

• AI on/off toggle