Use WhatsApp AI agents for sales and support.

What an agent really is

Model, tools, instructions, and working context.

OpenAI describes an agent around three core components: a model, tools, and instructions. In a customer conversation, useful working context matters too. Waaru combines those parts in one workspace. You choose a supported model, connect approved tools, define instructions and policies, and retain the context needed to complete a multi-turn task.

Tool calling

Typed tools, validated arguments, every call logged.

Every action your agent can take is a tool with a JSON-schema signature. When the agent decides to call a tool, Waaru validates the arguments against the schema before any external system is touched. If the schema is wrong, the agent gets a structured error and retries — your downstream systems never see malformed input.

• WhatsApp — send_message, send_template, send_flow, list_conversations
• Custom REST — define an endpoint with an OpenAPI spec and the agent gets the tool
• Handoff — escalate_to_human(reason, priority, summary)
• Available business integrations: Shopify, Razorpay, Shiprocket, Zoho CRM, Google Calendar, Cal.com, Google Sheets, Google Drive, and Zapier. WooCommerce is in progress
• Planned integrations: HubSpot, Pipedrive, Freshdesk, and Zendesk

MCP-native

Connect your existing AI agent to WhatsApp via Model Context Protocol.

The Model Context Protocol standardises how an AI application discovers and uses tools, resources, and prompts. It does not define a product's tool coverage, permissions, or approval model. In Waaru, MCP-native means the WhatsApp operations intended for approved agents are designed as documented, workspace-scoped tools rather than exposed as an afterthought. Your existing MCP-compatible agent can use the same governed operations across messages, contacts, flows, and analytics.

Memory

Per-contact, per-workspace, persists across sessions.

Memory is the unsexy feature that decides whether an agent feels human. Waaru maintains three tiers of memory. Conversation memory — the full transcript of the active session, used as the immediate context window. Contact memory — facts the agent has learned about this specific customer across every prior conversation (preferred language, last order, complaint history, name). Workspace memory — facts about your business that every agent shares (catalog, policies, FAQs). The agent decides what to remember automatically. If a customer says 'I prefer Hindi', the agent stores that preference at contact level and switches language on the next conversation, six weeks later, on a different device.

Governance

What the agent can and cannot do, by policy.

Autonomy without guardrails is a liability. Every Waaru agent runs inside a policy envelope you configure per workspace. You set the rules for which tools the agent can call without approval, which actions require human confirmation, what the agent must refuse, and what triggers escalation. The agent obeys the policy or escalates — it never silently overrides it.

• Tool allowlists — limit the agent to a subset of tools per workflow
• Approval gates — actions over a threshold (refund > ₹5,000, manual booking change) require human confirmation
• Refusal rules — explicit topics or actions the agent will not engage on, even if asked
• Brand-voice guardrails — tone, banned phrases, mandatory disclaimers per channel
• Rate limits — per-contact and per-workspace caps on tool calls

Handoff

When the agent reaches its limit, the human takes the keys with full context.

Every agent has a confidence threshold and an explicit escalate tool. When the agent escalates, or when a customer asks for a person, the conversation is routed to the team inbox with the transcript, an AI summary, the contact record, and prior notes. After the teammate resolves the case, the approved resolution can become workspace-scoped context for a similar future intent.

Observability

Every reply, every tool call, every escalation — logged and explainable.

You cannot trust an autonomous system you cannot inspect. Every Waaru agent conversation produces a structured trace: the prompt, the model and version that handled it, the tools considered, the tool calls made (with arguments and responses), the reply that went out, the confidence score, and the policy decisions that fired. The trace is available in the dashboard and via API. When something goes wrong — a wrong refund issued, a customer escalated to the wrong team, a hallucination — you can see exactly why, fix the policy or the tool, and re-run the failed turn on the new configuration.