Conversational setup with Master Agent
Users describe what they need in plain English, and the Master Agent asks about rules, limits, and tone, then builds the agent, connects tools, and writes a test set to show results before launch.
TOOL PROFILE TOOLAI
Lyro
AI customer service agent that resolves support, sales, and post-purchase conversations across channels
View full image
THE BIG PICTURE
About Lyro
Lyro is an AI customer service agent from Tidio that is positioned as a hire for a support team rather than a single helpdesk bot. According to the official site, it handles work across support, sales, and engagement, and can be invited into the tools a team already uses, including Zendesk, Salesforce, Intercom, HubSpot, and Tidio. The company says setup is conversational: a user describes the goal, and a Master Agent asks clarifying questions and turns the answers into a working configuration. Lyro is presented as running on the customer's chosen models and rules, with separate agents for different jobs.
The product is built around resolving conversations from a company's own knowledge rather than only deflecting them. Lyro answers from help articles and shows the source it used, and it can hand a conversation to a human with the full thread when it cannot finish. It supports multiple channels, including live chat, email, WhatsApp, Instagram DMs, Facebook Messenger, Slack, voice, and an API, with the same knowledge and rules applied across them. The site also describes agentic actions: once tools are connected, an agent can look up orders, open tickets, update records, and run workflows in connected systems.
Lyro is offered by Tidio and is described as usable by support, sales, and onboarding teams, as well as by developers who want to call agents through a REST API or configure them from AI builders via an MCP server. The official pages emphasize control over prompts, models, channels, guardrails, and handoffs, plus analytics and quality-assurance features such as evals and a Sentry auditor. Pricing is credit-based, with credits drawn down when Lyro resolves work rather than per seat.
A CLOSER LOOK
See it in action
Explore product screens and published examples. Open any image for a closer look.
An agent being configured in Lyro: crawling a site, syncing docs, and re-running its evals
Product interface published on the official website.
Lyro resolving a customer request in the chat widget
Product interface published on the official website.
Lyro highlighting knowledge gaps found in past conversations
Product interface published on the official website.
Lyro checking an order status across connected tools
Product interface published on the official website.
Lyro · Interface preview
WHAT YOU CAN DO
A toolkit worth exploring
Get to know the capabilities. Find your own way to use them.
Multiple specialist agents
Teams can create separate agents for support, sales, onboarding, and other customer work, each with its own role, rules, knowledge, and tools, with routing to the right agent.
Knowledge-grounded answers with source links
Lyro answers from company help articles and shows which article it used. Strict mode restricts answers to company content only, while full mode can fall back on general knowledge.
Agentic actions across connected tools
With 1,000+ connectors, MCP servers, and custom HTTP tools, agents can perform actions such as checking orders, opening tickets, updating records, and running workflows, with each action labeled read, write, or destructive before approval.
Multi-channel coverage
The same setup can run across live chat, email, WhatsApp, Instagram DMs, Facebook Messenger, Slack, voice, and API, with per-channel formatting and language settings.
Human handoff and unified inbox
Lyro hands off to a live teammate, a helpdesk ticket, or a phone transfer with the full thread, and teams can work chat, email, WhatsApp, phone, and API conversations in one queue.
Quality assurance and evals
Lyro reviews real conversations to find unanswered questions, drafts missing help articles, and lets teams turn bad answers into test cases that gate publishing.
Analytics and reporting
Reports cover resolution rate, answer rate, response time, satisfaction, grounding share, and tool performance, with drill-down from charts to the conversations behind them and CSV export.
MADE FOR YOUR WORKFLOW
Where it fits into your day
Resolving routine support requests
Lyro can answer common questions from help articles and close routine requests without a handoff, escalating only when it cannot finish.
Order and delivery status inquiries
With store and carrier tools connected, an agent can look up an order and tracking information and reply with delivery status.
Internal IT or HR support in Slack
Lyro can run inside a company's Slack as an internal agent answering employee questions about benefits, payroll, software access, and onboarding.
Document drafting and updates via Google Docs
Through the Google Docs MCP integration, Lyro can search and read documents, create docs from markdown, insert text, tables, and images, and export to PDF.
YOUR FIRST STEPS
From first click to first result
Start with free credits
Begin with 10,000 free credits to explore how Lyro works before committing to paid usage.
Describe your business to the Master Agent
Explain what you need in plain English; the Master Agent asks about rules, limits, and tone, then builds the agent and connects tools.
Connect your channels and tools
Connect the helpdesk, messaging channels, and tools you already use, such as Zendesk, Salesforce, Gmail, WhatsApp, or custom HTTP/MCP tools.
Test before launch
Use the private playground and generated test cases to see how the agent answers and which tools it calls before customers interact with it.
Go live and monitor
Publish the agent, track resolution and quality metrics, and review conversations to find gaps and improve knowledge over time.
PLAN YOUR NEXT STEP
A plan for the way you work
Credit-based pay-as-you-go wallet: $1 equals 1,000 credits, and credits are drawn down only when Lyro resolves a conversation, at each model's own rate. The pricing page shows a $200/mo example for a 200,000-credit selection. An Enterprise plan is available on request with private infrastructure, bring-your-own model contracts and API keys, guaranteed SLA and resolution rate, and a dedicated team.
PLAN
Pay as you go
Self-service wallet-based plan. $1 equals 1,000 credits, and each model burns credits at its own rate. Credits draw down only when Lyro resolves a conversation. The pricing page shows a $200/mo example for a 200,000-credit selection.
- Pay only for what you spend, no fixed fees
- Native Claude Code and Codex integration
- Swap Claude, GPT, Gemini per agent or per skill
- Available models include Claude Haiku 4.5, Claude Opus 4.7, GPT-5 mini, Gemini Flash, Claude Sonnet 4.6, GPT-5, and Gemini 2.5 Pro
PLAN
Enterprise
Contact sales for pricing on your usage profile. Use your own model contract with Anthropic, OpenAI, or Google, with Lyro routing through your keys and billing you directly.
- Private cloud instance in your preferred region
- Connect custom model with your own API keys
- Guaranteed SLA and AI resolution rate
- Dedicated forward deployed engineer and customer success manager
- Training for your team and a dedicated Slack channel
- SSO
Prices, usage limits and terms can change. Confirm the latest details on the tool's official website before subscribing.
Official pricing page confirms the wallet model and the $200/mo example tied to a 200,000-credit selection; users can top up any amount, and Enterprise pricing requires contacting sales.
Sources checked
What is a credit and when am I charged?
A credit is the unit you pay with. $1 buys 1,000 credits, and Lyro draws them down as it resolves conversations, with light models drawing fewer credits and stronger ones drawing more. You are charged only when a conversation is resolved; there is no platform fee, no per-seat pricing, and no minimum.
Can I use different models for different tasks?
Lyro allows model selection at both the agent and individual-skill level. This lets you assign a lower-cost model to routine work and reserve a more capable model for tasks that require it.
What happens when Lyro cannot resolve something?
It hands the conversation to your team with the full history and context. Handoffs are not resolutions, so they do not spend credits.
Is there a free trial?
Yes. You can build your agent and test it against your past tickets before spending anything, and credits only go toward live resolutions. The site also mentions starting with 10,000 free credits.
Can I cap my monthly spend?
Yes. Lyro can only spend the credits you have topped up, and you can set alerts and hard limits so the bill does not surprise you.
What is the difference between Self-service and Enterprise?
The self-service option charges against prepaid credits and does not require a contract. Lyro describes its Enterprise offer as adding a dedicated team, isolated infrastructure, customer-managed model credentials and contracts, plus contractual commitments for service levels and resolution rates.
Can Lyro share a Google Doc or change its permissions?
No. Sharing and access control are not in the Google Docs toolkit. Lyro can produce something shareable, such as a copy of the document or a PDF export, while sharing itself stays with the document owner.
FROM THE COMMUNITY
What has your experience been?
Tried this tool?
Sign in to share your experience and help others find the right tool.
YOUR NEXT DISCOVERY
More tools to explore
Domesticating ai for your business
Use ai as your catalyst for sales, support and development functions with on-premise infrastructure and complete business privacy.
SwiftDM
Our all-in-one platform streamlines the process of finding customers and initiating personalized conversations, all with a touch of automation. All you need to do is press send.
Wing Assistant
Wing is a 24/7 assistant powered by humans & AI that can handle anything, as long as it's legal and possible. All you have to do is place a request on our app, or text us, and we'll handle the rest. 😻
goML
Main features: Design, build, and manage generative AI applications with 6 enterprise-grade LLM boilerplates (Conversational Agent, Search Engine, Agentic Workflows, Data Analytics & Insights, Content Generation, Data Synthesis), enabling Gen AI pilot builds in 8 weeks. Target users: Institutional clients in healthcare, life sciences, and financial services. Key advantages: 50+ proven implementations, 10X faster development, AWS strategic partner (Top 10 global Gen AI innovator), deep domain expertise. Typical use cases: Clinical decision acceleration (10X), pharma compliance audit (99% faster), disease diagnosis improvement (80%), real-time financial fraud detection (99% faster), automated portfolio generation ($6M revenue increase), early glaucoma detection (90% faster). Pricing: Contact for custom quotes.
MAKE YOUR NEXT MOVE
Ready to explore Lyro?
Visit the official website to explore the latest features and get started.
Lyrogetlyro.ai
Visit website