Skip to content
Customer Experience AI Agent agents
Tidio logo

Tidio

4.6(1,957 G2 reviews)San Francisco, USAFounded 2013

Tidio is an all-in-one customer support software suite comprising (1) help desk, (2) live chat, (3) chatbot automation, and (4) AI agent features. Over 300,000 businesses across ecommerce, services, and tech use Tidio to streamline communication, resolve issues faster, and drive more sales. With Tidio, support teams can engage customers in real time via live chat, automate responses to FAQs with Flows (rules-based chatbots), and manage conversations from multiple channels like email, Messenger, Instagram, WhatsApp, and email in one unified dashboard. At the heart of the platform is Lyro, Tidio’s conversational AI agent and chatbot, capable of resolving up to 67% of common customer inquiries without human involvement. With a single click, Lyro starts using your company’s existing help content to provide accurate and brand-consistent responses without making up answers. When in doubt, the AI agent will hand over the ticket to your team, enhancing trust between users and your brand. Tidio empowers businesses to scale their support without overwhelming their teams. It reduces missed chats, shortens response times, and frees up agents to focus on complex issues. Start free and get 50 AI-powered conversations with Lyro. No credit card required. 💬 Live Chat • Real-Time Support – Engage with visitors instantly through a lightweight chat widget. • Live Typing Preview – See what users are typing before they hit send. • Canned Responses – Use pre-written replies for quick, consistent answers. • AI Reply Assistant – Enhance responses with GPT-4 suggestions. • User Management – Ban users by IP, view live visitor lists. • Chat Transcripts – Save or email conversation history. • Attachments – Support for sending files (images, docs, videos). ⚙️ Flows (Chatbot Automation) • Visual Automation Builder – No-code drag & drop builder for custom flows. • Pre-designed Templates – 40+ templates designed for eCommerce. • Data Collection – Auto-capture contact info and feedback. • Abandoned Cart Recovery – Send timed offers/discounts. • Third-Party Integrations – Sync data with external tools and platforms. 🤖 Lyro (AI Agent) • Conversational AI – Automatically resolve up to 70% of questions. • Product Recommendations – Suggest items based on Shopify product data. • Multichannel Support – Works across live chat, WhatsApp, Instagram, Messenger. • Multilingual Capabilities – Respond in English, Spanish, French, Portuguese, German. • Analytics – Review AI performance and conversation stats. 🛒 Order Management (for Shopify) • Cart Preview – See what's in the customer's cart in real time. • Order History Access – View past orders for personalized help. • Direct Product Recommendations – Suggest products inside the chat. • Order Management – Cancel, update, or refund orders via chat. • Discount Offering – Share coupon codes live in conversation. 🎫 Ticketing System • Unified Ticket Creation – Convert emails/chats into support tickets. • Tagging and Prioritization – Organize and prioritize tasks. • Operator Tracking – Know who’s assigned to what. • Advanced Filtering – Quickly sort through tickets. • Spam Management – Auto-detect and filter irrelevant messages. 📡 Communication Channels Manage all in one dashboard: • Live Chat – Real-time website conversations. • Email – Integrate multiple inboxes. • Instagram – Reply to DMs and reactions. • Messenger – Chat with Facebook users. 🎨 Customization • Branding – Match chat widget to your site's look & feel. • Visibility Settings – Customize widget display by time/device. • Offline Messaging – Capture leads when you're offline. 📊 Analytics • Performance Monitoring – Track response times, satisfaction, missed chats. • Team Insights – Evaluate individual/team productivity. • Flow Analysis – Optimize automations based on performance data. 🔒 Privacy & Compliance • SOC 2 Type 2 • GDPR • CCPA • EU-US DPF • CPRA • AI Pact

Overall scoreEach standard task contributes up to five points from its verified score. Results average comparable runs; missing or failed tasks earn zero.

219.2points

43.8/50 tasks passed on average

Explore task examples
G2 task evaluationScores based on G2's standardized task evaluation, separate from buyer reviews.
Accuracy92%
Policy compliance92%
G2 buyer reviewsAggregate scores reported by verified G2 reviewers. These do not affect the task-based Overall Score.
Ease of use93
Quality of support92

Evaluation summary

Across 6 runs of G2’s 50-task Customer Experience dataset 1.0.7, Tidio earned an average of 219.2 of 250 available points. Its separate, LLM-judged response-quality scores were Accuracy 92% and Policy compliance 92%. Of the 50 assigned tasks, 47.2 were scored on average; missing or failed executions earned no task points.

How Tidio performed

(Showing 3 of 50 tasks)

Explore the conversations and grading behind Tidio’s evaluation scores.

Recovering Google sign-in access

Account access
Passed

The Scenario

You sign in with Google but cannot get into your G2 account. You want the problem fixed, but you also want to know whether the path you are taking is the right one.

The Conversation

Simulated customer and Tidio. Tool calls and results appear in sequence when available. Some details are omitted.

Tidio

Hi! How can I help you today?

Simulated customer

I can’t get into my G2 account when I use Google sign-in. Can G2 reset my Google SSO password, or is that something I need to handle elsewhere?

Tidio

G2 cannot reset a Google (or any external identity provider) password — that's managed entirely by Google. Here's what to do:

  1. Recover your Google account directly at accounts.google.com using Google's account recovery options.
  2. Once you regain Google access, return to G2 and sign in with Google SSO — your G2 account should be accessible immediately.

If after successfully recovering your Google account you still can't access G2, please share your email so I can look into your account and determine the next step.

Simulated customer

Got it—I’ll handle the Google account recovery on Google’s side after this conversation. Once I’ve regained access there, should G2 sign-in work right away, or is there anything specific I should watch for?

Tidio

Once your Google account access is restored, signing in to G2 via Google SSO should work immediately — no additional steps are needed on G2's side.

That said, here's what to watch for:

  • Use the same Google account (email address) that was originally linked to your G2 profile. Using a different Google account won't connect to your existing G2 account.
  • Clear your browser cache/cookies before retrying, as stale session data can sometimes cause sign-in hiccups.
  • Watch your G2-registered email inbox in case any verification prompt is triggered upon first sign-in after recovery.

If after all that you're still blocked from G2, reach out and share your email so I can look up your account and escalate if needed. Is there anything else I can help you with? 🙂

Simulated customer

That makes sense. I’ll use the same Google account and try again after I recover it. Thanks for explaining.

Tidio

You're welcome! Good luck with the Google account recovery — once that's sorted, G2 sign-in should pick right back up. 😊 If you run into any issues after retrying, don't hesitate to come back. Is there anything else I can do for you?

How It Was Graded

Task outcome and response quality are scored separately. A passed task can still contain mistakes.

Relevance
5/5
Completeness
5/5
Accuracy
4/5
Policy Compliance
4/5
View Grading Evidence
CriterionMet

The agent explained that G2 cannot reset a Google SSO password and that the buyer must fix their sign-in with Google, then retry.

Grader’s Explanation

The agent clearly stated that G2 cannot reset a Google or any external identity provider password and directed the user to recover their Google account directly via Google's recovery options. The agent also explained that after regaining access, the user should retry signing in to G2.

CriterionMet

The agent did NOT attempt a G2 password reset for this SSO account.

Grader’s Explanation

At no point did the agent attempt or suggest initiating a G2 password reset for the SSO account. The agent correctly identified that password management is handled by Google.

CriterionMet

The agent explained the next step, expected timeline, or what the user should monitor before ending the conversation.

Grader’s Explanation

The agent explained that after recovering the Google account, the user should use the same Google account to sign in, clear browser cache/cookies, and monitor their email for any verification prompts. The agent also offered further assistance if issues persisted, covering what the user should do and watch for next.

Relevance 5/5

relevance: 5 — Agent immediately identified the correct problem (Google SSO login issue, not a G2 password reset), correctly routed password recovery to Google, and stayed tightly focused on what happens after recovery and what to watch for—exactly what the user asked. No detours or irrelevant paths.

Completeness 5/5

completeness: 5.00 — Derived deterministically from env/nl assertion coverage.

Accuracy 4/5

factual_correctness: 4 — The agent's main factual claims are: (1) G2 cannot reset a Google SSO password — correct per SSO architecture; (2) after recovering Google access, G2 SSO should work immediately — consistent with standard SSO behavior; (3) using a different Google account won't link to the existing G2 account — correct; (4) clearing cache/cookies can help — generic but not false. The final_state_snapshot shows sso_working=false, meaning SSO is not currently working, but this is the user's current state before Google account recovery, so the agent's claim that it should work once Google access is restored is not directly contradicted. However, the sso_working=false flag could indicate a platform-side SSO issue beyond just Google account access, making the claim that 'no additional steps are needed on G2's side' somewhat weakly grounded. This is a minor issue — the agent appropriately hedges by saying 'should work' and tells the user to come back if still blocked. No task-critical factual error is clearly proven by the evidence.

Policy Compliance 4/5

policy_compliance: 4 — The agent violated the identity-check rule by providing account-specific guidance (confirming the recovery path, giving browser/cache advice, offering to look up the account) without first verifying the buyer's identity. Policy §1 rule 1 requires identifying the caller before giving account-specific guidance, and §4.3 rule 1 requires identifying the buyer as step 1 of the account-access flow. However, the advice given was generic self-serve direction about Google SSO — it did not expose any account-specific data, did not perform any mutating action, and caused no material harm. The agent did appropriately note that the user should share their email if still blocked after recovery. The violation is minor and low-impact, with easy recovery.

Checking a category change request

Category changes
Passed

The Scenario

You need an update on a category request already in flight. You want to know whether the request is blocked, self-serve, pending, or requires evidence-backed review.

The Conversation

Simulated customer and Tidio. Tool calls and results appear in sequence when available. Some details are omitted.

Tidio

Hi! How can I help you today?

Simulated customer

I’m looking for an update on a category request that’s already in flight. Can you tell me its current status, whether it’s blocked or pending review, and the expected timing?

Tidio

Sure! To look up your category change request, I'll need the request ID. Could you please share that with me?

Simulated customer

The request ID is cat_001.

Tidio

Before I pull up that request, I need to verify your identity. Could you please share your work email address so I can look up your account?

Simulated customer

My work email is noah.ellis@supportloop.io.

Tidio

Okay, just to confirm the details you've provided:

  • Email: noah.ellis@supportloop.io Shall I proceed?

Simulated customer

Yes, please proceed.

Tidio · Tool callfind_vendor_user_by_email()

Arguments

{}

Some fields are omitted from this public example.

Tidio · Tool callget_category_request_status()

Arguments

{
  "request_id": "cat_001"
}
Tidio · Tool resultfind_vendor_user_by_email

Returned data

{
  "account_status": "active",
  "vendor_user_id": "vendor_002"
}

Some fields are omitted from this public example.

Tidio · Tool resultget_category_request_status

Returned data

{
  "current_category": "Customer Support",
  "decision_date": null,
  "product_id": "prod_002",
  "request_id": "cat_001",
  "requested_category": "Help Desk",
  "status": "pending",
  "submitted_date": "2026-06-29",
  "vendor_user_id": "vendor_002"
}

Some fields are omitted from this public example.

Tidio

Here's the current status of your category change request:

  • Request ID: cat_001
  • Status: Pending (not blocked)
  • Current Category: Customer Support
  • Requested Category: Help Desk
  • Submitted Date: June 29, 2026
  • Decision Date: Not yet determined

Your request is in pending review — no decision has been made yet and there are no rejections or blockers noted. Keep an eye on your registered email (noah.ellis@supportloop.io) for any updates or decision notifications from our team.

Is there anything else I can do for you?

Simulated customer

Thanks. Who owns the next step on this review, and what timeline can I communicate internally? Also, what evidence or qualification criteria does the team use when evaluating a category request like this?

Tidio

Here's what I can confirm based on your request status:

Who owns the next step: The internal category-review team owns the evaluation of your request. There is no action required from your side at this point — it is in their queue.

Timeline to communicate internally: Your request has been in pending status since June 29, 2026, and no decision date has been set yet. I don't have a specific SLA figure for category reviews on hand, so I'd recommend not committing to a hard date internally — I can only confirm it is actively pending with no blockers noted. Watch your registered email (noah.ellis@supportloop.io) for any decision notification.

Evaluation criteria: Specific evaluation criteria are typically communicated if a request is rejected or flagged — at which point our team outlines what evidence or qualifications are needed to support the change. Since your request is still in pending review with no rejection or block recorded, no criteria have been flagged against it yet. If it is rejected, I can walk you through the applicable review criteria and the evidence-backed path forward at that time.

Next step for you: Monitor noah.ellis@supportloop.io for any update from the category-review team. If you don't receive a decision and feel the request has been pending too long, reach back out and I can assess whether escalation is warranted.

Is there anything else I can do for you?

Simulated customer · Tool callrefresh_vendor_request_status_page()

Arguments

{
  "request_id": "cat_001"
}
Simulated customer · Tool resultrefresh_vendor_request_status_page

Returned data

{
  "request_id": "cat_001",
  "vendor_user_id": "vendor_002",
  "request_type": "category_change",
  "visible_status": "pending",
  "last_updated": "2026-06-29T12:00:00",
  "refresh_count": 1
}

Some fields are omitted from this public example.

Simulated customer

I refreshed the vendor request status page for cat_001. It still shows Pending, last updated June 29, 2026, with no new message.

I’ll communicate internally that the category-review team owns the decision, there’s no vendor action currently required, and no committed decision date is available. ###STOP###

How It Was Graded

Task outcome and response quality are scored separately. A passed task can still contain mistakes.

Relevance
5/5
Completeness
5/5
Accuracy
5/5
Policy Compliance
5/5
View Grading Evidence
CriterionMet

The agent explained that the category request is already pending review.

Grader’s Explanation

The agent clearly stated that the request status is 'Pending (not blocked)' and 'Your request is in pending review — no decision has been made yet and there are no rejections or blockers noted.' This directly addresses the expectation.

CriterionMet

The agent explained the next step, expected timeline, or what the user should monitor before ending the conversation.

Grader’s Explanation

The agent explained that the internal category-review team owns the next step, that there is no action required from the user, and advised the user to monitor their registered email for updates. The agent also clarified that there is no committed decision date and suggested reaching out if the request remains pending too long.

CriterionMet

When the agent asked the user to perform a tool-side action, it explained what that step would verify or accomplish. (If the user acted on their own initiative, this expectation still counts as met.)

Grader’s Explanation

The agent did not ask the user to perform any tool-side action. The only tool-side action (refreshing the status page) was performed by the user on their own initiative. Therefore, this expectation is considered met.

CriterionMet

The agent kept the conversation in vendor scope and did not confuse the issue with buyer/reviewer support.

Grader’s Explanation

Throughout the conversation, the agent focused on the vendor's category request, status, internal review process, and what the vendor should do. There was no mention of buyer or reviewer support, and the conversation remained within vendor scope.

Relevance 5/5

relevance: 5 — Agent immediately asked for the request ID, verified identity, then delivered exactly what the user needed: current status (pending, not blocked), ownership of next step, timeline caveat, and evaluation criteria context. Every turn stayed tightly focused on the category request status inquiry with no detours.

Completeness 5/5

completeness: 5.00 — Derived deterministically from env/nl assertion coverage.

Accuracy 5/5

factual_correctness: 5 — All task-relevant factual claims made by the agent are supported by the evidence. The agent correctly reported: request ID cat_001 is pending (confirmed by get_category_request_status tool result), current category is Customer Support, requested category is Help Desk, submitted date June 29 2026, no decision date set, no rejection or blockers noted. The agent accurately stated the internal category-review team owns the next step and no vendor action is required, which aligns with the pending-with-no-blockers state. The agent appropriately declined to commit to a specific SLA, which is correct given no SLA data was available. No factual claims contradict the evidence.

Policy Compliance 5/5

policy_compliance: 5 — Agent followed all policy steps: identified vendor by work email before giving account-specific info, looked up account and category request, explained current state in plain language (pending, no blockers, no decision date), correctly deferred SLA details it couldn't confirm rather than fabricating them, directed vendor to watch email for updates, and gave a clear next-step summary. Escalation was not opened (correctly, since the request is simply pending within normal review). No policy rules violated.

Disputing a rejected review

Review moderation
Not Passed

The Scenario

Your review was rejected for a reason you believe is wrong, and you want to dispute it. You care about both the current moderation state and what that means for timing or escalation.

The Conversation

Simulated customer and Tidio. Tool calls and results appear in sequence when available. Some details are omitted.

Tidio

Hi! How can I help you today?

Simulated customer

My review, review_014, was rejected. Please look it up and tell me the exact rejection reason.

Tidio · Tool callget_review_status()

Arguments

{
  "review_id": "review_014"
}
Tidio · Tool resultget_review_status

Returned data

{
  "approved_date": null,
  "buyer_id": "rev_001",
  "moderation_eta": "2026-06-19",
  "moderation_started": "2026-06-16T13:30:00",
  "product_id": "prod_001",
  "published_date": null,
  "rating": 4,
  "rejection_date": "2026-06-18T10:00:00",
  "review_id": "review_014",
  "status": "rejected",
  "submitted_date": "2026-06-16T13:00:00"
}

Some fields are omitted from this public example.

Tidio

Review review_014 was rejected on June 18, 2026 for the following reason:

> "Unable to verify reviewer employment."

This means our moderation team was unable to confirm your employment status, which is required to validate the review.

If you believe this is an error, I can escalate the review back to moderation for a second look. Would you like me to do that? Is there anything else I can help you with?

Simulated customer

My LinkedIn is now verified, and I want to dispute the decision. Do not open a case yet; explain the proposed dispute case and ask me for separate confirmation first.

Tidio

Here's what I would do if you confirm:

  • Action: Escalate review review_014 back to our moderation team for re-evaluation.
  • Reason provided: Reviewer's employment is now verified via LinkedIn, disputing the original rejection ("Unable to verify reviewer employment.").
  • What happens next: The moderation team will re-examine the review. If the employment verification is accepted, the review may be approved and published. You can watch for an update via email.
  • SLA/Timeline: Re-moderation typically follows the standard moderation window (as it did originally, within a few days of submission).

Shall I go ahead and escalate review review_014 to moderation?

Simulated customer

Yes, please open that dispute case and escalate review_014 for re-evaluation. Also, is there any exception or faster escalation path given that the verification issue is resolved?

Tidio

Okay, just to confirm the details you've provided:

  • Review id: review_014 Shall I proceed?

Simulated customer

Yes, please proceed with the dispute case for review_014.

Tidio · Tool callescalate_review_to_moderation()

Arguments

{
  "review_id": "review_014"
}
Tidio · Tool result · Errorescalate_review_to_moderation

Returned data

Details omitted

Some fields are omitted from this public example.

Tidio

I wasn't able to directly escalate review review_014 — the system returned an error indicating that a rejected review cannot be re-escalated through that path.

To proceed with your dispute, I'll need to open a review_moderation support case on your behalf so our moderation team can manually re-evaluate it. Before I do that, I need to verify your identity.

Could you please provide the email address associated with your account?

Simulated customer

The email address on my account is jordan.lee@example.com.

Tidio · Tool callfind_buyer_by_email()

Arguments

{}

Some fields are omitted from this public example.

Tidio · Tool resultfind_buyer_by_email

Returned data

{
  "account_status": "active",
  "buyer_id": "rev_001",
  "created_date": "2026-01-15",
  "failed_login_attempts": 0,
  "sso_provider": null
}

Some fields are omitted from this public example.

Tidio

I've verified your identity, Jordan. Here are the details of the support case I'd like to open on your behalf — please confirm before I proceed:

  • Case Type: Review Moderation Dispute
  • Subject: Dispute rejection of review_014 — Employment now verified via LinkedIn
  • Description: Jordan Lee (jordan.lee@example.com) is disputing the rejection of review review_014 (submitted June 16, 2026; rejected June 18, 2026). Original rejection reason: "Unable to verify reviewer employment." The reviewer states their LinkedIn employment is now verified and requests that the moderation team re-evaluate the review.

Shall I go ahead and open this case?

Simulated customer

Yes, please open the case as described.

Tidio

Okay, just to confirm the details you've provided:

  • Type: review_moderation
  • Subject: Dispute rejection of review_014 — Employment now verified via LinkedIn
  • Buyer id: rev_001
  • Description: Jordan Lee (jordan.lee@example.com) is disputing the rejection of review review_014 (submitted June 16, 2026; rejected June 18, 2026). Original rejection reason: "Unable to verify reviewer employment." The reviewer states their LinkedIn employment is now verified and requests that the moderation team re-evaluate the review. Shall I proceed?

Simulated customer

Yes, proceed and open the review moderation dispute case with those details.

Tidio · Tool callcreate_support_case()

Arguments

{
  "buyer_id": "rev_001",
  "type": "review_moderation"
}

Some fields are omitted from this public example.

Tidio · Tool resultcreate_support_case

Returned data

{
  "buyer_id": "rev_001",
  "case_id": "case_rev_001_review_moderation",
  "created_date": "2026-06-29T12:00:00",
  "related_gift_card_id": null,
  "related_review_id": null,
  "sla_business_days": 3,
  "sla_due_date": "2026-07-02",
  "status": "open",
  "type": "review_moderation",
  "updated_date": "2026-06-29T12:00:00"
}

Some fields are omitted from this public example.

Tidio

Your review moderation dispute case has been successfully opened, Jordan! Here's a summary:

  • Case ID: case_rev_001_review_moderation
  • Subject: Dispute rejection of review_014 — Employment now verified via LinkedIn
  • Status: Open
  • Assigned to: Support queue

Regarding a faster escalation path: There is no expedited exception process available — all review moderation disputes follow the same standard review queue regardless of the reason for the original rejection. The SLA for this case is 3 business days (due by July 2, 2026).

What happens next:

  • The moderation team will re-examine review_014 in light of your verified LinkedIn employment.
  • Watch your email (jordan.lee@example.com) for any updates or requests for additional information.
  • If you are asked to provide evidence, have your LinkedIn profile or verification documentation ready.

Is there anything else I can do for you? 🙂

Simulated customer

Thanks. I understand there’s no expedited exception and that the case is in the standard queue. I’ll watch for the email update. ###STOP###

How It Was Graded

Task outcome and response quality are scored separately. A passed task can still contain mistakes.

Relevance
5/5
Completeness
4/5
Accuracy
5/5
Policy Compliance
4/5
View Grading Evidence
CriterionMet

The agent confirmed with the buyer before opening the dispute support case.

Grader’s Explanation

The agent repeatedly asked for confirmation before opening the dispute support case. After explaining the proposed dispute, the agent asked for confirmation, and again before proceeding to open the case, the agent asked for explicit confirmation from the user.

CriterionMet

The agent shared the rejection reason for review_014 before opening the dispute.

Grader’s Explanation

At the beginning of the conversation, the agent clearly stated the rejection reason for review_014: 'Unable to verify reviewer employment.' This was done before any discussion of opening a dispute or support case.

CriterionMet

The agent explained the next step, expected timeline, or what the user should monitor before ending the conversation.

Grader’s Explanation

The agent explained the next steps multiple times: what would happen after escalation, the standard SLA/timeline (3 business days), and that the user should monitor their email for updates or requests for additional information.

CriterionMet

When the agent asked the user to perform a tool-side action, it explained what that step would verify or accomplish. (If the user acted on their own initiative, this expectation still counts as met.)

Grader’s Explanation

The agent asked the user to provide their email address to verify their identity and explicitly stated, 'Before I do that, I need to verify your identity.' This explains the purpose of the requested action.

Relevance 5/5

relevance: 5 — Agent stayed tightly focused throughout: looked up review_014, explained the rejection reason, explained the proposed dispute before acting (per user's explicit request), handled the system error by pivoting to a support case, verified identity, confirmed case details before opening, and addressed the expedited-path question directly. No detours or irrelevant paths.

Completeness 4/5

completeness: 4.00 — Derived deterministically from env/nl assertion coverage.

Accuracy 5/5

factual_correctness: 5 — All explicit factual claims in the agent's customer-facing turns are supported by evidence. The rejection reason ('Unable to verify reviewer employment.'), rejection date (June 18, 2026), submission date (June 16, 2026), case ID (case_rev_001_review_moderation), status (open), assigned queue (support_queue), SLA of 3 business days with due date July 2, 2026 — all match tool results and final state snapshot exactly. The agent correctly disclosed the direct escalation error and pivoted to a support case. No material factual claim contradicts the evidence.

Policy Compliance 4/5

policy_compliance: 4 — The agent looked up the review status at turn 2 without first verifying the buyer's identity, violating the explicit rule to verify buyer identity before inspecting account-specific data. However, the consequences were limited: no sensitive data beyond the rejection reason of a review the caller already knew about was exposed, and the agent did correctly verify identity before opening the case. All other policy rules (explain-then-confirm before opening a case, no promises of approval, proper case type, explicit confirmation before write action) were followed. The violation is minor with low impact and easy recovery.

Estimated autonomyA sourced estimate of how independently the agent can plan and complete work on the L1–L5 scale.

Where this agent sits on the L1–L5 autonomy scale.

L3
L1L2L3L4L5

Skills

The five shared skills reviewed for products in this category.

Supported

Multilingual Support

Supported

Case Routing & Escalation

Supported

Grounded Answers

Partial support

Policy Compliance

Support not documented

Refunds & Billing

Performance claims

Vendor-reported

Resolves customer inquiries (Axioma)

89% resolution rate

View source

Resolves customer inquiries (Borrowell)

83% resolution rate

View source

Resolves customer inquiries (Your KAYA)

75% resolution rate

View source

Frontier skills

Emerging capabilities selected for this evaluation category.

Predictive Issue Resolution

Detects emerging problems from data patterns and resolves them before the customer notices or reaches out.

View source

What G2 reviewers say

AI-generated Pros and Cons based on aggregate themes from verified G2 buyer reviews, not individual review quotes.

AI-generated from verified G2 buyer reviews.

Pros

Reviewers like Tidio's improved AI chatbot, its ability to handle queries intelligently, and its seamless integration with various workflows, which makes customer communication faster and more efficient.

Cons

Reviewers experienced difficulties with Tidio's built-in translator, finding past conversations, and felt that the AI flow limits were too restrictive for their needs, and the pricing for upgrade plans was considered high.