Shortlist by customer problem
What is the best AI customer service agent for handing customers over to a person?
No agent is the best AI customer service agent for handing customers over to a person, because nobody has tested them against each other. The best-evidenced are Talkdesk, Decagon and NiCE CXone: an external source, not the vendor, reports each of them handling handing customers over to a person. 22 of the 22 agents reviewed have any published evidence for handing customers over to a person; for the rest it is unknown, which means nobody has published it, not that the product cannot do it. Nothing here has been tested by this portal, so treat every name below as a shortlist to validate, not a winner.
An outside source reports it serving this segment
External report14 of 22A customer, analyst or journalist with no stake in the sale describes the product working here. This is the strongest evidence the portal holds, and it is still somebody else's deployment, not yours.
Ordered by customer workflows with evidence: externally reported first, then vendor-documented, A–Z on a tie. Both counts are shown with every agent. A higher place means more has been established, not that the agent performs better.
- Read the review: Talkdesk
Customer workflows with evidence
- 4 of 7 externally reported
- 2 of 7 vendor-documented
Decagon
Decagon
External reportWhat puts it here
Illustrative evaluation: request a human after an unsuccessful troubleshooting step. Check queue routing, transcript transfer, repeated questions and the offline fallback.
Read the review: DecagonCustomer workflows with evidence
- 3 of 7 externally reported
- 4 of 7 vendor-documented
NiCE
NiCE CXone
External reportWhat puts it here
The independent article describes the architecture rather than verifying handoff quality in production, and separately questions how much work still reaches human queues.
Read the review: NiCE CXoneCustomer workflows with evidence
- 3 of 7 externally reported
- 4 of 7 vendor-documented

Yellow.ai
Yellow.ai
External reportWhat puts it here
The escalation documentation notes routing rules cannot name a tool, so escalation must be triggered from the agent's instructions rather than routing logic, and warns that malformed SIP headers can drop calls during voice transfer. Both are authoring constraints with documented workarounds rather than capability gaps.
Read the review: Yellow.aiCustomer workflows with evidence
- 3 of 7 externally reported
- 4 of 7 vendor-documented
Ada
Ada
External reportIllustrative scenario, not a test: a customer requests a person after an unsuccessful answer. Verify that the receiving team gets the conversation and that, outside working hours, the customer receives a clear follow-up path.
Read the review: AdaCustomer workflows with evidence
- 3 of 7 externally reported
- 3 of 7 vendor-documented

Crescendo
Crescendo
External reportWhat puts it here
Handoff here is not only a software escalation: the humans on the receiving end can be supplied by Crescendo itself (via the acquired PartnerHero workforce) or by partner BPOs, so a buyer may be purchasing the escalation tier as well as the AI. The independent article's description of the handoff is sourced to partner and vendor executives quoted by the reporter.
Read the review: CrescendoCustomer workflows with evidence
- 2 of 7 externally reported
- 5 of 7 vendor-documented
NiCE
NiCE Cognigy
External reportWhat puts it here
Cognigy's documentation states its native Cognigy Live Agent handover provider covers chat conversations, and that real-time queue notifications are available only with Cognigy Live Agent.
Read the review: NiCE CognigyCustomer workflows with evidence
- 2 of 7 externally reported
- 5 of 7 vendor-documented

Salesforce
Agentforce
External reportWhat puts it here
Illustrative scenario, not a test: a customer asks to speak to a person. Confirm the destination queue is staffed, the conversation reaches it and the customer receives an off-hours path when nobody is available.
Read the review: AgentforceCustomer workflows with evidence
- 2 of 7 externally reported
- 4 of 7 vendor-documented
LivePerson
LivePerson
External reportWhat puts it here
No independent evaluation of handoff quality in production was located, so this area remains unverified.
Read the review: LivePersonCustomer workflows with evidence
- 2 of 7 externally reported
- 4 of 7 vendor-documented
- Read the review: Five9
Customer workflows with evidence
- 2 of 7 externally reported
- 1 of 7 vendor-documented

Kore.ai
Kore.ai
External reportWhat puts it here
The same CX Today piece flags context preservation across agent handoffs as the thing buyers should verify; Kore.ai's own documentation lists missing conversation_history and incomplete on_human_complete handlers as implementation failure points.
Read the review: Kore.aiCustomer workflows with evidence
- 1 of 7 externally reported
- 5 of 7 vendor-documented

Sprinklr
Sprinklr
External reportThe handover figure originates from a named customer deployment reported by the publication; Sprinklr has not published a methodology for it.
Read the review: SprinklrCustomer workflows with evidence
- 1 of 7 externally reported
- 5 of 7 vendor-documented
Zendesk
Zendesk AI Agents
External reportIllustrative scenario: a customer asks for a human after troubleshooting. Verify contact capture, transcript transfer, destination queue, and the ability to reply on the intended channel. The cited community workaround shows one implementation path, not a general handoff success rate.
Read the review: Zendesk AI AgentsCustomer workflows with evidence
- 1 of 7 externally reported
- 4 of 7 vendor-documented

Genesys
Genesys Cloud CX
External reportWhat puts it here
Marketing-page claim; the specific fields or transcript passed to the human agent are not documented on the sources reviewed. Genesys's About Virtual Agent article now documents automatic bot-conversation summaries and wrap-up codes for transfers to human agents (genesys-cloud-cx-doc-handoff-summary). The YouTube demonstration is a single test-lab build with a scripted transfer after the bot finished, not a customer-requested escalation in a production deployment.
Read the review: Genesys Cloud CXCustomer workflows with evidence
- 1 of 7 externally reported
- 3 of 7 vendor-documented
The vendor documents this segment, and nobody else has written about it
Vendor-documented2 of 22The vendor says it serves this segment. That is a reasonable place to start a shortlist and it is not confirmation, because no independent source has reported on it either way.
Ordered by customer workflows with evidence: externally reported first, then vendor-documented, A–Z on a tie. Both counts are shown with every agent. A higher place means more has been established, not that the agent performs better.
Sierra
Sierra
Vendor-documentedWhat puts it here
Illustrative evaluation: request a person during a failed account update. Check queue routing, transcript and summary delivery, plus what the customer sees when the team is offline.
Read the review: SierraCustomer workflows with evidence
- 2 of 7 externally reported
- 5 of 7 vendor-documented
Gorgias
Gorgias AI Agent
Vendor-documentedWhat puts it here
Handover configuration differs by channel: email and SMS expose customer-notification settings, while chat adds confirmation prompts, wait-time messaging and email capture.
Read the review: Gorgias AI AgentCustomer workflows with evidence
- 0 of 7 externally reported
- 5 of 7 vendor-documented
A limitation is documented for this segment
Caveat documented6 of 22A cited source describes a limit or a bad experience here. It sits below vendor documentation because it is not evidence of fit, and above the agents nobody has written about because somebody at least looked. Read the condition: it may not apply to you at all.
Ordered by customer workflows with evidence: externally reported first, then vendor-documented, A–Z on a tie. Both counts are shown with every agent. A higher place means more has been established, not that the agent performs better.
PolyAI
PolyAI
Caveat documentedWhat puts it here
Both UK public-sector records describe escalation to human agents working in production; the vendor-documented SIP REFER and voicemail-detection limits remain the documented gap.
Read the review: PolyAICustomer workflows with evidence
- 4 of 7 externally reported
- 0 of 7 vendor-documented
Tidio
Lyro
Caveat documentedWhat puts it here
Reports on handoff point both ways: a 2025 Shopify merchant review and a 2025 Trustpilot review of Tidio describe Lyro passing conversations to a person, while a 2024 Trustpilot review of Tidio reports Lyro failing to transfer conversations or create tickets.
Read the review: LyroCustomer workflows with evidence
- 2 of 7 externally reported
- 3 of 7 vendor-documented

Forethought (Zendesk)
Forethought
Caveat documentedWhat puts it here
All three fit verdicts in this record rest on the same single independent article about the acquisition, so they stand or fall together rather than representing independent corroboration.
Read the review: ForethoughtCustomer workflows with evidence
- 2 of 7 externally reported
- 2 of 7 vendor-documented
Intercom
Fin
Caveat documentedWhat puts it here
Illustrative scenario: a customer asks for a person after an unsuccessful answer. Verify the destination inbox, transcript transfer, and after-hours response. A handoff event alone does not show how quickly a human replies.
Read the review: FinCustomer workflows with evidence
- 0 of 7 externally reported
- 5 of 7 vendor-documented

Freshworks
Freddy AI Agent
Caveat documentedThe documented gap is conditional: it applies when the account's AI Agent sessions are exhausted and the agent is deployed through the self-service widget. On other deployments Freshworks states chats are handed to live agents.
Read the review: Freddy AI AgentCustomer workflows with evidence
- 0 of 7 externally reported
- 5 of 7 vendor-documented

HubSpot
Breeze Customer Agent
Caveat documentedNo independent evaluation of handoff quality or escalation accuracy was found. Both community reports date from 2025; HubSpot has since documented custom handoff guidelines and live, async or no-handoff options.
Read the review: Breeze Customer AgentCustomer workflows with evidence
- 0 of 7 externally reported
- 4 of 7 vendor-documented
Nothing published for this segment
Not established0 of 22No reviewed source places these agents here, by the vendor's own documentation or otherwise. That is a gap in the public record, not a finding against the products, and several of them may suit you.
No agent in the catalogue is in this group.
Every claim behind these groups
Each agent above with evidence for handing customers over to a person, and the claims that placed it, with the source type and the date it was checked.
Talkdesk
External reportTalkdesk states Autopilot seamlessly redirects customers to a human agent when it detects a complex case requiring human expertise.Vendor-reported
- Source
- Talkdesk Autopilot — Self-Service Experience
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
talkdesk-fit-handoff-vendor
Trade coverage of Talkdesk AI Agents for Retail reports the agents support routing to in-store specialists, escalating from AI to a human when necessary.Independent report
- Source
- Talkdesk Launches AI Agents for Retail, Goes All In on Agentic AI
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
talkdesk-fit-handoff-indep
Decagon
External reportIllustrative evaluation: request a human after an unsuccessful troubleshooting step. Check queue routing, transcript transfer, repeated questions and the offline fallback.
Decagon documents live-chat escalation, email handoff and voice transfer to human agents.Vendor-reported
- Source
- Integrations (Decagon)
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
decagon-fit-handoff-vendor
Krishan Y.’s August 12, 2026 review says their team can step in when human attention is needed. This corroborates takeover in one self-reported deployment, without measuring routing accuracy or waiting time.Independent report
- Source
- Krishan Y., G2 review syndicated by AWS Marketplace
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
decagon-human-handoff-g2-krishan
NiCE CXone
External reportThe independent article describes the architecture rather than verifying handoff quality in production, and separately questions how much work still reaches human queues.
NiCE states its self-service AI agents hand over to a human agent when the conversation hits escalation parameters, supporting a smooth handover.Vendor-reported
- Source
- AI Agents for Self-Service
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
nice-cxone-fit-handoff-vendor
CX Today describes NiCE's agentic AI as preserving context across channels and across handoffs between AI agents, human agents and back-office systems.Independent report
- Source
- Customer Journey Orchestration Is Getting Serious. Is NiCE Agentic AI Architecture Already Ahead?
- Published
- Checked
- History
- First published · Last changed
- Correct this
- Request a correction with a public source. Claim ID
nice-cxone-fit-handoff-independent
Yellow.ai
External reportThe escalation documentation notes routing rules cannot name a tool, so escalation must be triggered from the agent's instructions rather than routing logic, and warns that malformed SIP headers can drop calls during voice transfer. Both are authoring constraints with documented workarounds rather than capability gaps.
Yellow.ai documents two escalation tools: Escalate to Agent, which routes chat into Inbox queues with round-robin, least-busy or specific-group assignment and passes a conversation summary to the human agent, and Transfer Call, which forwards voice calls over PSTN or SIP with custom headers for context.Vendor-reported
- Source
- Escalation (Yellow.ai docs)
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
yellow-ai-fit-handoff-vendor
A software architect reviewing yellow.ai on G2 writes that it helps “answer FAQs and command problems through bot journeys, and also I can have agents to answer queries where the bot doesn't have a reply”, adding “I support my customers through all mediums of social channels, i.e., Facebook messenger, Whatsapp, Web”.Independent report
- Source
- yellow.ai reviews on G2
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
yellow-ai-g2-handoff-fallback
A software engineer reviewing yellow.ai on G2 says they “could respond to them through bot flows and also if required, connect them with customer service agents”.Independent report
- Source
- yellow.ai reviews on G2
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
yellow-ai-g2-handoff-agents
Ada
External reportIllustrative scenario, not a test: a customer requests a person after an unsuccessful answer. Verify that the receiving team gets the conversation and that, outside working hours, the customer receives a clear follow-up path.
Ada documents live transfers, follow-up tickets, off-hours paths and error fallbacks across its handoff setup.Vendor-reported
- Source
- Handoff management (Ada docs)
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
ada-fit-handoff-vendor
A G2 reviewer wrote in 2019 that when more help is needed, "Ada can hand off the conversation to one of our live chat agents, providing a summary of the issue to the agent for context".Independent report
- Source
- Ada reviews on G2, review by a verified user
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
ada-g2-handoff-summary
A G2 reviewer wrote in 2021 that Ada provides quick first-time resolutions or "creates the needed tickets on Zendesk to ensure our customer contacts are assigned to the relevant teams".Independent report
- Source
- Ada reviews on G2, review by a verified user
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
ada-g2-handoff-zendesk-tickets
A G2 reviewer wrote in 2019 that their Ada chatbot answered many questions and "could easily hand off to our customer support email when needed".Independent report
- Source
- Ada reviews on G2, review by an APM
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
ada-g2-handoff-email
Crescendo
External reportHandoff here is not only a software escalation: the humans on the receiving end can be supplied by Crescendo itself (via the acquired PartnerHero workforce) or by partner BPOs, so a buyer may be purchasing the escalation tier as well as the AI. The independent article's description of the handoff is sourced to partner and vendor executives quoted by the reporter.
Crescendo states that when Concierge escalates it "passes along the entire conversation — customer history, issue context, recommended next action" so the specialist "starts at the answer".Vendor-reported
- Source
- Crescendo — Concierge Agent
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
crescendo-fit-handoff-vendor
CX Today reported on the Alorica–Crescendo partnership that AI "handles the heavy lifting upfront" and that "when escalation is needed, that full context is passed seamlessly to a human agent", with Alorica's 100,000+ employees across 16 countries available to augment Crescendo deployments.Independent report
- Source
- Alorica and Crescendo Partner to Bring AI into Live Enterprise Service Channels
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
crescendo-fit-handoff-ind-alorica
A Gartner Peer Insights reviewer (4 out of 5, June 16, 2026) titled their review of Crescendo "Smooth escalation to human agents, but limited customization restricts flexibility".Independent report
- Source
- Crescendo Reviews — Gartner Peer Insights (AI Agents for Customer Service and Support)
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
crescendo-rev-gartner-handoff
NiCE Cognigy
External reportCognigy's documentation states its native Cognigy Live Agent handover provider covers chat conversations, and that real-time queue notifications are available only with Cognigy Live Agent.
Cognigy documents ten named handover providers for escalating conversations to human agents, including NiCE CXone, Genesys Cloud, Salesforce Service Cloud, Salesforce MIAW, 8x8, RingCentral Engage, Chatwoot, storm and Cognigy Live Agent.Vendor-reported
- Source
- Handover Provider Reference - Overview | Cognigy Documentation
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
nice-cognigy-fit-handoff-vendor
CX Today reports that Cognigy grew via partnerships with contact centre providers including Avaya, Genesys and RingCentral before developing into a standalone platform.Independent report
- Source
- Why Is NiCE Spending Almost $1BN on Cognigy? A Deep Dive
- Published
- Checked
- History
- First published · Last changed
- Correct this
- Request a correction with a public source. Claim ID
nice-cognigy-fit-handoff-ind1
Agentforce
External reportIllustrative scenario, not a test: a customer asks to speak to a person. Confirm the destination queue is staffed, the conversation reaches it and the customer receives an off-hours path when nobody is available.
Service Agents use configured Omni-Channel Flow routing to transfer support requests to service representatives or other destinations.Vendor-reported
- Source
- Agentforce Service Agent (Salesforce Help)
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
agentforce-fit-handoff-vendor
An enterprise reviewer of Agentforce Service (formerly Salesforce Service Cloud) on G2 wrote that Agentforce “escalates for customers when it can't while leaving them with a summary doing so”, replacing deflection tools that “deflected without solving”.Independent report
- Source
- Agentforce Service (formerly Salesforce Service Cloud) reviews on G2
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
agentforce-g2-handoff-summary
Diginomica reported that Wiley’s Agentforce pilot could “tackle registration and payment queries in order to route callers to appropriate handlers, freeing up human agents to work on more complex issues”, and passed conversation summaries to those agents.Independent report
- Source
- Dreamforce 24 - Wiley turns the page on productivity gains with Agentforce (diginomica)
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
agentforce-press-wiley-routing
LivePerson
External reportNo independent evaluation of handoff quality in production was located, so this area remains unverified.
LivePerson states its AI chatbots can 'seamlessly transfer complex customer queries to live agents' and describes a 'Bot Human Tango' model in which both humans and bots contribute to a conversation with handoff from one type of agent to the other.Vendor-reported
- Source
- AI Chatbots — LivePerson
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
liveperson-fit-handoff-vendor
A small-business reviewer of LivePerson on G2 wrote: "AI bots handle simple, repetitive questions automatically. Human agents only step in when needed." The same reviewer added that "AI can gather required information automatically before escalating to a human."Independent report
- Source
- LivePerson reviews on G2 (vendor-level listing)
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
liveperson-g2-handoff-1
Five9
External reportFive9 states that "when escalation is needed, full conversation context transfers instantly to a live agent, so customers never start over."Vendor-reported
- Source
- Five9 AI Agents
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
five9-handoff-context
CX Today reported that with Five9 AI Agents, "contact centers can add guardrails to ensure these conversations still pass through to a live agent" when needed.Independent report
- Source
- Five9 Co-Innovates with ServiceNow, Unveils Its AI Agents
- Published
- Checked
- History
- First published · Last changed
- Correct this
- Request a correction with a public source. Claim ID
five9-handoff-guardrails
Kore.ai
External reportThe same CX Today piece flags context preservation across agent handoffs as the thing buyers should verify; Kore.ai's own documentation lists missing conversation_history and incomplete on_human_complete handlers as implementation failure points.
Kore.ai documents escalation to a human agent that passes session variables and conversation history via a context_for_human block, converting routing metadata to SIP headers on voice channels and forwarding it through the provider's API on digital channels.Vendor-reported
- Source
- Escalation to human agent - Kore.ai Agent Platform documentation
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
kore-ai-fit-handoff-vendor
CX Today reported that Kore.ai's agent platform supports orchestration patterns including handoff and escalation across channels, and quoted the design position that handing off to a human is part of the journey rather than a failure state.Independent report
- Source
- Kore.ai Makes Its Third Wave Play, Multi-Agent Orchestration For CX
- Published
- Checked
- History
- First published · Last changed
- Correct this
- Request a correction with a public source. Claim ID
kore-ai-fit-handoff-cxtoday
A PeerSpot reviewer who has built Kore.ai customer-service chatbots in-house for four and a half years wrote that users "could also connect to a live agent to get any queries sorted which were not handled through the chat agent", and that Kore.ai has "a lot of in-built integrations for live agent connections" including Salesforce, Genesys and ServiceNow.Independent report
- Source
- Kore.ai review by a Conversational AI Developer at a tech vendor with 10,001+ employees (PeerSpot)
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
kore-ai-rev-peerspot-live-agent
A G2 reviewer of Kore.AI (vendor-level listing) wrote that it enables them to build assistants that "answer common questions, guide users through various processes, connect to external APIs, and hand off conversations to human agents when needed".Independent report
- Source
- Kore.AI reviews on G2
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
kore-ai-g2-handoff
Sprinklr
External reportThe handover figure originates from a named customer deployment reported by the publication; Sprinklr has not published a methodology for it.
Sprinklr states its AI Agents "Respond with empathy and precision. Intelligently escalate to human agents when needed."Vendor-reported
- Source
- Sprinklr AI Agents
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
sprinklr-handoff-vendor
CX Today reports the Sprinklr deployment at telecom operator Umniah was cited with a 53% reduction in handovers to human agents.Independent report
- Source
- Sprinklr Service and the Shift from AI Explainability to AI Assurance
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
sprinklr-handoff-umniah
Zendesk AI Agents
External reportIllustrative scenario: a customer asks for a human after troubleshooting. Verify contact capture, transcript transfer, destination queue, and the ability to reply on the intended channel. The cited community workaround shows one implementation path, not a general handoff success rate.
Zendesk states that its AI agents can escalate to human teams with conversation context.Vendor-reported
- Source
- Zendesk AI Agents product overview
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
zendesk-fit-handoff-vendor
Kārlis Stenders describes collecting an issue description conversationally so it appears in the transcript during an Advanced AI Agent messaging handoff. The same post reports form limitations and corrects a custom workaround; it does not quantify reliability.Independent report
- Source
- Kārlis Stenders: Advanced AI Agent escalation form (Zendesk Community)
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
zendesk-human-handoff-transcript-carryover
Genesys Cloud CX
External reportMarketing-page claim; the specific fields or transcript passed to the human agent are not documented on the sources reviewed. Genesys's About Virtual Agent article now documents automatic bot-conversation summaries and wrap-up codes for transfers to human agents (genesys-cloud-cx-doc-handoff-summary). The YouTube demonstration is a single test-lab build with a scripted transfer after the bot finished, not a customer-requested escalation in a production deployment.
Genesys states its Agentic Virtual Agent provides seamless, contextual handoffs with full context when humans step in.Vendor-reported
- Source
- Virtual Agents - Genesys
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
genesys-fit-handoff
In a YouTube tutorial recorded in his own test lab, Seth On Call added a transfer-to-queue step after his Genesys bot flow in an inbound message flow and showed a web-messaging conversation reaching a live agent once the bot had collected the customer's details: "Thanks for chatting with us. And then I should be actually getting routed into the queue. Okay, there we go. So, we'll answer this." He then answered as the agent, with the chat conversation shown in the agent view.Independent report
- Source
- How to Build Bot Flows in Genesys Cloud Architect (Step-by-Step Tutorial) (YouTube, Seth On Call)
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
genesys-cloud-cx-yt-handoff-demo
Sierra
Vendor-documentedIllustrative evaluation: request a person during a failed account update. Check queue routing, transcript and summary delivery, plus what the customer sees when the team is offline.
Sierra’s SDK page documents routing an escalated conversation to a team member with a generated summary. It does not establish how quickly a human answers in a particular contact center.Vendor-reported
- Source
- Agent SDK (Sierra)
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
sierra-handoff-sdk
Gorgias AI Agent
Vendor-documentedHandover configuration differs by channel: email and SMS expose customer-notification settings, while chat adds confirmation prompts, wait-time messaging and email capture.
Gorgias documents built-in handover signals (customer anger, explicit requests for a human, sensitive topics such as self-harm, violence, legal threats or financial account requests), configurable handover topics, and a pre-send draft review where "If it doesn't have enough knowledge to answer reliably...it hands over rather than guessing."Vendor-reported
- Source
- Customize how AI Agent hands over to your team
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
gorgias-fit-handoff-vendor
PolyAI
Caveat documentedBoth UK public-sector records describe escalation to human agents working in production; the vendor-documented SIP REFER and voicemail-detection limits remain the documented gap.
PolyAI documents voice handoff via SIP REFER, SIP INVITE or SIP BYE with escalation context passed through custom X- SIP headers, a Handoff State API endpoint and a Conversations API transcript, plus chat handoff integrations for Salesforce, Zendesk, NICE CXone, Amazon Connect, Webex and Five9.Vendor-reported
- Source
- PolyAI Docs — Voice channel: Handoffs
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
polyai-handoff-vendor
NS&I's algorithmic-transparency record states that PolyAI "can escalate complex or sensitive issues to human agents", integrating with its contact centre via the Genesys DX platform, and that agents are trained to "ensure smooth handover from the bot to human support".Independent report
- Source
- NS&I: PolyAI (UK algorithmic transparency record, GOV.UK)
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
polyai-press-nsi-handoff
The UK Ministry of Justice's algorithmic-transparency record states that a PolyAI voice assistant is in production at the Prison Enquiry Centre for five prisons, answering "frequently asked process questions" from prisoners' friends and families, and that when no FAQ is identified, a safeguarding issue is detected or the caller asks for an agent, "the call is transferred to the next available human agent".Independent report
- Source
- MoJ: PolyAI / Luna (UK algorithmic transparency record, GOV.UK)
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
polyai-press-moj-prison-enquiries
PolyAI's handoff documentation states that with the default SIP REFER method "the utterance may not play before the transfer completes because the REFER fires at the same time as function execution", and that inbound SIP voicemail detection on the destination side is "not available by default" for SIP REFER, BYE or INVITE transfers.Vendor-reported
- Source
- PolyAI Docs — Voice channel: Handoffs
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
polyai-handoff-gap
Lyro
Caveat documentedReports on handoff point both ways: a 2025 Shopify merchant review and a 2025 Trustpilot review of Tidio describe Lyro passing conversations to a person, while a 2024 Trustpilot review of Tidio reports Lyro failing to transfer conversations or create tickets.
Tidio states users can set flexible handoff and escalation rules and that Lyro creates a ticket in the connected support solution so a human agent can answer.Vendor-reported
- Source
- Lyro AI Agent (Tidio)
- Checked
- History
- First published · Last changed
- Correct this
- Request a correction with a public source. Claim ID
lyro-fit-handoff-vendor
A Shopify merchant described the agent as able to answer repetitive questions automatically and escalate questions when needed.Independent report
- Source
- Tidio Live Chat and AI Chatbots reviews (Shopify App Store)
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
lyro-fit-handoff-ind-1
A UK Shopify merchant four months in wrote that in their testing Tidio's AI had been 'spot on with all the questions, some of which have been quite technical', and that 'if its unsure then it will actually handoff to a human'.Independent report
- Source
- Tidio Live Chat and AI Chatbots reviews (Shopify App Store), review by Concrete Lab
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
lyro-rev-handoff-1
A Trustpilot reviewer of Tidio wrote that Tidio combined with Lyro gave them an AI chatbot trained on their help center 'with the ability to pass off the conversation to me'.Independent report
- Source
- Tidio reviews (Trustpilot)
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
lyro-tp-handoff-1
A one-star Trustpilot reviewer of Tidio wrote that they lost hundreds of dollars in chargebacks because Lyro was 'not transferring to operator or creating Tickets', and that their customers blamed their customer service for it.Independent report
- Source
- Tidio reviews (Trustpilot)
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
lyro-tp-handoff-fail
Forethought
Caveat documentedAll three fit verdicts in this record rest on the same single independent article about the acquisition, so they stand or fall together rather than representing independent corroboration.
The vendor states Solve hands conversations off to human agents when the AI cannot resolve an issue or the customer asks for a person, with the Triage agent classifying and routing the ticket to the appropriate agent with full context.Vendor-reported
- Source
- Forethought Solve
- Checked
- History
- First published · Last changed
- Correct this
- Request a correction with a public source. Claim ID
forethought-handoff-vendor
SiliconANGLE reports that the system determines whether an issue can be resolved automatically or requires escalation to a human agent.Independent report
- Source
- Zendesk announces deal to acquire customer support AI startup Forethought
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
forethought-handoff-independent
An IT business analyst reviewing Forethought on G2 wrote that, deployed on their website, "It solves the generic and simple questions of the learners and only redirect to support if it is something that actually requires human interaction."Independent report
- Source
- Forethought reviews on G2, review by an IT business analyst
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
forethought-g2-handoff-redirect
A Trustpilot reviewer on Forethought's company page, contacting an online service about a missing invoice through a support chat "powered by forethought", wrote that the bot "never put me through support and kept going in circles asking the same questions", among them "please describe your issue so I can put you through the right support team", and that they gave up after half an hour.Independent report
- Source
- Forethought reviews on Trustpilot (forethought.ai), review titled 'Infinite loop with a useless chatbot, unable to get through to support'
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
forethought-tp-billing-loop
Fin
Caveat documentedIllustrative scenario: a customer asks for a person after an unsuccessful answer. Verify the destination inbox, transcript transfer, and after-hours response. A handoff event alone does not show how quickly a human replies.
Fin uses configured workflows to route escalations. Intercom states that no escalation offer is shown when no human routing target exists.Vendor-reported
- Source
- Manage Fin AI Agent's escalation guidance and rules (Intercom Help)
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
fin-handoff-vendor
A reviewer on G2 wrote that Fin "solves people's problems autonomously and only escalates when needed", while adding that it sometimes "doesn't seem to understand what the problem is and frustrates users".Independent report
- Source
- Fin reviews on G2
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
fin-g2-fit-small-2
A reviewer on G2 wrote that over chat basic questions are answered automatically and more complex ones are framed for staff, so that "When needed, a human can then take over with all the relevant information."Independent report
- Source
- Fin reviews on G2
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
fin-g2-handoff-chat
A reviewer on G2 wrote that Fin "integrates smoothly with existing help desk workflows" and "provides clear handoffs when human intervention is needed".Independent report
- Source
- Fin reviews on G2
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
fin-g2-handoff-clear
A reviewer on G2 wrote that Fin can be repetitive and that "By the time the conversation is handed over to the human queue, there can be a lot of chat history for us to go through before we can understand the issue".Independent report
- Source
- Fin reviews on G2
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
fin-g2-fit-mid-market-1
Freddy AI Agent
Caveat documentedThe documented gap is conditional: it applies when the account's AI Agent sessions are exhausted and the agent is deployed through the self-service widget. On other deployments Freshworks states chats are handed to live agents.
Freshworks documents an Agent handoff block that transfers a Freddy AI Agent conversation to a live human agent at any point in a workflow, and handover settings to transfer a conversation to a human agent or transfer it outside business hours.Vendor-reported
- Source
- Workflows for AI Agents in Freshdesk (Freshdesk Support)
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
freddy-ai-doc-handoff
A verified AWS customer using Freshchat for a B2C product wrote that customers first interact with its live chatbot, which gathers "their primary requirements, identify what problem they are facing, and then direct them to an agent who can conduct live chat with the customer and provide a resolution."Independent report
- Source
- Freshchat reviews (AWS Marketplace), review by Vikas Kejriwal
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
freddy-ai-rev-aws-handoff
Freshworks' AI Agent Studio FAQ states that when 100% of sessions are consumed the AI agent stops responding and chats are handed over to live agents, but that an AI agent deployed through the self-service widget will stop working and won't be handed over to a live chat agent.Vendor-reported
- Source
- Freddy AI Agent Studio: Configure, Automate, and Scale with AI (Freshdesk Support)
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
freddy-ai-doc-handoff-exhausted
Breeze Customer Agent
Caveat documentedNo independent evaluation of handoff quality or escalation accuracy was found. Both community reports date from 2025; HubSpot has since documented custom handoff guidelines and live, async or no-handoff options.
HubSpot documents that the agent transfers a conversation to a human when its confidence is low, when escalation rules are met, when a visitor explicitly asks for a human, or when a configured handoff phrase is triggered.Vendor-reported
- Source
- Understand the customer agent — HubSpot Knowledge Base
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
hubspot-breeze-fit-handoff-vendor
In an April 2025 HubSpot Community thread, a user without a live-chat team reported that assigning incoming tickets to the agent and, when "the AI can´t answer", to no one meant "I then get a ticket in my help desk" to answer by chat or email.Independent report
- Source
- How do I set custom instructions and ticket conversion in HubSpot Customer Agent? — HubSpot Community
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
hubspot-breeze-forum-ticket-handoff
A HubSpot Community user testing Help Desk with the agent reported in June 2025 that its "transfer" button sometimes "appears during the very first interaction" and "offers the option to speak to an agent even before attempting to answer the question", and that the timing could not be managed.Independent report
- Source
- Possibility to manage Customer Agent's "transfer" button — HubSpot Community
- Published
- Checked
- History
- First published
- Correct this
- Request a correction with a public source. Claim ID
hubspot-breeze-forum-transfer-early
How these groups are formed
- Agents are grouped by what the cited sources establish for this segment, not scored against each other.
- An outside source reporting the product in this segment comes first, then the vendor's own documentation, then a documented limitation, then silence.
- Within a group, the agent with more of the seven customer workflows reported by an outside source comes first, then the one with more vendor-documented workflows; only where both counts tie is the order alphabetical.
- No agent is dropped: the ones with nothing published are named too.
Groups and the order inside them are derived from the cited claims at build time and describe the evidence, not the products. Nothing here has been tested, so a higher group or a higher place inside one means more has been established about an agent, not that it performs better. An agent can be well suited to you and sit in the last group simply because nobody has written about it. Published review-site ratings do not order these groups either: where a record carries one it is cited on the profile, but those ratings score whole products against each other — one vendor's bundled chat widget against another's full help desk — and none of them measures the AI agent on its own.
The methodology page explains why the portal groups evidence rather than scoring products.
Other shortlists
Facts last checked . No agent on this page has been tested by this portal.