Intercom and Fin
UK SOFTWARE PROFILE
Intercom and Fin
Intercom combines a customer-support workspace with Fin, an agent that can use business knowledge and carry out multi-step procedures.
One product. Different jobs.
Each score uses that category's criteria. Compare products within a category, rather than comparing scores across unrelated tasks.
AI agent platforms ↗
67–98/100 documented fit69% evidence coverageCompare in this category ↗Pricing & practicalities
Model your total cost ↗Published starting point
Customer service software
US$0.99Fin usage · Fin outcome · usage billing
VAT basis not stated
US$0.99 per outcome, with helpdesk seats or standalone minimum commitments as applicable. A procedure handoff can count as an outcome.
Check current price ↗AI agent platforms
US$0.99Fin usage · Fin outcome · usage billing
VAT basis not stated
US$0.99 per outcome, with helpdesk seats or standalone minimum commitments as applicable. A procedure handoff can count as an outcome.
Check current price ↗Consider before choosing
- Model the definition of a billable outcome, including configured handovers.
- Seat subscriptions and Fin usage are separate cost components.
Connected workflows
- APIs
- MCP
- Data connectors
- Existing helpdesks
Confirm the integration's direction, permissions, plan and sync behaviour with the supplier.
BEHIND THE AI CLAIM
AI capabilities
Fin performs knowledge-based conversations and connected procedures, with testing and performance analysis.
Documented capabilities
- Knowledge answers
- API/data-connector/MCP actions
- Regression tests and simulations
- AI insights and QA
Plans, limits & questions
- An outcome is not always a verified customer resolution.
- Inspect action permissions and failure handling in a trial.
Feature-by-feature evidence
Customer service software — 20 scored checks
| Capability & demo question | Intercom and Fin42–98/100 documented fit |
|---|---|
Core workflowShared inbox and tickets7.0 points availableAsk in the demoCreate a case from email and assign it without duplicate ownership. | ✓ Supported Essential includes shared inbox and tickets. 7.0 / 7.0 pointsEvidence ↗ |
Core workflowCustomer interaction history7.0 points availableAsk in the demoShow the customer's previous conversations while handling the new case. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–7.0 / 7.0 points |
Core workflowAutomatic ticket routing7.0 points availableAsk in the demoAssign a ticket according to type, priority or team. | ✓ Supported Advanced provides round-robin workflows. 7.0 / 7.0 pointsEvidence ↗ |
Core workflowSearchable knowledge base7.0 points availableAsk in the demoPublish an answer and find it as a customer and as an agent. | ✓ Supported Plans include a help centre. 7.0 / 7.0 pointsEvidence ↗ |
Core workflowOperational support reports7.0 points availableAsk in the demoInspect first-response time, backlog and resolution trends. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–7.0 / 7.0 points |
Workflow depthSLA and escalation rules4.0 points availableAsk in the demoDemonstrate a breached target and the next escalation. | ✓ Supported Expert includes SLA management. 4.0 / 4.0 pointsEvidence ↗ |
Workflow depthBusiness-hours calendars4.0 points availableAsk in the demoApply a team working-hours calendar to a response target. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–4.0 / 4.0 points |
Workflow depthConnected service channels4.0 points availableAsk in the demoContinue a case with history from at least two channels. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–4.0 / 4.0 points |
Workflow depthInternal collaboration4.0 points availableAsk in the demoAdd a private note or involve another team without exposing it to the customer. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–4.0 / 4.0 points |
Workflow depthReusable response actions4.0 points availableAsk in the demoApply a reusable reply that also updates ticket fields. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–4.0 / 4.0 points |
Workflow depthCustom case fields4.0 points availableAsk in the demoMake an issue type available for routing and reporting. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–4.0 / 4.0 points |
Workflow depthAgent roles and permissions4.0 points availableAsk in the demoPrevent a junior agent changing restricted settings or records. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–4.0 / 4.0 points |
Workflow depthTicket change history4.0 points availableAsk in the demoSee who changed ownership, priority or status. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–4.0 / 4.0 points |
Workflow depthService API or integrations4.0 points availableAsk in the demoCreate or update a case in a connected business system. | ✓ Supported Retrieve conversations with customer, assignee, message and conversation-part data through the authenticated API. 4.0 / 4.0 pointsEvidence ↗ |
Workflow depthCustomer satisfaction feedback4.0 points availableAsk in the demoCollect feedback linked to the closed case. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–4.0 / 4.0 points |
Workflow depthPortable case data5.0 points availableAsk in the demoExport a case with its messages and useful identifiers. | ◐ Limited The conversation API returns the latest 500 parts; this endpoint alone does not guarantee a complete export of longer cases. 2.5 / 5.0 pointsEvidence ↗ |
Workflow depthBot-to-agent continuity5.0 points availableAsk in the demoTransfer a bot conversation with context and customer details. | ✓ Supported Fin procedures can hand off to people. 5.0 / 5.0 pointsEvidence ↗ |
AIGrounded AI reply assistance5.0 points availableAsk in the demoDraft a response from the case and approved knowledge. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–5.0 / 5.0 points |
AIAI summaries and classification5.0 points availableAsk in the demoSummarise the case or identify its intent before routing. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–5.0 / 5.0 points |
AIControlled AI resolution5.0 points availableAsk in the demoResolve a supported issue and escalate an unsupported request to staff. | ✓ Supported Fin answers and performs configured service procedures. 5.0 / 5.0 pointsEvidence ↗ |
“Not verified” means the recorded evidence does not settle this specific check. It does not mean the feature is absent. Read the scoring method.
AI agent platforms — 20 scored checks
| Capability & demo question | Intercom and Fin67–98/100 documented fit |
|---|---|
Core workflowBusiness knowledge grounding7.0 points availableAsk in the demoAnswer a question using an approved document or help article. | ✓ Supported Fin uses approved policies and business information. 7.0 / 7.0 pointsEvidence ↗ |
Core workflowBusiness-system actions7.0 points availableAsk in the demoRetrieve or update a permitted record through an integration. | ✓ Supported Connectors, APIs and MCP perform external actions. 7.0 / 7.0 pointsEvidence ↗ |
Core workflowMulti-turn task completion7.0 points availableAsk in the demoComplete a request that needs clarification over several turns. | ✓ Supported Procedures handle multi-step requests. 7.0 / 7.0 pointsEvidence ↗ |
Core workflowHuman escalation7.0 points availableAsk in the demoEscalate an unsupported request with its conversation context. | ✓ Supported Procedures support human handoff. 7.0 / 7.0 pointsEvidence ↗ |
Core workflowConversation and action logs7.0 points availableAsk in the demoInspect the agent's messages and the actions it attempted. | ✓ Supported Fin provides operational monitoring and alerts. 7.0 / 7.0 pointsEvidence ↗ |
Workflow depthKnowledge source management4.0 points availableAsk in the demoAdd, update and remove a source used by the agent. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–4.0 / 4.0 points |
Workflow depthRestricted tool permissions4.0 points availableAsk in the demoLimit which systems and actions this agent can use. | ✓ Supported Restrict exposed response fields, eligible audiences and whether Fin may trigger a connector automatically. 4.0 / 4.0 pointsEvidence ↗ |
Workflow depthApproval before consequential actions4.0 points availableAsk in the demoRequire a person to approve an action before it executes. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–4.0 / 4.0 points |
Workflow depthFailed-tool handling4.0 points availableAsk in the demoSimulate a failed integration and show a useful recovery path. | ✓ Supported On authentication failure, dynamic tokens can refresh and retry once; failed refreshes are logged and repeated failures trigger a circuit breaker. 4.0 / 4.0 pointsEvidence ↗ |
Workflow depthCustomer or user authentication4.0 points availableAsk in the demoProtect a private-record lookup from an unauthenticated visitor. | ✓ Supported Enable customer authentication before a connector accesses or displays private data. 4.0 / 4.0 pointsEvidence ↗ |
Workflow depthOperational guardrails4.0 points availableAsk in the demoSet a restricted topic or action and test it. | ✓ Supported Required inputs and restricted response fields constrain connector use and exposed data. 4.0 / 4.0 pointsEvidence ↗ |
Workflow depthMultiple deployment channels4.0 points availableAsk in the demoUse the agent in two supported channels. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–4.0 / 4.0 points |
Workflow depthVersions and environments4.0 points availableAsk in the demoTest a change separately before promoting it. | ✓ Supported Connector changes remain drafts until published; preview supports test-user validation. 4.0 / 4.0 pointsEvidence ↗ |
Workflow depthRepeatable evaluation cases4.0 points availableAsk in the demoRun a saved set of cases after changing the agent. | ✓ Supported Saved tests and simulations check changes. 4.0 / 4.0 pointsEvidence ↗ |
Workflow depthTask-outcome analytics4.0 points availableAsk in the demoReport successful actions, escalations and failed requests separately. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–4.0 / 4.0 points |
Workflow depthConversation-data export5.0 points availableAsk in the demoExport relevant logs for independent review. | ◐ Limited Conversation transcripts and AI metadata are retrievable, with a 500-part limit per conversation and feature-dependent AI fields. 2.5 / 5.0 pointsEvidence ↗ |
Workflow depthUsage and cost visibility5.0 points availableAsk in the demoInspect usage and set or explain the spending limit. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–5.0 / 5.0 points |
AIModel choice or configuration5.0 points availableAsk in the demoShow how model behaviour or choice is configured for the task. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–5.0 / 5.0 points |
AINatural-language agent building5.0 points availableAsk in the demoDescribe an agent and inspect the generated configuration. | ? Not verified Exact workflow not verified in the reviewed material; request a demonstration. 0.0–5.0 / 5.0 points |
AIAI-assisted quality review5.0 points availableAsk in the demoIdentify weak conversations or score outcomes with configurable criteria. | ✓ Supported AI QA surfaces trends and improvement recommendations. 5.0 / 5.0 pointsEvidence ↗ |
“Not verified” means the recorded evidence does not settle this specific check. It does not mean the feature is absent. Read the scoring method.