Homeworks moved from keyword-rule bots that resolved only 20 to 30% of chats to Intercom's Fin. Intercom reports an 85% Fin resolution rate and 92% involvement.
Reported outcomes
Fin resolution rate
85%
Source [1] · self-reported
prior bot resolution
20 to 30% of chats
Source [1] · self-reported
Outcomes are reported exactly as stated by the source; we have not independently audited them.
How it works
- Fin answers inbound support conversations using the company's help content.
- Hands unresolved conversations to human agents.
Risks & compliance
- Incorrect answers to customers; escalation paths needed
- Vendor-published results; not independently audited
Build this yourself
Tools mentioned & how to build it
Disclosure: Some links may earn us a commission; it never affects grades. Tools are listed by fit to this case, never by payment.
Tools mentioned
- Fin AI Agent (Intercom)
Intercom's customer-service AI agent; the most-documented tool in the casefile.
Build a version yourself
- HubSpot (Breeze agents)
SMB-friendly CRM with Breeze AI agents for prospecting and support. - n8n
Open-source workflow automation with AI agent nodes; self-host or cloud. - Relevance AI
Build an 'AI workforce' of agents, e.g. BDR agents that research and book meetings.
Sources
“every reply had to be built manually with keyword rules, and the bot resolved only 20 to 30% of chats.”Homeworks and Fin
Grade rationale: Named organization with a quantified outcome from the vendor or the organization itself (self-reported). Automated check on Oct 17, 2026: 1/1 quotes and 2/2 outcome claims matched the source. Compiled by the Agent Casefile research desk (AI-assisted; see methodology). Spot an error? Request a correction.
