Loading post…
IntercomDeclan IvoryAnnouncement
What’s new with Fin 3: The best AI Agent for complex queries across every channel
Summary
Fin 3 is presented as an AI Agent for customer service focused on increasing automation rate by handling complex queries end-to-end across more channels. Procedures combine natural-language instructions with data connectors, conditional steps, code snippets, and approval checkpoints, allowing teams to encode standard operating procedures with varying levels of control. Simulations provide multi-turn testing for different customer segments and scenarios, while Fin Voice, Slack, and Discord expand deployment options. Insights upgrades add CX Score Reasons, Topic Trends, and AI-powered Suggestions that surface quality changes, topic shifts, and content improvements. The announcement says Fin 3’s broader goal is to increase the share of overall support workload it handles, beyond a resolution-rate metric that had reached 66% on average across more than 6,000 customers.
Context
Fin evolved from Fin 1, which used knowledge content for informational queries, to Fin 2, which demonstrated human-quality service. Since Fin 2 launched, its average resolution rate reached 66% across more than 6,000 customers, but the announcement argues that resolution rate does not capture the differing complexity of interactions. Fin 3 therefore emphasizes complex queries, additional channels, and automation rate.
Approach / What changed
Fin 3 expands the Fin Flywheel across training, testing, deployment, and analysis. Teams can write Procedures in natural language, add deterministic controls such as connectors, conditions, code, and approval checkpoints, test multi-turn behavior with Simulations, deploy through chat, Voice, Slack, and Discord, and use upgraded Insights for CX measurement, topic trends, and content or workflow suggestions.
Takeaways
Procedures combine natural-language SOPs with deterministic controls, including data connectors, conditional steps, code snippets, and approval checkpoints for sensitive actions.
Simulations run full multi-turn conversations for selected Procedures and customer segments, helping teams test edge cases, inspect behavior, and rerun suggested fixes.
Fin 3 shifts emphasis from resolution rate to automation rate: the stated average resolution rate is 66% across more than 6,000 customers, but query complexity affects how much work is actually automated.
FAQ
How do Procedures make complex customer-service workflows controllable?
Teams can provide natural-language instructions and layer in data connectors, conditional steps, code snippets, and approval checkpoints. Fin can reason through conversations while following defined processes and pausing for human control when required.
What does Simulations test?
Simulations run complete, multi-turn conversations for a selected Procedure and user or customer segment. Teams can inspect how Fin follows and reasons through each step, store scenarios in a library, and rerun tests after changes.
Which channels does Fin 3 support?
The announcement says Fin 3 extends deployment to Slack and Discord and includes improvements to Voice. Fin Voice logs calls with transcripts, summaries, and outcomes, and uses the same foundation as chat.
Source and freshness
- Source
- intercom.com
- Published
- Added to Yomu
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.