IntercomChris DalleyAnnouncement
Announcing major updates to Procedures and Simulations: Enabling Fin to handle complex queries
Summary
Intercom announces 12 updates to Fin’s Procedures and Simulations, the mechanisms it presents for handling complex customer queries while keeping teams in control. Procedures combine natural-language instructions, deterministic controls such as conditional steps, data connectors, code snippets, checkpoints, and fully agentic behavior; new features include AI drafting, reusable Sub-procedures, explicit switching rules, targeted knowledge-hub references, internal handoff notes, automatic switching, and structured extraction from PDFs and images. The Procedures UI also adds improved authoring and reporting on triggers, resolutions, and handoffs. Simulations support full multi-turn conversations, image uploads, clearer visibility into Fin’s reasoning, and AI-generated tests stored in a central library that can be rerun after changes. Procedures and Simulations are available now, with the stated goal of helping teams train, test, deploy, analyze, and refine complex workflows before and after launch.
Context
Teams that gain early improvements in AI speed, coverage, and cost to serve can hit a ceiling when they limit AI to simple automation and information retrieval. Customers also wanted to connect data for reliable status or eligibility checks and avoid routing engineering teams through every logic change for mid-conversation decisions. The source describes deployment of complex AI as requiring ongoing training, validation, production measurement, and refinement.
Approach / What changed
Procedures combine natural-language instructions, deterministic controls, and agentic behavior. Teams can use AI to draft workflows, add conditional steps, data connectors, code snippets, checkpoints, knowledge-hub rules, and reusable Sub-procedures, while Fin can switch Procedures as intent changes and extract structured data from uploaded files. Simulations provide multi-turn testing with images, reasoning visibility, AI-suggested edge cases, centralized test storage, and reruns after changes.
Takeaways
Procedures support a gradual mix of natural-language instructions and deterministic controls, including conditional branching, data connectors, code snippets for guaranteed outputs, and checkpoints for approval or handoff.
Fin can automatically switch to a more relevant Procedure when customer intent changes and can extract structured data from uploaded PDFs and images for use during the conversation.
Simulations can be generated from Procedures, include image inputs and multi-turn conversations, expose Fin’s reasoning, and be stored in a library for rerunning after product, policy, or Procedure changes.
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.