# How Forward Deployed Engineering is done at Decagon — Sunny Rekhi

## Executive summary

The talk details the function and evolution of Forward Deployed Engineering (FDE) at Decagon, a company specializing in AI customer service agents. FDE is described as being functionally identical to product engineering, requiring engineers to not only configure complex agent workflows for specific enterprises but also to proactively identify and build platform features that solve anticipated problems across multiple clients. The core philosophy emphasizes architectural restraint: ensuring all custom work is designed to be self-serve and compound into the overall platform, allowing the solution to scale from bespoke deployments to a generalized product.

## Key takeaways

- FDE Blurs with Product Engineering: The line between forward deployed service and internal product development is highly blurred. When an enterprise expresses a pain point, it should be treated as a potential product feature that needs prioritization for the entire platform (13:00).
- Focus on Architectural Restraint: A critical skill in scaling FDE is exercising restraint—avoiding simple one-off patches and instead architecting solutions so they benefit future, unknown customers. This ensures the solution does not become a brittle 'black box' (8:20).
- Custom Work Must Compound: The goal of every deployment is to ensure that custom integrations or workflows are systematically fed back into the platform, transforming bespoke solutions into self-service capabilities for all customers (14:18).

## Technical details

- Decagon's AI Agent Capabilities: Decagon provides a multilingual, omni-channel, 24/7 AI customer service agent that handles complex support workflows and can expand into proactive revenue generation (e.g., lease renewal outreach) beyond simple inbound deflection (1:06).
- Two Modes of Forward Deployment: FDE involves two specialized lanes: 1) Configuring the 'agent brain' with specific instructions, brand tonality, and handoff rules for an enterprise; and 2) Acting as the front line to identify recurring product needs that must be brought back into the core platform (3:40).
- Scaling Engineering Roles: As the company scaled from 50 to 500 people, the original agent software engineering role was specialized into 'agent builders' (focused on UI configuration) and dedicated 'agent software engineers' (focused on productizing customer requests) (6:12).

## Practical implications

- Treat yourself as an advisor, not just an executor: Use domain expertise gained from multiple customers to advise on the highest ROI automation points.
- Prioritize requirements gathering upfront: When scoping a deal, define success metrics and ideal outcomes in writing to prevent miscommunication and scope creep.
- Design for scale: Always ask how a current custom solution can be generalized into a self-service feature or platform capability.

## Topics

Forward Deployed Engineering, AI Agents, Productization, System Scaling, Omni-channel, Decagon, sunny@degagon.ai

Source: https://www.youtube.com/watch?v=7wu2hsRfvV0