AI Engineer

How Forward Deployed Engineering is done at Factory — Eno Reyes

Published 2026-07-28 · Duration 21:21

Summary

Forward Deployed Engineering (FDE) is evolving from traditional professional services consulting into a strategic function where engineers act as 'the tip of the spear' for product development. The core goal is to build an autonomous 'Software Factory' within a customer's environment. This factory automates the entire signal-to-deploy pipeline—from capturing external signals (e.g., bug reports, Slack conversations) through planning, coding, and rigorous validation (SAST, linters, type checkers)—with minimal human intervention. Success hinges on achieving 'agent readiness,' which measures the density of deterministic validation loops in a codebase, enabling massive migrations (e.g., 30-50 million lines of code) autonomously.

Download summary

Key takeaways

  1. The Shift from Consulting to Product Strategy

    Factory argues that FDE should not be professional services work on behalf of a customer, but rather the stream of information gathered from critical customers. This data is fed back into the product to rapidly improve it, making the deployed engineer an integral part of the product's evolution.

  2. The Software Factory Pipeline 8:23

    This factory concept describes a continuous process where external signals flow in, are prioritized into plans, converted into code changes (the source of truth), pass through automated validation stages (linters, type checkers, SAST tools), and finally deploy. The goal is an uninterrupted signal-to-deploy flow without human intervention.

  3. Data Ownership and Autonomy 10:57

    To ensure scalability and security, the deployed engineer must utilize a model independent agent harness (like Droid) that guarantees the customer owns all traces and data. This allows for highly secure deployments, including air-gapping in sensitive environments like finance or healthcare.

  4. Agent Readiness as a Metric 20:05

    Autonomy is measured by 'agent readiness,' which quantifies the number of deterministic validation loops (e.g., passing linters, type checkers) present in a codebase. A high volume of these loops allows advanced agents to operate on complex tasks for extended periods without human intervention.

Technical details

  • Software Factory Pipeline 503s

    The pipeline stages include: Signal Ingestion (customer conversations, bug reports) $\rightarrow$ Planning/Triage $\rightarrow$ Code Generation (source of truth codebase) $\rightarrow$ Validation (SAST tools, linters, type checkers) $\rightarrow$ Deployment. The system aims for a flow with no human intervention.

  • Agent Harness and Model Independence 657s

    The platform must provide a canonical, model independent agent harness to prevent vendor lock-in. Crucially, the customer must own all data traces flowing through the system.

  • Autonomy Maturity Model 1008s

    The role of humans shifts from directly manipulating software to maintaining and managing the automated system that builds software—an upgrade in abstraction level. The process requires an ROI story linking code changes (AI QA, AI security analysis) directly to core business goals.

  • Advanced Agent Capabilities

    The system can solve problems where 'complete is verifiable.' Examples include migrating 30-50 million line codebases and optimizing complex financial models (e.g., equity research). The quality of output from long-running harnesses is directly proportional to the degree of validation.

Mentioned resources

  • Factory (Company/Product)
  • Droid (Agent Harness) (Product)

Channel & topics

Watch on YouTube · Back to latest

This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.