# Inside Kikimora: We Built a Dark Software Factory

## Executive summary

The presentation introduces the concept of a 'Dark Factory'—an autonomous software development model where processes run without constant human supervision. The speaker details how rapid advancements in coding agents have broken traditional bottlenecks built for slow software. This factory approach uses tools like Tessl Agent to automate workflows (e.g., taking an issue from Linear, solving it with an agent, and opening a GitHub PR that self-corrects until merged). The core shift is moving the engineer's value proposition from writing code to understanding complex systems and trusting autonomous results.

## Key takeaways

- The Dark Factory Concept: A dark factory involves building software in a highly autonomous way, where human supervision is minimized. It is modeled after manufacturing factories with no lights on (i.e., no humans inside).
- Bottleneck Breaking Point: As coding agents increased speed, existing processes designed for slower development began to break down, necessitating a fundamental shift in how software was built.
- The Shift in Engineering Value: The value of an engineer is shifting from the ability to write code (which agents can do) to understanding the system's architecture and interlocking technical/business constraints. Trusting autonomous results is the new challenge.

## Technical details

- Dark Factory Workflow: The process starts with creating a Linear issue, which is then picked up by an autonomous agent that solves it in the cloud and opens a GitHub PR. The factory 'babysits' this PR, making necessary changes until the human user merges it.
- Night Shift Orchestrator: The speaker developed Night Shift, an internal orchestrator designed for side projects with the rule: 'don't look at the code at all.' This served as a proof point for autonomous capabilities.
- Tessl Agent and Automation: The Tessl agent is designed not primarily for writing code, but for helping identify workflows, extracting them from existing silos, formatting them for agents, uploading them to a skills registry, and creating automations.

## Practical implications

- Organizations must prepare for a fundamental shift in engineering roles, moving from code authorship to system oversight and process design.
- The concept of 'loop engineering' (continuous autonomous improvement) is presented as the necessary way forward for modern software development.
- Adoption requires cultural change; leadership must be willing to trust automated results enough to sign off on PRs they did not write.

## Topics

Software Automation, AI Agents, DevOps, Autonomous Systems, Productivity, Tessl Agent, Linear

Source: https://www.youtube.com/watch?v=u37qkpp5eB8