====== Factory ====== **Factory** is an autonomous coding agent company that develops **Droid**, a multi-model CLI coding agent that achieved the **#1 ranking on [[terminal_bench|Terminal-Bench]]** with a score of 58.75%. The company raised $150 million in funding from Khosla Ventures, establishing a $1.5 billion valuation that reflects significant investor confidence in the autonomous coding agent market (([[https://www.theneurondaily.com/p/[[anthropic|anthropic]]))-shipped-opus-4-7-openai-countered|The Neuron - Coding Agent Landscape Update (2026]])).(([[https://factory.ai|Factory.ai Website]]))(([[https://factory.ai/product/ide|Droid IDE Integration]])) ===== Overview ===== Factory positions itself as a major competitor in the coding agent space, specializing in intelligent code generation and autonomous programming tasks. Unlike open-source alternatives, Droid is a commercial product with a proprietary architecture optimized for enterprise software development. The company's core technical innovation centers on **dynamic model selection**, where the system intelligently switches between different language models based on the complexity and characteristics of the coding task at hand. Website: [[https://factory.ai]] | Benchmark: [[https://factory.ai/news/terminal-bench]] ===== Droid Product ===== ==== Key Features ==== * **[[terminal_bench|Terminal-Bench]] #1** — Achieved state-of-the-art 58.75% on Terminal-Bench, outperforming all other agents including those from model labs * **Specialized Droids** — Pre-built specialized agents (Code, Review, QA, Security, etc.) optimized for specific task types * **Multi-Model Flexibility** — Uses any model ([[claude|Claude]], GPT, Gemini, custom) per task with no vendor lock-in * **Adjustable Autonomy** — Levels from low (manual approval) to high (full autonomy), starting supervised for safety * **Large Codebase Handling** — Agentic search understands million-line repositories instantly * **Cross-Platform** — Runs in terminal, VS Code, JetBrains, Vim, web browser, [[slack|Slack]], and Jira * **Background Execution** — Supports long-running tasks with process management and cleanup * **Custom Droids** — Define specialized agents in ''.factory/droids/'' using YAML/Markdown configuration ==== Specialized Droids ==== ^ Droid ^ Purpose ^ Optimization ^ | Code Droid | Feature development, refactoring, bug fixes | Full tool access, implementation focus |(([[https://factory.ai/news/code-droid-technical-report|Code Droid Technical Report]])) | Review Droid | Pull request analysis and feedback | Code quality patterns, security checks | | QA Droid | Testing and quality assurance | Test generation, coverage analysis | | Security Droid | Security auditing and vulnerability detection | OWASP patterns, dependency scanning | | Custom Droids | User-defined specialized behaviors | Configurable via YAML/MD in .factory/droids/ | ==== Architecture ==== Droid's architecture is optimized for speed and accuracy: * **Main Agent** — Central orchestrator that delegates to specialized droids based on task analysis * **Droid System** — Each specialized droid has its own optimized prompts, tool configurations, and model preferences * **System Bootstrap** — Automatically gathers environment context (languages, git state, env vars, running processes) at session start * **Speed Optimizations** — Uses ripgrep for fast code search, short timeouts for rapid iteration, efficient tool implementations * **Context Layers** — Hierarchical context management for maintaining awareness across complex multi-step tasks * **Dynamic Model Selection** — Intelligently routes simpler programming tasks to more efficient models while reserving larger, more capable models for complex algorithmic challenges, architecture design, and systems-level programming requirements ===== Market Context ===== Factory represents one of three major fronts in the autonomous coding agent competitive landscape. The company competes with established AI development tools and newer entrants focused on automating software development workflows. The autonomous coding agent market has attracted significant venture capital investment, driven by the potential productivity gains from automating routine and complex programming tasks. Factory's approach to model switching and specialized droid agents distinguishes it from competitors that may rely on single-model architectures or fixed routing strategies. ===== See Also ===== * [[ai_software_factory|AI Software Factory]] * [[coding_agents_comparison_2026|Coding Agents Comparison 2026]] ===== References =====