# Factory AI — The Context Window Problem: Scaling Agents Beyond Token Limits

- Company: Factory AI (factory.com)
- Announced: 2025-08-25
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://factory.com/news/context-window-problem
- Record: https://forck.live/items/17826-the-context-window-problem-scaling-agents-beyond-token-limits
- Subject: Droid
- Context window: approximately 1 million tokens

Factory describes its approach to scaling agentic workflows by building multiple layers of scaffolding that treat context as a scarce resource, including structured repository overviews, semantic search, targeted file operations, and integrations with enterprise context sources like Datadog, Slack, and Notion. The post explains why naive vector retrieval fails for code navigation and how Factory's architecture addresses these limitations.

## Evidence

Verbatim from https://factory.com/news/context-window-problem:

> At Factory, we've addressed these limitations by building multiple layers of scaffolding, such as structured repository overviews, semantic search, targeted file operations, and integrations with enterprise context sources that go beyond just the code, like Datadog, Slack, and Notion.

---

Record: https://forck.live/items/17826-the-context-window-problem-scaling-agents-beyond-token-limits
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md