# Linear Says Coding Agents Miss Product Context

_Linear's Tom Moor showed triage and review agents that keep product intent with coding agents._

**Published:** 2026-11-11
**Source:** https://www.startuphub.ai/ai-news/technology/2026/linear-says-coding-agents-miss-product-context

---

Tom Moor demoed Linear's cents-per-task triage system for coding agents on [AI Engineer](https://www.youtube.com/watch?v=Xw9utONfhIY). The target is coding agents working in Linear issues and pull requests.

Linear began in 2019 as an issue tracker, Moor said. [GitHub Copilot](https://www.startuphub.ai/ai-news/technology/2026/github-copilot-app-launches-for-agents) brought AI tab completion in 2021, Moor said. First functional coding agents arrived in 2024, Moor said.

Intelligence costing $100 three years ago costs 5 cents today, Moor said. Agents now run for hours and days, Moor said. "Code is not the bottleneck now," Moor said.

Triage pulls ideas from Zendesk, Slack, [Gong](https://www.startuphub.ai/startups/gong-io) and Datadog alerts, Moor said. The agent labels, assigns, groups and closes duplicates, Moor said. It leaves investigation, customer value and related decisions on the issue, Moor said. ChatGPT Learn docs state Triage rules can delegate new issues to Codex automatically.

Review is where that context gets tested.

The review agent starts from that base issue context, Moor said. It checks prior decisions, reverts and overlapping work, Moor said. It caught a DB transaction risk and blocked iconography rejected a year earlier, Moor said. A daily automation distills merged fixes back into agents.md, Moor said.

---

Original analysis from [startuphub.ai](https://www.startuphub.ai), the #1 AI startup directory.

© StartupHub.ai. All rights reserved. You may not republish this article in full without a license. Search engines and AI research tools may crawl and summarize for reference. Bulk reproduction or model training on this content requires a license. See https://www.startuphub.ai/terms.