# Canopy product essays

> Product thinking about directing coding agents, coordinating work, and interpreting model usage without overstating results.

Canopy runs installed coding CLIs; each CLI keeps its own account, model, network behavior, and billing. Check the installed release for version-specific features. Each link below opens a clean Markdown version of the article.

## Pages

- [A workspace for people who direct AI agents](https://canopyide.dev/blog/a-workspace-for-people-who-direct-ai-agents.md): A practical founder workflow for directing a coding agent: define one outcome, run the product, inspect evidence, and hand off risky decisions.
- [Agent swarms do not ship software. Ownership does.](https://canopyide.dev/blog/agent-swarms-do-not-ship-software.md): Running more coding agents can increase output and confusion at the same time. Here is a better way to divide work and review the result.
- [Canopy 0.3.4: test tab recovery, OpenCode usage, and Remote](https://canopyide.dev/blog/canopy-034-agent-workflow-release-guide.md): A task-based reading of the v0.3.4 release notes with a short installed-build trial for closed tabs, OpenCode Statistics, and Remote continuity.
- [Understanding AI coding agent usage and estimated cost](https://canopyide.dev/blog/understanding-ai-coding-agent-costs.md): Read Canopy's CLI, model, session, plan-limit, and estimated-cost views without mistaking a token estimate or stale quota snapshot for a provider charge.
- [Why an AI coding workspace still needs a real terminal](https://canopyide.dev/blog/why-coding-agent-clis-need-real-terminals.md): What a PTY preserves for interactive coding CLIs, what Canopy adds around it, and a quick test for comparing agent workspaces.
- [Why cheaper AI tokens can make a coding task more expensive](https://canopyide.dev/blog/cheaper-tokens-more-expensive-coding-task.md): A worked task-cost comparison that counts retries, cache categories, human review, and accepted code instead of ranking models by input-token price.
- [Your AI coding cost dashboard is not your bill](https://canopyide.dev/blog/your-ai-coding-cost-dashboard-is-not-your-bill.md): Separate the three ledgers behind a coding-agent dashboard: model consumption, plan capacity, and actual provider charges.