# How to roll out AI coding tools to an engineering team Authors: AutoRouter Published: 2026-10-23T02:20:00.723Z Reading time: 8 min Canonical: https://autorouter.com/blog/ai-coding-tools-for-teams Publisher: AutoRouter, the Mac app for Codex and Claude Code (https://autorouter.com) > Rolling out Claude Code, Codex or GitHub Copilot to an engineering team comes down to six decisions: sign-in, deployment, model access, budgets, reporting and data retention. Each vendor's admin controls cover only its own tool, and Claude Code and Codex both read policy from a macOS MDM profile. For teams on Codex and Claude Code, AutoRouter, the Mac app for Codex and Claude Code, has an Enterprise plan that puts allowed models, team budgets and zero data retention in one place, reports spend by team, project or ticket, and rolls out through Jamf or another MDM. Treat an AI coding rollout as six decisions to make before the first seat goes out: sign-in, how settings reach each machine, which models each team may use, what each team can spend, what you report on, and what happens to prompts and code. Anthropic, OpenAI and GitHub each give admins controls for their own tool, and the ones that hold are enforced by managed settings or the vendor's server. If your developers work in Codex or Claude Code, [AutoRouter, the Mac app for Codex and Claude Code](https://autorouter.com), has an Enterprise plan that puts allowed models, team budgets and zero data retention in one place and reports spend by team, project or ticket. AutoRouter wrote this post. Vendor plans, prices and controls are as of October 22, 2026, and each one links its source. ## What goes on the rollout checklist? Identity comes first, because Anthropic applies zero data retention and server-side model restrictions only to people signed in to your organization: 1. **Identity.** Require SSO, use SCIM where your plan includes it, and pin sign-in to your organization. Claude Code's `forceLoginMethod` and `forceLoginOrgUUID` managed settings do the pinning, and Anthropic says [zero data retention covers only requests that sign in to the ZDR organization](https://code.claude.com/docs/en/zero-data-retention), so a session on a personal account isn't covered. 2. **Deployment.** Push policy to every machine so developers have nothing to configure. [Claude Code](https://code.claude.com/docs/en/managed-settings) and [Codex](https://learn.chatgpt.com/docs/enterprise/managed-configuration) both read a macOS configuration profile that Jamf or another MDM can carry. 3. **Models.** Decide which models each team may use, and enforce that list with an allowlist. A managed default model restricts nothing: Anthropic calls it ["a starting default, not a lock"](https://code.claude.com/docs/en/settings), and OpenAI calls Codex workspace model choices ["defaults, not permissions"](https://learn.chatgpt.com/docs/enterprise/workspace-model-availability). 4. **Budgets.** Set caps that stop usage when they're reached. GitHub warns that a Copilot budget without ["Stop usage when budget limit is reached"](https://docs.github.com/en/copilot/how-tos/manage-and-track-spending/manage-company-spending) sends a notification while charges keep accruing. 5. **Reporting.** Pick the unit you'll be asked about (person, team or project) and check that each tool reports it. All three report per user; GitHub also [reports by repository](https://docs.github.com/en/copilot/concepts/copilot-usage-metrics/copilot-metrics), and Claude Code can stream per-user token and cost metrics into your own stack over [OpenTelemetry](https://code.claude.com/docs/en/costs). 6. **Data retention.** Decide whether you need zero data retention, and check which features it removes: under [Anthropic's ZDR](https://code.claude.com/docs/en/zero-data-retention), features that store prompts, such as cloud sessions and Remote Control, are turned off. ## How do you push the settings to every Mac? Deploy each tool's managed configuration as a macOS configuration profile through your MDM, then confirm it on one test machine before the rest. For Claude Code, put the keys in the `com.anthropic.claudecode` preferences domain, or in `/Library/Application Support/ClaudeCode/managed-settings.json`. [Managed settings](https://code.claude.com/docs/en/settings) override every user and project setting, and as of October 22, 2026, Claude Code [checks MDM policy for changes every 30 minutes](https://code.claude.com/docs/en/managed-settings). This example pins claude.ai sign-in to one organization and allows only Sonnet and Haiku models: ```json { "forceLoginMethod": "claudeai", "forceLoginOrgUUID": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx", "availableModels": ["sonnet", "haiku"], "enforceAvailableModels": true } ``` [`enforceAvailableModels`](https://code.claude.com/docs/en/settings-reference) also keeps the picker's Default option inside the list, and it needs Claude Code v2.1.175 or later. Run `/status` on the test machine: its Setting sources line should show Enterprise managed settings. On Team and Enterprise plans, the claude.ai admin console can deliver the same keys instead, and Claude Code [fetches them at startup and every hour](https://code.claude.com/docs/en/admin-setup). For Codex, write a `requirements.toml`. OpenAI defines [requirements](https://learn.chatgpt.com/docs/enterprise/managed-configuration) as admin-enforced constraints that users can't override. This example from OpenAI's docs blocks `--ask-for-approval never` and `--sandbox danger-full-access`: ```toml allowed_approval_policies = ["untrusted", "on-request"] allowed_sandbox_modes = ["read-only", "workspace-write"] ``` Install it at `/etc/codex/requirements.toml`, or base64-encode it without line wrapping and deliver it in the `com.openai.codex` domain under the `requirements_toml_base64` key. [OpenAI names](https://learn.chatgpt.com/docs/enterprise/managed-configuration) Jamf Pro, Fleet and Kandji as tools that can distribute it. ## How much should you budget per developer? Start from a pilot group's real usage. As of October 22, 2026, [Anthropic says](https://code.claude.com/docs/en/costs) Claude Code averages about $13 per developer per active day and $150 to $250 per developer per month across enterprise deployments, with 90% of users under $30 per active day. Agent work past a seat's allowance is billed as usage, so the cap matters as much as the seat price: - **Claude Team:** each seat's Claude Code usage draws from an allowance that resets on a rolling five-hour window and a weekly window, which [How Claude Code usage limits work](/blog/claude-code-usage-limits) explains. Past it, usage credits apply, with [spend limits at the organization, group or member level](https://code.claude.com/docs/en/costs). - **GitHub Copilot:** [since June 1, 2026](https://github.blog/changelog/2026/04/27/github-copilot-is-moving-to-usage-based-billing/), each Business seat ($19 a month) includes $19 of AI credits and each Enterprise seat ($39 a month) includes $39, pooled across the business. As of October 22, 2026, extra usage costs [$0.01 per credit](https://docs.github.com/en/copilot/how-tos/manage-and-track-spending/manage-company-spending), with budgets at the enterprise, cost center and user level. - **Codex:** OpenAI says ["Business, Edu, and Enterprise plans with flexible pricing"](https://learn.chatgpt.com/docs/pricing) can buy workspace credits to keep working, and admins govern credit-funded Codex use with [ChatGPT usage limits and spend controls](https://learn.chatgpt.com/docs/enterprise/admin-setup). ## What do Anthropic, OpenAI and GitHub's own controls cover? Each vendor covers SSO, model access, spend caps and reporting for its own tool, and most keep SCIM, audit and retention controls for the top tier, as of October 22, 2026: | Control | Claude Code (Anthropic) | Codex (OpenAI) | GitHub Copilot | | --------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | SSO | [Team and Enterprise](https://claude.com/pricing) | [SAML SSO and MFA on Business](https://learn.chatgpt.com/docs/pricing) | [Through GitHub: SAML SSO or Enterprise Managed Users](https://docs.github.com/en/enterprise-cloud@latest/admin/managing-iam/understanding-iam-for-enterprises/about-identity-and-access-management) | | SCIM | [Enterprise](https://claude.com/pricing) | [Enterprise, Edu and Healthcare](https://learn.chatgpt.com/docs/enterprise/user-lifecycle) | [Enterprise Managed Users, provisioned from your IdP](https://docs.github.com/en/enterprise-cloud@latest/admin/managing-iam/understanding-iam-for-enterprises/about-identity-and-access-management) | | Model allowlist | `availableModels` in managed settings; Enterprise can also [disable models server-side](https://code.claude.com/docs/en/model-config) | [Admins enable models for the workspace](https://learn.chatgpt.com/docs/enterprise/workspace-model-availability) (Enterprise, Edu) | [Owners enable or disable models](https://docs.github.com/en/copilot/how-tos/use-ai-models/configure-access-to-ai-models) for Business and Enterprise seats | | Spend caps | [Spend limits by organization, group or member](https://code.claude.com/docs/en/costs) | [Usage limits and spend controls on workspace credits](https://learn.chatgpt.com/docs/enterprise/admin-setup) | [Budgets by enterprise, cost center or user](https://docs.github.com/en/copilot/how-tos/manage-and-track-spending/manage-company-spending) | | Usage reporting | [Spend report by user and model; Analytics API on Enterprise](https://code.claude.com/docs/en/costs); OpenTelemetry | [Codex analytics dashboard; Analytics API](https://learn.chatgpt.com/docs/enterprise/governance) | [Metrics dashboard and APIs](https://docs.github.com/en/copilot/concepts/copilot-usage-metrics/copilot-metrics), down to repository and user | | Audit | [Audit logs and Compliance API on Enterprise](https://claude.com/pricing) | [Compliance API for audit records](https://learn.chatgpt.com/docs/enterprise/governance) | [Audit logs on Business and Enterprise](https://docs.github.com/en/copilot/get-started/plans) | | Data retention | Custom retention on Enterprise; [ZDR for qualified Enterprise accounts](https://code.claude.com/docs/en/zero-data-retention), enabled by Anthropic | [Retention and residency controls on Enterprise](https://learn.chatgpt.com/docs/pricing); [Work Cloud local computer access isn't strict ZDR](https://learn.chatgpt.com/docs/enterprise/admin-setup) | [IDE prompts not retained](https://github.com/features/copilot); GitHub.com, mobile and CLI prompts kept 28 days | Each set of controls stops at its vendor's tool, so a team that uses two of these tools keeps two sets of model lists, budgets and reports. ## Where does AutoRouter Enterprise fit? AutoRouter Enterprise fits teams on Macs whose developers work in Codex, Claude Code or both. AutoRouter, the Mac app for Codex and Claude Code, adds 20+ models to both apps, plus one more choice: AutoRouter, which picks a model for each turn and uses the ChatGPT and Claude plans people already pay for first. Every turn shows its model, what it cost and why. [How AutoRouter picks a model](/blog/how-autorouter-picks-a-model) explains the routing, and [Does model routing make your results worse?](/blog/does-model-routing-hurt-quality) answers the quality question. Enterprise is available and priced by seats for the team. It includes everything in Pro, plus: - Rollout to every Mac through Jamf or another MDM, with nothing for anyone to set up and every Mac running the same way. - Allowed models, team budgets and zero data retention, in one place for the whole organization. - Spend by team, project or ticket, for any period. - SSO, SCIM and an audit log. Two features are coming soon and aren't available yet: what each pull request cost (who shipped it, which models did the work and what it cost), and one skills library for a whole team. AutoRouter is in beta, runs on macOS 14 or later, and works with Codex (the app and the CLI) and the Claude Code CLI, so GitHub Copilot and machines that aren't Macs still need their vendors' own controls. To plan a rollout, email [sales@autorouter.com](mailto:sales@autorouter.com). ## Questions ### Can developers override managed settings? No, developers can't override a managed key in Claude Code or a requirement in Codex. In Claude Code, [nothing in a developer's own files or the `--settings` flag overrides a managed key](https://code.claude.com/docs/en/settings), apart from a few keys where the stricter value wins. In Codex, [requirements](https://learn.chatgpt.com/docs/enterprise/managed-configuration) can't be overridden, while managed defaults are only starting values. ### How much do the seats cost? As of October 22, 2026, [Claude Team](https://claude.com/pricing) Standard seats cost $20 a month billed annually or $25 monthly, Premium seats cost $100 or $125, and Claude Enterprise costs $20 a seat a month billed annually, with a 20-seat minimum, plus usage at API rates. On the same date, [ChatGPT Business](https://learn.chatgpt.com/docs/pricing) cost $20 per user a month billed annually or $25 monthly, ChatGPT Enterprise was priced through sales, and [Copilot Business and Copilot Enterprise](https://docs.github.com/en/copilot/get-started/plans) cost $19 and $39 per seat a month. AutoRouter Enterprise is priced by seats through [sales@autorouter.com](mailto:sales@autorouter.com). ### Does AutoRouter see our prompts? Requests pass through AutoRouter's servers on their way to each provider, and AutoRouter doesn't store transcripts. It keeps the message that opens each turn, up to 4,000 characters, to review routing, along with records of the model chosen, tokens and cost. Details are in [AutoRouter's privacy policy](https://autorouter.com/privacy); for how Enterprise zero data retention applies to your organization, ask [sales@autorouter.com](mailto:sales@autorouter.com). ## Sources Each vendor page was read on October 22, 2026. - [AutoRouter](https://autorouter.com) - [AutoRouter privacy policy](https://autorouter.com/privacy) - [Anthropic: Set up Claude Code for your organization](https://code.claude.com/docs/en/admin-setup) - [Anthropic: Deploy managed settings](https://code.claude.com/docs/en/managed-settings) - [Anthropic: Settings files and precedence](https://code.claude.com/docs/en/settings) - [Anthropic: All settings](https://code.claude.com/docs/en/settings-reference) - [Anthropic: Model configuration](https://code.claude.com/docs/en/model-config) - [Anthropic: Manage costs effectively](https://code.claude.com/docs/en/costs) - [Anthropic: Zero data retention](https://code.claude.com/docs/en/zero-data-retention) - [Anthropic: Claude pricing](https://claude.com/pricing) - [OpenAI: Codex admin setup](https://learn.chatgpt.com/docs/enterprise/admin-setup) - [OpenAI: Managed configuration](https://learn.chatgpt.com/docs/enterprise/managed-configuration) - [OpenAI: Workspace model availability](https://learn.chatgpt.com/docs/enterprise/workspace-model-availability) - [OpenAI: User lifecycle](https://learn.chatgpt.com/docs/enterprise/user-lifecycle) - [OpenAI: Governance](https://learn.chatgpt.com/docs/enterprise/governance) - [OpenAI: Pricing](https://learn.chatgpt.com/docs/pricing) - [GitHub: Plans for GitHub Copilot](https://docs.github.com/en/copilot/get-started/plans) - [GitHub: Configure access to AI models](https://docs.github.com/en/copilot/how-tos/use-ai-models/configure-access-to-ai-models) - [GitHub: Manage company spending](https://docs.github.com/en/copilot/how-tos/manage-and-track-spending/manage-company-spending) - [GitHub: Copilot usage metrics](https://docs.github.com/en/copilot/concepts/copilot-usage-metrics/copilot-metrics) - [GitHub changelog: Copilot is moving to usage-based billing](https://github.blog/changelog/2026/04/27/github-copilot-is-moving-to-usage-based-billing/), April 27, 2026 - [GitHub Copilot: FAQ on data retention](https://github.com/features/copilot) - [GitHub: About identity and access management](https://docs.github.com/en/enterprise-cloud@latest/admin/managing-iam/understanding-iam-for-enterprises/about-identity-and-access-management) ## Read next - [Subscription or API: which is cheaper for coding agents?](https://autorouter.com/blog/subscription-vs-api-pricing.md): A Claude or ChatGPT plan costs less than paying per token once a month of your coding would cost more than the plan at API list prices, and the plan's limits still hold that work. As of October 22, 2026, Anthropic reports Claude Code averaging $150 to $250 per developer per month at API prices across enterprise deployments, against $20 for Claude Pro and $100 or $200 for Max. AutoRouter, the Mac app for Codex and Claude Code, uses the ChatGPT and Claude plans you already pay for first and bills other models at the provider's price plus 10%. - [How to use Claude Code and Codex without a subscription](https://autorouter.com/blog/no-subscription-coding-agents.md): Claude Code runs on a Claude Console account and Codex runs on an OpenAI API key, and both bill per token with no ChatGPT or Claude plan. AutoRouter, the Mac app for Codex and Claude Code, is a third option: AutoRouter Pro costs $20 a month with $20 of included usage and bills paid models at the provider's price plus 10%. On the same models, a direct API key costs less, so Pro comes out ahead only when cheaper models take enough of your turns. - [How do Codex and Claude Code compare, and can you use both?](https://autorouter.com/blog/codex-vs-claude-code.md): As of October 2026, Codex is OpenAI's coding agent, included with every ChatGPT plan, and Claude Code is Anthropic's, included with every paid Claude plan; ChatGPT Plus and Claude Pro both cost $20 a month. They overlap on most features, so the choice comes down to the models you prefer (GPT-6.1 Sol and GPT-6 Luna, or Claude Opus 5.5, Sonnet 5.5 and Haiku 5.5) and the plan you already pay for, and both can share one AGENTS.md in the same repository. AutoRouter, the Mac app for Codex and Claude Code, works in both and picks a model for each turn by how hard it is. Tags: [Teams](https://autorouter.com/blog/tags/teams.md), [Claude Code](https://autorouter.com/blog/tags/claude-code.md), [Codex](https://autorouter.com/blog/tags/codex.md) Drafted with AI from the sources linked above, then checked and edited by the AutoRouter team.