Help Center

Walkthroughs for installation, integration, billing, and the common errors people hit on their first few sessions. Each topic has a deep-link anchor — share the URL with a teammate and they'll land on the right answer.

Install the AI Expedite Terminal app

The Terminal app is a small, code-signed application that runs on your Windows, Mac, or Linux machine. It lets AI Expedite's central agents dispatch coding tasks (Claude Code, Codex, builds, tests) to your computer using your own subscription and toolchain.

Download and install

  • Go to the Downloads page from the workspace menu.
  • Pick the binary for your OS (macOS .dmg, Windows .exe, Linux AppImage).
  • On macOS, drag the app into Applications. On Windows, run the installer. On Linux, mark the AppImage executable and run it.
  • Sign in to the same AI Expedite account you use in the browser.
  • Click Connect to cloud in the app's title bar to register the machine as a worker.

First-run permissions

The first time the terminal app runs a command outside the default allowlist, your OS will show a native approval dialog with the exact command. You can approve once, approve as a pattern, or deny. The agent cannot run anything you have not explicitly approved.

If you don't see the connect button after install, see the Troubleshooting the Terminal topic below.

Connect your GitHub account

GitHub is the substrate AI Expedite builds on — every feature, branch, PR, and code analysis pass routes through it. You need to connect a GitHub account before agents can run coding work.

Steps

  • Open Settings → Integrations in the workspace.
  • Find the GitHub card and click Connect.
  • Authorize the AI Expedite GitHub App on the account or organization that owns the repos you want agents to work in.
  • Pick the specific repositories the app should have access to. You can change this list at any time from GitHub's installed-apps page.
  • Back in AI Expedite, the repos appear under Code → Repositories. Enable Code Analysis on the ones you want agents to reason about.

Scopes we ask for

AI Expedite requests repository-scoped access — never org-wide read. The GitHub App permissions are visible during the install flow and listed on our Security page.

Wire up your Claude Code subscription

AI Expedite can route Claude Code work through your existing Claude Pro, Max, or Team subscription. This is the cheapest way to run agentic coding at any meaningful volume.

Prerequisites

  • An active Claude subscription with Claude Code CLI access.
  • The Claude Code CLI installed and authenticated on the machine that will run agents.
  • The AI Expedite Terminal app installed and Connected to cloud on the same machine.

How to verify

  • Open a terminal on the machine and run `claude --version`. You should see the installed version, no auth prompt.
  • In the AI Expedite Terminal app, the worker status should show Claude Code: ready.
  • Dispatch a small test feature from chat — anything trivial, like 'add a console.log to file X.' The orchestrator should route the task to this machine.

If the worker doesn't show Claude Code as ready, check that the CLI is on the system PATH the terminal app is using. We never see or proxy your Anthropic credentials — the CLI handles auth directly with Anthropic.

Wire up your Codex subscription or API key

AI Expedite supports both the Codex CLI (subscription-routed) and the OpenAI Batch API (metered) for async coding work. The orchestrator routes to the cheaper viable option per job.

Subscription-routed (Codex CLI)

  • Confirm your ChatGPT plan includes Codex CLI access.
  • Install the Codex CLI on the machine that runs the Terminal app.
  • Run `codex --version` to confirm the CLI is on the PATH.
  • The Terminal app's worker status should show Codex: ready.

API-routed (Batch)

  • Open Settings → Integrations and connect the OpenAI integration.
  • Add an API key with permission to call the Batch API.
  • Routing happens automatically — batch-friendly jobs (cross-codebase refactors, dependency upgrades) use the cheaper Batch API even if the CLI is also available.
Connect an MCP server

Model Context Protocol (MCP) servers let your agents reach external tools and data sources — internal APIs, databases, custom search indexes, anything that exposes an MCP endpoint.

Add an MCP server

  • Open Settings → MCP Servers.
  • Click Add server and paste the server URL.
  • If the server requires authentication, paste a token. Tokens are encrypted at rest in Firestore.
  • Pick which workspaces and agents the server is available to.
  • Save. The server becomes available as a tool in chat and in custom agents.

MCP server calls flow through AI Expedite's request layer, so they get the same logging, rate limiting, and audit trail as built-in tool calls.

Workspace roles and permissions

Workspaces have a small set of roles, enforced server-side via Firestore Security Rules. Membership is managed in Settings → Workspace → Members.

Roles

  • Owner — full control, including billing and integrations. Each workspace has exactly one owner; transfer is possible from the workspace settings.
  • Admin — manages members, integrations, and workspace settings. Cannot change the billing plan or the owner.
  • Member — drives agent work, edits documents, opens PRs. Cannot change integrations or workspace settings.
  • Viewer — read-only access to workspace content. Useful for stakeholders and procurement reviewers.

Code analysis and scheduled activities are billed to the workspace owner, not the individual member running the work. That keeps cost predictable for teams while letting each engineer drive agents from their own account.

GitHub: "Email already in use"

If you're trying to link your GitHub account but you're receiving the error 'Email already in use', that typically indicates that you have signed into AI Expedite with multiple accounts.

To resolve this issue

  • Go to github.com
  • Click your user profile image at the top right.
  • Click Settings.
  • At the left of the page, click the 'Emails' button.
  • You'll see the email addresses you have associated with your GitHub account.
  • Note the email address you have set to primary.
  • Google will attempt to sign you in to the same Google account you used previously. Open an incognito/private window or tab and go to aiexpedite.com.
  • Log in using Google — make sure to log in with your GitHub account's default email address.
  • You can now either use this account and link your GitHub account to it, or...
  • Go to user preferences and delete your account. This will only remove this account from AI Expedite.
  • Return to your original tab with your other account and try linking your GitHub account again.
Common GitHub OAuth errors

'Repository not found' on a private repo

This means the AI Expedite GitHub App is installed on a different account than the one that owns the repo, or the repo is not in the app's configured allowlist. Open GitHub → Settings → Applications → Installed GitHub Apps → AI Expedite, and confirm the repo is listed. If not, click Configure and add it.

'Bad credentials' or 'Token expired'

Long-lived GitHub installation tokens are refreshed automatically. If you see this error persistently, disconnect the GitHub integration from Settings → Integrations and reconnect. The reconnect refreshes the underlying installation token.

'Resource not accessible by integration'

The action you tried to perform requires a permission the AI Expedite GitHub App does not currently hold. This is most common when a new feature requires a scope that existing installations don't yet grant. Open the GitHub App settings → Permissions and approve the new permissions when prompted.

Credits, billing, and Auto-Reload

AI Expedite uses credits to meter AI execution. Browsing the app, editing documents manually, and managing billing settings do not consume credits.

How credits are consumed

  • Running an agent (Claude Code, Codex, review agents, UI tests).
  • Generating insights, roadmap recommendations, or launch content.
  • Running code analysis on a repo (initial index + ongoing updates).
  • Scheduled activities (recurring agent runs, scheduled posts).

Auto-Reload

If you hit your included monthly credit limit, AI Expedite pauses new AI work by default. Auto-Reload lets you set a monthly spending cap and automatically tops up credits when you run out. Find it in Settings → Billing → Auto-Reload. The cap is hard — once you hit it, work pauses again until the next month or until you raise the cap.

Top-ups

Prepaid top-ups are a one-time purchase that adds credits to your account immediately. Top-up credits roll over for 60 days, then expire. Included monthly credits do not roll over.

When an agent fails or gets stuck

Agents fail for predictable reasons. The session always surfaces in the workspace with the full transcript, the build / test output, and the current state — failed runs are never silently retried.

Common failure modes

  • Build failure — the agent's diff doesn't compile or breaks tests. The failure context is attached; you can hand the task back to the queue (the next run sees the failure) or step in and fix.
  • Approval needed — the agent has paused at a requirements, design, or merge gate. Approve, edit, or reject from the task surface.
  • External tool error — an integration call (GitHub, Linear, Jira, MCP server) failed. The transcript shows the underlying error.
  • Subscription unavailable — the machine the orchestrator dispatched to is offline, or the CLI on that machine is not authenticated. Reconnect the worker.
  • Agent confusion — Claude Code or Codex couldn't make progress and asked for more context. Reply directly in the session to unblock, or revise the feature description and re-run.

How to recover

  • Read the transcript first — the failure reason is usually in the last few lines.
  • If the failure is build / test related, re-dispatching the task often resolves it because the next run sees the failure context.
  • If the failure is structural (missing context, ambiguous scope), edit the feature description and re-dispatch.
  • If a worker is the problem, reconnect the terminal app and re-dispatch to a different machine.
Enabling and using Code Analysis

Code Analysis builds a structured index of a repo — file structure, exports, call graph, type information, conventions in use. Agents reference the index to reason about code in context: when Claude Code edits a function, the orchestrator knows about every call site; when the reviewer agent reads a diff, it knows what tests cover the changed lines.

How to enable

  • Open Code → Repositories.
  • Find the repo and toggle Code Analysis: On.
  • The initial index takes a few minutes for typical repos, longer for monorepos. Progress shows in the repo card.
  • After the initial pass, the index updates incrementally on every push.

What it costs

Code Analysis is a workspace-owner cost: it bills to the workspace, not the individual member who enabled it. The cost is roughly proportional to repo size and commit volume. For very large monorepos, consider scoping analysis to the directories your team actively works in.

When you can skip it

Ship still works without Code Analysis — agents fall back to live reads against the repo. The downside is slower runs and less informed review. Discover features that depend on effort estimation, and Launch features that depend on codebase context, both benefit substantially from having analysis enabled.

Troubleshooting the Terminal app

App won't connect to cloud

Confirm you're signed in to the same AI Expedite account in the app and in the browser. If the Connect to cloud button is greyed out, sign out of the app, sign back in, and retry. Corporate networks sometimes block the outbound connections — check that `*.aiexpedite.com` is reachable.

Worker shows but doesn't take jobs

Open the app's Status tab. Each capability (Claude Code, Codex, build, test) shows a green / red indicator. Red means the underlying tool isn't on the PATH the app uses, or isn't authenticated. Install or authenticate the tool, then click Re-detect.

OS approval dialog never appears

If a command should be prompting for OS approval but isn't, it may already be on the allowlist (intended) or your OS may be configured to suppress dialogs (not intended). Check the Allowlist tab in app settings — anything you've previously approved as a pattern runs without re-prompting.

Commands hang or time out

The app enforces a per-command timeout (default 10 minutes). Long-running jobs (large builds, full test suites) can exceed it. Raise the timeout in app settings for the affected repo, or split the command into smaller steps.