← BrizzCONTENT HISTORY

Update to Brizz

Snapshot Nov 16, 2026 · 18:17 UTC · version 1.0.0

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save Brizz and check future changes in Following.

Up to 3 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Get from zero to a working Brizz connection — install the `brizz` CLI, authenticate, confirm the MCP server is reachable, and pick the right access path for the task. Trigger when the user installs or first opens the Brizz plugin, when `brizz` is missing from PATH, when a Brizz command exits with an auth error, when the user asks how to log in, switch tenant, or connect their AI client to Brizz, or when a Brizz question can't be answered because nothing is connected yet.",
  "included_files": [],
  "name": "brizz-setup",
  "skill_md_contents": "---\nname: brizz-setup\ndescription: Get from zero to a working Brizz connection — install the `brizz` CLI, authenticate, confirm the MCP server is reachable, and pick the right access path for the task. Trigger when the user installs or first opens the Brizz plugin, when `brizz` is missing from PATH, when a Brizz command exits with an auth error, when the user asks how to log in, switch tenant, or connect their AI client to Brizz, or when a Brizz question can't be answered because nothing is connected yet.\n---\n\n# Set up Brizz access\n\nThis plugin gives you two independent ways into a Brizz workspace. They are not\nalternatives to choose between once — each answers a different kind of question, and a\nnormal session uses both.\n\n| Path | Needs | Best at |\n|---|---|---|\n| **MCP server** (`brizz_*` tools) | OAuth in the client, nothing installed | Structured queries, issue and session lookups, the server's own investigation runbooks |\n| **`brizz` CLI** | A binary on PATH plus `brizz auth login` | Terminal work, piping and scripting, `--agent` output you can chain, anything you want to run in a loop |\n\nThe MCP server ships with this plugin and needs no install, so **prefer it when you only\nneed to read something**. Reach for the CLI when the user is working in a terminal, wants\nto script a sweep, or asks for it by name.\n\n## Confirm what you already have\n\nRun these before concluding anything is missing. Both are cheap.\n\n```bash\nbrizz auth whoami --json     # exit 0 = authenticated, exit 2 = not logged in\nbrizz describe --json        # active tenant, app, and platform URL\n```\n\nFor the MCP path, call `brizz_whoami` instead — it returns the identity behind the current\ntoken. If that tool isn't available at all, the plugin's MCP server hasn't connected yet;\ntell the user to connect Brizz from their client's apps or connectors settings and sign in. Don't try to fix an MCP connection from\nthe shell.\n\n## Install the CLI\n\nOnly needed for the CLI path.\n\n```bash\nbrew install brizzai/tap/brizz-cli                                          # macOS\n```\n\nOn Linux or Windows, download the archive for your platform from\nhttps://github.com/brizzai/brizz-cli/releases, extract it, and add `brizz` (`brizz.exe` on Windows) to PATH.\n\nNever build from source to work around a failed install, and never hand-roll API calls\nagainst the platform because the binary is missing — say what failed and let the user\nchoose.\n\n## Authenticate\n\n```bash\nbrizz auth login                    # opens a browser for OAuth\nbrizz auth login --api-key <key>    # CI or headless\n```\n\nAuth is interactive and the CLI owns it. If `whoami` exits 2, surface the command and stop\n— do not retry, and do not attempt to log in on the user's behalf.\n\n## Set the working scope\n\nBrizz is tenant-scoped, and a query against the wrong tenant looks exactly like a query\nthat found nothing. Resolution order is **flag > env > config**:\n\n| Context | Flag | Env var | Config field |\n|---|---|---|---|\n| Tenant | `--tenant` | `BRIZZ_TENANT` | `default_tenant` |\n| App | `--app` | `BRIZZ_APP` | `default_app` |\n\nThe \"app\" is the OTel `service.name` of the instrumented application. When the user's\nquestion names one — \"checkout assistant is broken\" — pass `--app checkout-assistant`\nexplicitly even if a default is set.\n\n## Verify the whole path end to end\n\nOne command proves auth, scope, and that telemetry is actually arriving:\n\n```bash\nbrizz sessions list --limit 5 --output markdown\n```\n\n| What you see | What it means |\n|---|---|\n| Rows | Everything works. Move on to the task. |\n| Empty list, exit 0 | Connected, but this tenant/app has no sessions in the window. Widen `--from`, or check the app is instrumented. |\n| Exit 2 | Not authenticated. `brizz auth login`. |\n| Exit 3 | The tenant or app slug doesn't exist in this workspace. Re-check `brizz describe`. |\n\nAn empty list is the common one, and it is almost never a bug in the CLI. If the app has\nnever sent telemetry, setup isn't finished — use the **brizz-instrument** skill, which\ncovers getting spans flowing in the first place.\n\n## Where to go next\n\n- Data exists, user wants to know what's wrong → **brizz-investigate** skill (investigation workflow, flags, exit codes)\n- No data yet, or a service looks sparse → **brizz-instrument** skill\n- Deeper questions once connected → the MCP server ships its own runbooks; list them with `brizz_list_skills`\n"
}

SHA-256 of public snapshot: 11254661aa439dd4e572adea71fa2ce20ff5a3970995d6ff1694b77a07613344