> ## Documentation Index > Fetch the complete documentation index at: https://docs.crewship.ai/llms.txt > Use this file to discover all available pages before exploring further. # Demo use cases > Twelve product use cases as twelve scripts — run one at a time against a seeded install, each narrated for an audience and verified by assertions. # Demo use cases The second version of the demo scripts. The first, `scripts/walkthrough.sh`, was one checklist under `set -e`: the first failing line ended it, and there was no way to run step six without steps one to five. This version is twelve units under `scripts/demo/`, one script per use case, each runnable alone and each ending in a verdict. ```bash theme={null} export CREWSHIP_PROFILE=dev2 # or CREWSHIP_SERVER scripts/demo/run.sh # list the use cases and what each needs scripts/demo/run.sh memory-recall # run one scripts/demo/run.sh --all # run all twelve, one summary table scripts/demo/run.sh --all --needs none # only the ones that need no model and no token ``` The scripts sit on the CLI integration harness under `scripts/test-harness` and drive the real `crewship` binary; nothing here reads a database or calls the API by hand. ## The use cases | # | Use case | Needs | What the audience sees | | -- | ----------------------- | ------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- | | 1 | `memory-recall` | model | A fact told to Alex in one session comes back in a fresh one, and `crewship memory search` finds it. | | 2 | `delegation` | model | Alex hands a task to Sam and reports Sam's answer; a new agent-to-agent chat appears on Sam. | | 3 | `ephemeral-hire` | — | `crewship hire` stages a contractor in a guided crew; the approval and the inbox waitpoint; `crewship hire approve`. | | 4 | `credential-escalation` | model | Morgan asks for a token it lacks; a human answers with `crewship escalation supply`, from stdin. The value never comes back out of the API. | | 5 | `approval-gate` | model | `approval-gate-demo` drafts a change and parks on `wait(approval)`; `crewship routine waitpoints approve` resumes it to completion. | | 6 | `routine-notification` | — | `workspace-digest` (query → transform → notify, no model) completes; the inbox item carries the run id. | | 7 | `schedule-wake-gate` | — | A schedule gated by `cost-spike-probe` holds on a real scheduler tick: the probe ran, the digest did not. | | 8 | `eval-tiers` | model | `crewship eval scenarios` runs two recipes on the fast and the smart tier. | | 9 | `github-injection` | github, model | A bound GitHub token reaches the container as `GH_TOKEN`; `gh auth status` inside it says so; the transcript never holds the value. | | 10 | `pack-ci-watch` | github | The [nightly CI watch pack](/guides/demo-packs#nightly-ci-watch): the delivered script, the token-zero probe, `crewship seed verify --pack ci-watch`. | | 11 | `pack-docs-drift` | github | The [docs drift pack](/guides/demo-packs#docs-drift) through `seed verify`, with this checkout as the fact-check source. | | 12 | `pack-site-replica` | — | The [site replica pack](/guides/demo-packs#site-replica) through `seed verify`; `NOT BUILT` until somebody asks Alex to copy the site. | **Needs** is what a use case cannot run without. `model` is an ACTIVE model-provider credential in the workspace; `github` is `SEED_GITHUB_TOKEN` at seed time, or a bound GITHUB credential. A use case whose need is missing does not pretend: it exits with a reason and the runner prints **SKIP** for it. A green row means the use case ran and every assertion held. ## Reading a run Each use case prints numbered steps, the commands it runs with their output, a ✓ or ✗ per assertion, and a 👀 line naming where to look in the web UI right now — the inbox, the agent, the Page. It ends with its own summary. The runner then prints one table: ``` USE CASE RESULT TIME NOTE routine-notification PASS 1s schedule-wake-gate PASS 18s pack-ci-watch SKIP 0s no GitHub token: set SEED_GITHUB_TOKEN and re-run `crewship seed` … ``` Exit status is 1 when any use case failed. A SKIP never fails the run; the reason is in the NOTE column. ## Before you start A seeded install and a login: [`crewship seed`](/cli/seed) prints the account. The use cases with a model need the seed's model credential to be ACTIVE; `eval-tiers` needs `crewship seed --with-evals`. Point the scripts at the same server the browser shows (`CREWSHIP_PROFILE` or `CREWSHIP_SERVER`) and, when the UI lives on another host than the API, set `DEMO_WEB_URL` so the 👀 lines are right. The packs with a GitHub token (10, 11) need the token at seed time — see [Demo packs → Credentials](/guides/demo-packs#credentials). Without it they SKIP, and so does `seed verify`. ## Writing one A use case is a bash script `scripts/demo/uc-NN-.sh` with a four-line header the runner lists from, `source "$HERE/lib.sh"`, `preflight`, its steps, and `finish`. `lib.sh` gives it the harness (`cs`, `ask_agent`, `assert_*`, `poll_until`, `nonce`) plus the demo layer: `demo_step`, `demo_say`, `demo_show`, `demo_ui`, `demo_need` and `demo_skip_all`, `run_routine`, `demo_cleanup`. There is no `set -e` on purpose: a failed assertion is a red line, and the audience still sees the steps after it. `scripts/demo/README.md` has the contract; the existing twelve are the examples. ## Known limits * `crewship routine schedules now` runs the target routine directly and bypasses the wake gate, so use case 7 waits for a real tick instead (under 90 seconds). * Use cases 2 and 4 depend on an agent doing what it was asked. Each retries once, then SKIPs with the reason rather than reporting the model's phrasing as a product failure. * What `walkthrough.sh` still shows and this does not: nothing. Its steps are use cases 1 to 9 here; step 8 (seeded cron schedules) no longer matches what the seed creates and became use case 7.