# The internship radar — the prompts

The radar reads the **job-alert emails** your LinkedIn alert sends (set that up with the LinkedIn card in this packet), and ranks every posting against the one-page `career-fit.md` you saved in your Career Fit folder. Change the words in [brackets] before you run it.

> **The sender.** LinkedIn job alerts come from `jobalerts-noreply@linkedin.com` for everyone (confirmed from a real alert, 15 Sep 2026). The prompt filters on that address, with a `@linkedin.com` fallback in case LinkedIn varies it. Good to know: the very first email — "your job alert has been created" — already lists real postings, not an empty confirmation. It can take up to an hour to arrive, so set your alert early; in a live session, run the radar on a digest that's already in the inbox and let your own alerts feed it from then on. If your school's CDC also emails you a Symplicity digest, the same prompt reads that too.

## Cowork (Scheduled → Create with Claude)

Reads your email through your connected inbox (Gmail or Outlook), so it needs no LinkedIn login to build the table — the alert email already carries the role, employer, location and a short description of each posting. Point Cowork at your Career Fit folder first, and connect your email in **Cowork → Customize → Connectors** (or be signed into your webmail in Cowork's browser).

```
Every Monday morning, search my email for the newest job-alert email from
jobalerts-noreply@linkedin.com (or any sender at linkedin.com whose subject is about new
jobs; also accept a "Symplicity" digest from my school's career centre if one is newer).
That email lists new job postings — each with a role, employer, location and a short
description right there in the email. Read career-fit.md in my folder. Rank the postings in
the email best fit first, dropping any that break a hard constraint from that profile. Give
me a table: role, employer, location, why it fits or doesn't in two lines, and the link.
When you email me the summary, write it as a numbered list with each posting on its own
line (rank. Role — Employer, Location: the two lines) — never one paragraph, because email
flattens a table into a wall of text. List any dropped postings under the list with the
limit each broke. Also save the full result on disk so I keep a history: in my Career Fit
folder, make a subfolder `Internship Radar/<alert date> — <number of postings> matches`
(for example `Internship Radar/2026-09-16 — 6 matches`) and write the full ranked table,
with links and the dropped postings, as `ranking.md` inside it. Never move or change
career-fit.md — it stays at the folder root. Rank from what the email itself says — you
don't need to open the postings.
Optional, only if a posting looks like a strong fit: open its link for the full description
and refine that one row. If a page asks you to sign in or won't open, skip the deep read and
rank that posting from the email instead. Never invent a detail you didn't read.
If you can't find the alert email at all, tell me — don't guess.
```

## The Code tab (same folder)

For the curious. The point is the plan and the diff, not a finished page.

```
Build me the internship radar as a small page I can run with one click. It should read
career-fit.md in this folder, take a LinkedIn job-alert email I paste into it, and rank the
postings against the profile with two lines on why each fits. Show me the plan before you
build anything. Keep it to one file.
```

## Prove it (Task 3)

Take the top-ranked posting. Open the link yourself. Does the posting say what the two lines say?
Then change one line of your profile — a city or a sector — run again on the top three only, and see whether the ranking moves.