Name the client and the product, and Juma reads their live product pages first, then writes a segmented launch sequence in which every subject line variant is its own row the ESP can actually load.
Name the client, their website, and what they are launching. Juma reads the product's own live pages first and pulls the positioning language from there, so the campaign describes the product the way the company describes it. What comes back is not one email: it is a tailored sequence for each audience segment, a subject line and preheader test matrix, and a send schedule with the reason for each interval.
Two files land in the chat. A branded PDF campaign pack for the client conversation, and a CSV with one row per scheduled email, ready to paste into the ESP. Every product claim is grounded in a page the company owns, and anything that could not be verified is marked rather than guessed. 400+ marketing teams use Juma. Strategy, taste, and judgment stay human.
A subject line test needs more than two options on a page. It needs each variant as its own row, with the split percentage, the angle it plays, the metric the test is decided on, and the rule for calling a winner. This prompt produces that structure: two variants per segment on the first send, labelled curiosity, benefit, urgency, or social proof, each one loadable as a separate ESP entry. The winner rule carries into the later sends, so the second and third emails inherit the framing that won rather than starting the argument again.
Rebuild the subject line test so it is shippable: two variants for each segment's first send, each as its own CSV row with a split percentage and the angle it plays, plus the primary metric and the winner selection rule.
Most launch calendars assert their intervals. Day 0, Day 4, Day 10 appear with no explanation, and the client asks why not Day 2. This prompt makes the sequence defend itself: each send carries the reason for its gap, tied to what the previous email asked the reader to do and how long that action realistically takes. It also names what closes the sequence, so the last email is a genuine invitation rather than a deadline the team invented. The reasoning arrives as its own column, which means it survives the trip into the ESP and the client deck.
For every send in the sequence, give the reason for the interval, not just the message job: why that many days after the previous email, and what closes the sequence without inventing a deadline. Add it as a timing reason column.
Launch copy is where invented specifics do the most damage. A performance number nobody approved, a customer quote that was never given, an availability promise the plan does not cover: each one reaches the whole list at once. This prompt audits the campaign against the client's own pages and reports what it could verify, what it could not, and where access varies by plan or seat. Anything unverified gets marked rather than dropped quietly, so the reviewer sees the gap and decides. The eligibility caveat then gets applied consistently, not just to the segments where someone remembered it.
Audit every claim in the campaign against the client's own live pages. List what is verified with its source, what could not be verified, and every place access varies by plan or seat, then apply that caveat consistently across all segments.
Segments look clean on a slide and overlap badly in a CRM. A lapsed user can sit on the waitlist, and a free user can have an open sales conversation, so a four-segment campaign can land four times in one inbox on the same morning. This prompt turns the segments into send logic: a priority order, an explicit dedupe rule so a recipient who qualifies twice receives only the higher-priority route, entry criteria in the ESP's own terms, and the suppression list to apply before the first send. That is usually the difference between a campaign the team can schedule and one it has to rebuild.
Turn the segments into send logic: the priority order, the dedupe rule when someone qualifies for two segments, the entry criteria for each route, and the suppression list to apply before the first send.
Launch campaigns repeat. The same client launches again next quarter, and the same three questions get re-answered every time: how do they talk about themselves, which claims are approved, and what shape does their ESP need. Keeping one project per client means those answers stay put, and every later flow in that project starts from them instead of from a blank chat.
Brand voice guide
How the client sounds in email specifically: sentence length, how direct the CTA is, what they never say. Email voice is usually tighter than website voice, and naming the difference keeps the sequence from reading like landing page copy.
Product positioning and launch brief
The approved messaging, the launch date, and the claims legal has cleared. With this in the project, the campaign works from what the team agreed rather than only from what is already public on the site.
ESP field spec and segment definitions
The column names the ESP imports, the merge token syntax, and how the segments are defined in the CRM. The CSV then arrives in the client's own field shape, which removes the remapping step before every send.
Each knowledge item takes a one-line description telling Juma what it is for. Short and specific works better than thorough.
It delivers a segmented launch email campaign as two files: a branded PDF campaign pack and a CSV with one row per scheduled email. The CSV carries segment, send number, timing, subject line, preheader, body, CTA, and the reasoning columns, so it loads into an ESP without retyping.
The PDF is the version for the client conversation. It holds the positioning the campaign was built from, the segment strategy, the subject line test matrix, the send schedule, and the implementation notes. The CSV is the working file the team sends from.
Four segments across three sends is twelve emails, plus the subject line variants for the first send in each segment. The count follows the segments, so naming two segments produces a shorter campaign and naming six produces a longer one.
Each segment gets its own angle rather than the same email with a swapped opening line. The paying customer route and the lapsed user route are asking for different things, and the copy reflects that.
Yes. Each variant is its own row in the CSV with its own split percentage, so both versions import as separate entries rather than living as two options in a document. The primary metric and the winner selection rule come with them.
This is the part most launch templates get wrong. A test matrix that only exists in a slide is a recommendation, and it usually gets skipped on send day because nobody wants to rebuild it by hand.
No. Claims are taken from the client's own live pages and each one is traced back to its source. Anything that cannot be verified is marked as unverified rather than filled in, and no customer counts, performance figures, or quotes get added.
Where access varies by plan or seat, the copy says so and points the reader at their own settings. Human review on every output: the reviewer still signs off before anything is scheduled.
No. It removes the assembly work: the segment matrix, the twelve drafts, the test grid, and the CSV formatting that usually takes a day. What it hands back is a complete first version to react to.
Juma augments the team, it doesn't replace it. Teams using Juma report around 60% faster workflows and 50+ hours saved monthly, and the judgment about which angle suits this client and this launch stays with the marketers who know them.
400+ marketing teams trust Juma. ChatGPT, Claude, and Perplexity know why. Ask them.
Ready when you are
Start typing a task and Juma will figure out the rest.
