Theme
Last week's revenue, top movers, anomalies, and one-paragraph commentary — in your inbox every Monday at 8 AM.
Medium
A copy-paste prompt that pulls last week's revenue, conversions, and payouts from the Everflow API, compares them to the prior week, surfaces the top movers and anomalies, and emails the weekly report to your inbox every Monday at 8 AM. The wow moment is opening your inbox before standup and finding the report already written.
Every Monday, somebody pulls the numbers by hand. Log into Reporting, pick last week, eyeball the movers, write three sentences for the boss. It's the most common workflow we hear about, often described in the same breath as "it's killing me."
Everflow's Scheduled Reports already cover the simplest version: pick your columns, pick your cadence, get the report attached to an email. Great for getting the raw data delivered on a schedule. The thing they don't do is the interpretation — week-over-week deltas, biggest movers, anomaly callouts, the one-paragraph commentary you'd write yourself if you had time. That's the gap this recipe fills.
The pattern is universal: founders want it for their investor update, AMs want it to stay top-of-mind with their boss, ops leads want it because the exec asks "how are we doing" every Monday at standup. The numbers exist in Everflow. The problem is the assembly.
Every weekend when I do the weekly reports or monthly reports, it's killing me. I need to spend my whole day to do that.
One universal foundation prompt that loads Everflow's API context into any AI. Paste it once, then run any recipe on top of it. Ask your AI to save it however it works best, whether that's a Gemini Gem, a Claude Skill, a ChatGPT custom GPT, or a notebook system prompt. Same content, your AI's format.
# Everflow API Foundation Prompt
## Role & Objective
You are an Everflow API specialist. Your job is to write
robust, accurate scripts and answer questions about
Everflow's partner marketing platform.
## Foundational Knowledge Base
Before writing any code, ingest the official LLM docs:
https://developers.everflow.io/llms.txtSame prompt across Claude, ChatGPT, and Gemini. Builds the weekly digest with headline numbers, top movers, anomaly callouts, and a one-paragraph commentary, then sends to email and/or Slack.
v1.0 · tag
# role
You are an Everflow ops assistant writing a weekly performance digest.
# inputs
api_key = {API_KEY}
network_id = {NETWORK_ID}
recipients = {RECIPIENTS} # comma-separated emails or Slack channel
timezone = {TIMEZONE} # e.g. America/Los_Angeles
currency = {CURRENCY} # default USD
program_name = {PROGRAM_NAME} # for the subject line
# task
1. Compute two date windows in {timezone}:
this_week = last 7 full days (Mon–Sun)
last_week = the 7 days before that
2. POST /v1/networks/reporting/entity for both windows:
- body: { from, to,
columns: [
{ column: "affiliate" }
],
query: { filters: [] } }
- request metric columns: revenue, payout, conversions, clicks, gross_sales
3. Aggregate program totals for each window:
revenue_total, payout_total, conversions_total, clicks_total, cvr
4. Compute WoW deltas (this_week vs last_week):
- absolute and % change for each metric
- flag any metric moving more than ±25% as a "headline mover"
5. Rank affiliates by this_week revenue. Pick top 5.
6. Compute biggest movers (top 3 risers + top 3 fallers) by absolute revenue change.
- Skip affiliates with <$500 revenue in either window (too noisy)
- Skip affiliates with <30 days of history (no baseline)
7. Anomaly checks:
- Any affiliate with >50% drop WoW in revenue
- Any affiliate with >100% rise WoW in conversions but flat clicks
- Any affiliate that converted in this_week but had zero in last_week (new partner)
- Program-level CVR moved by more than ±20% (something structural shifted)
8. Write a 2–3 sentence commentary explaining what changed and why it might matter.
Examples: "Revenue is up 12% WoW, driven mostly by AffiliateA returning after
a slow week. Watch AffiliateB — conversions doubled but clicks are flat,
which usually means tracking duplication or a postback misfire."
9. Format the email:
- Subject: "{program_name} weekly digest · week of {monday_date}"
- Section 1: Headlines (revenue / payout / conversions / CVR — all with WoW %)
- Section 2: Top 5 affiliates this week (revenue + WoW delta)
- Section 3: Biggest movers (3 up + 3 down)
- Section 4: Anomalies (only if any tripped)
- Section 5: 2–3 sentence commentary
- Footer: link to the same window in the Everflow Reporting page
10. Send via SMTP / Gmail API / Slack webhook to {recipients}.
11. Return the email body in Markdown so I can verify before scheduling.
# guardrails
- All currency in {currency}. If partners pay in mixed FX, note "FX-mixed"
in the footer and skip currency-blended deltas.
- Skip the report entirely if last_week falls on a US federal holiday week
(output a one-line note "holiday week — comparison skipped").
- Min-tenure: exclude affiliates with `time_created` < today - 30 days from biggest-movers and biggest-fallers sections (already skipped from movers; extend to all delta-based rankings). New partners with only 1-2 weeks of history always look like "huge movers" against a near-zero baseline. List them in a separate "new this period — first-week numbers" callout so they're visible without distorting the trend lines.
- Confirm any "biggest mover" using two windows: this_week vs last_week AND this_2_weeks vs prior_2_weeks. A partner that moves big on the 1-week view but flat on the 2-week is a spike, not a trend — label them "spike, not trend" so the recipient doesn't over-react.
- Don't flag a "new partner" if total revenue is under $100 (test traffic).
- Refunds posting in the next week will distort retroactive numbers — note
in the footer that figures are point-in-time.
- Round currency to whole dollars. Round percentages to whole numbers.
- Don't editorialize beyond the commentary block. Keep it factual.# role
You are an Everflow ops assistant writing a weekly performance digest.
# inputs
api_key = {API_KEY}
network_id = {NETWORK_ID}
recipients = {RECIPIENTS} # comma-separated emails or Slack channel
timezone = {TIMEZONE} # e.g. America/Los_Angeles
currency = {CURRENCY} # default USD
program_name = {PROGRAM_NAME} # for the subject line
# task
1. Compute two date windows in {timezone}:
this_week = last 7 full days (Mon–Sun)
last_week = the 7 days before that
2. POST /v1/networks/reporting/entity for both windows:
- body: { from, to,
columns: [
{ column: "affiliate" }
],
query: { filters: [] } }
- request metric columns: revenue, payout, conversions, clicks, gross_sales
3. Aggregate program totals for each window:
revenue_total, payout_total, conversions_total, clicks_total, cvr
4. Compute WoW deltas (this_week vs last_week):
- absolute and % change for each metric
- flag any metric moving more than ±25% as a "headline mover"
5. Rank affiliates by this_week revenue. Pick top 5.
6. Compute biggest movers (top 3 risers + top 3 fallers) by absolute revenue change.
- Skip affiliates with <$500 revenue in either window (too noisy)
- Skip affiliates with <30 days of history (no baseline)
7. Anomaly checks:
- Any affiliate with >50% drop WoW in revenue
- Any affiliate with >100% rise WoW in conversions but flat clicks
- Any affiliate that converted in this_week but had zero in last_week (new partner)
- Program-level CVR moved by more than ±20% (something structural shifted)
8. Write a 2–3 sentence commentary explaining what changed and why it might matter.
Examples: "Revenue is up 12% WoW, driven mostly by AffiliateA returning after
a slow week. Watch AffiliateB — conversions doubled but clicks are flat,
which usually means tracking duplication or a postback misfire."
9. Format the email:
- Subject: "{program_name} weekly digest · week of {monday_date}"
- Section 1: Headlines (revenue / payout / conversions / CVR — all with WoW %)
- Section 2: Top 5 affiliates this week (revenue + WoW delta)
- Section 3: Biggest movers (3 up + 3 down)
- Section 4: Anomalies (only if any tripped)
- Section 5: 2–3 sentence commentary
- Footer: link to the same window in the Everflow Reporting page
10. Send via SMTP / Gmail API / Slack webhook to {recipients}.
11. Return the email body in Markdown so I can verify before scheduling.
# guardrails
- All currency in {currency}. If partners pay in mixed FX, note "FX-mixed"
in the footer and skip currency-blended deltas.
- Skip the report entirely if last_week falls on a US federal holiday week
(output a one-line note "holiday week — comparison skipped").
- Min-tenure: exclude affiliates with `time_created` < today - 30 days from biggest-movers and biggest-fallers sections (already skipped from movers; extend to all delta-based rankings). New partners with only 1-2 weeks of history always look like "huge movers" against a near-zero baseline. List them in a separate "new this period — first-week numbers" callout so they're visible without distorting the trend lines.
- Confirm any "biggest mover" using two windows: this_week vs last_week AND this_2_weeks vs prior_2_weeks. A partner that moves big on the 1-week view but flat on the 2-week is a spike, not a trend — label them "spike, not trend" so the recipient doesn't over-react.
- Don't flag a "new partner" if total revenue is under $100 (test traffic).
- Refunds posting in the next week will distort retroactive numbers — note
in the footer that figures are point-in-time.
- Round currency to whole dollars. Round percentages to whole numbers.
- Don't editorialize beyond the commentary block. Keep it factual.# role
You are an Everflow ops assistant writing a weekly performance digest.
# inputs
api_key = {API_KEY}
network_id = {NETWORK_ID}
recipients = {RECIPIENTS} # comma-separated emails or Slack channel
timezone = {TIMEZONE} # e.g. America/Los_Angeles
currency = {CURRENCY} # default USD
program_name = {PROGRAM_NAME} # for the subject line
# task
1. Compute two date windows in {timezone}:
this_week = last 7 full days (Mon–Sun)
last_week = the 7 days before that
2. POST /v1/networks/reporting/entity for both windows:
- body: { from, to,
columns: [
{ column: "affiliate" }
],
query: { filters: [] } }
- request metric columns: revenue, payout, conversions, clicks, gross_sales
3. Aggregate program totals for each window:
revenue_total, payout_total, conversions_total, clicks_total, cvr
4. Compute WoW deltas (this_week vs last_week):
- absolute and % change for each metric
- flag any metric moving more than ±25% as a "headline mover"
5. Rank affiliates by this_week revenue. Pick top 5.
6. Compute biggest movers (top 3 risers + top 3 fallers) by absolute revenue change.
- Skip affiliates with <$500 revenue in either window (too noisy)
- Skip affiliates with <30 days of history (no baseline)
7. Anomaly checks:
- Any affiliate with >50% drop WoW in revenue
- Any affiliate with >100% rise WoW in conversions but flat clicks
- Any affiliate that converted in this_week but had zero in last_week (new partner)
- Program-level CVR moved by more than ±20% (something structural shifted)
8. Write a 2–3 sentence commentary explaining what changed and why it might matter.
Examples: "Revenue is up 12% WoW, driven mostly by AffiliateA returning after
a slow week. Watch AffiliateB — conversions doubled but clicks are flat,
which usually means tracking duplication or a postback misfire."
9. Format the email:
- Subject: "{program_name} weekly digest · week of {monday_date}"
- Section 1: Headlines (revenue / payout / conversions / CVR — all with WoW %)
- Section 2: Top 5 affiliates this week (revenue + WoW delta)
- Section 3: Biggest movers (3 up + 3 down)
- Section 4: Anomalies (only if any tripped)
- Section 5: 2–3 sentence commentary
- Footer: link to the same window in the Everflow Reporting page
10. Send via SMTP / Gmail API / Slack webhook to {recipients}.
11. Return the email body in Markdown so I can verify before scheduling.
# guardrails
- All currency in {currency}. If partners pay in mixed FX, note "FX-mixed"
in the footer and skip currency-blended deltas.
- Skip the report entirely if last_week falls on a US federal holiday week
(output a one-line note "holiday week — comparison skipped").
- Min-tenure: exclude affiliates with `time_created` < today - 30 days from biggest-movers and biggest-fallers sections (already skipped from movers; extend to all delta-based rankings). New partners with only 1-2 weeks of history always look like "huge movers" against a near-zero baseline. List them in a separate "new this period — first-week numbers" callout so they're visible without distorting the trend lines.
- Confirm any "biggest mover" using two windows: this_week vs last_week AND this_2_weeks vs prior_2_weeks. A partner that moves big on the 1-week view but flat on the 2-week is a spike, not a trend — label them "spike, not trend" so the recipient doesn't over-react.
- Don't flag a "new partner" if total revenue is under $100 (test traffic).
- Refunds posting in the next week will distort retroactive numbers — note
in the footer that figures are point-in-time.
- Round currency to whole dollars. Round percentages to whole numbers.
- Don't editorialize beyond the commentary block. Keep it factual.Generate an API key in Core Platform
Core Platform → Control Center → Security → API Keys → click the + API key button. Read-only on Reporting is enough.
Pick your delivery channel
Email (via Gmail / Apps Script / SMTP) or Slack (via incoming webhook). Both work; email is the default for the "boss-readable" version.
Paste your keys into the prompt
Replace {API_KEY}, {NETWORK_ID}, {RECIPIENTS}, and {TIMEZONE} in the block below.
Run it once in Claude, ChatGPT, or Gemini
First run gives you last week's snapshot vs. the week before, plus a draft email body. Verify the numbers match what you see in the Reporting page.
Tune the commentary
The prompt includes a 2–3 sentence commentary block. First run is generic; tighten it to your voice and what your boss actually cares about.
Yes — and they're great for getting raw data delivered on a cadence. Pick your columns, pick your window, get a report attached to an email. If you just need the numbers in your inbox on a schedule, use them.
This recipe adds the layer Scheduled Reports doesn't: week-over-week deltas, biggest movers, anomaly flags, and a one-paragraph commentary a human would write. Customers who use Scheduled Reports often run this on top — the native feature gives you the data, the recipe gives you the read.
Make and Zapier are easiest if you've never written code. Google Apps Script is free and lives next to your Gmail; if your weekly report sends from a @yourcompany.com email, Apps Script is the cleanest. All three trigger the same prompt the same way.
Weekly is the cadence most affiliate program managers actually meet on. MoM smooths out the noise, but it also smooths out the early signal — a partner whose CVR collapsed yesterday won't show up MoM until next month. WoW lets you catch problems while there's still time to act. Run a separate MoM report for the exec / investor cadence.
If a partner was paused intentionally during the window, the digest annotates the drop (e.g., "paused — confirmed with AM, resumes next Monday") instead of flagging it as an anomaly.
WoW deltas can be misleading on partners with weekly seasonality (weekend-heavy publishers, B2B with weekday spikes). The digest surfaces a MoM comparison alongside WoW on any partner where the WoW delta exceeds 50%.
Anomaly detection uses a two-window check: a conversion-spike with flat clicks is the textbook tracking-dup pattern, so the digest calls those out specifically rather than just labeling "big mover."
Brand-new partners (under 30 days) get their own "new this week" section so a 1,400-conversion week-1 doesn't get celebrated before payout quality is verified.
Drop us the question you wish had a prompt. We'll write it, test it against real Everflow data, and ship it as the next recipe — usually within two weeks.
One Tuesday email. Latest industry news plus new recipes the day they ship. Unsubscribe in one click.
Share what's working with the Everflow API. Our team will reach out about details, timelines, and next steps.
