Donor Retention Analyst
Finds the supporters you lost while income looked flat
- 8hard rules
- Things it must never do, enforced in every run
- 5handover rules
- Conditions where it stops and gives the work to a person
- 11output fields
- A structured result, not a paragraph you have to re-read
- ≤6steps per run
- Bounded work: at most 4 tool calls, enforced by the runtime
Read-only by design. This agent has no path to sending, spending, publishing or committing anything. Where that limit is the product, removing it would remove the reason to trust the output.
Overview
Fundraising is reported as income against target, and income can hold steady while the base underneath collapses — new donors replace lapsed ones and the total does not move. A charity can lose half its supporters over three years and read a flat income line the whole way down.
This matters more than commercial retention because acquiring a donor costs several times their first gift. A supporter who gives once and lapses loses money; the organisation only makes anything on the second, third and tenth gift. Retention is not a nice-to-have, it is the entire economics.
The failure point is consistent and early. Most lapsed donors are lost after their first gift, in the first year, and usually because of what did not happen: no thank-you within days, no word about what the money did, then a second ask arriving before either. That is a stewardship failure, not a generosity failure.
And there is almost always a quieter finding: regular gifts that stopped for a mechanical reason — an expired card, a failed instruction — where nobody decided to leave and nobody followed up.
This agent reports retention by cohort, the experience that preceded each lapse, and what each fix is worth. It contacts nobody and builds no wealth or capacity score for any individual.
Benefits
The loss becomes visible
Before three years of flat income turn into a cliff.
Stewardship fixed where it fails
Usually in the first fortnight after a first gift.
Payments recovered without a campaign
These supporters never chose to leave.
What it does
Retention behind the income line
Income holds flat while the base collapses, because new donors replace lapsed ones and the total does not move.
Finds where the loss happens
Almost always after the first gift, in the first year. That is a different fix from mid-life attrition.
Reads the experience before the lapse
Whether a thank-you went out, whether anyone said what the money did, and whether the next ask came before either.
Separates failed payments from decisions
An expired card is not a lapsed supporter. Nobody decided anything, and nobody followed up.
Values the second gift
Acquisition costs several times the first gift. The economics are entirely in the gifts after it.
Scores no individual
It builds no wealth or capacity rating. Ranking supporters by what they might be persuaded to give is a different product with its own ethics.
What this changes
What this changes about your week
- It takes over
- Measuring donor retention behind the income line.
- Done today by
- Income against target, which can hold flat while the base collapses.
- How often
- Reported monthly as income; retention rarely at all.
- Typical manual effort
- Cohort analysis plus the stewardship record before each lapse.
Why Nonprofit & NGOs in particular. Acquisition costs several times a first gift, so the economics live entirely in the second and tenth. Most loss happens in year one because of what did not happen — no thank-you, no impact, then another ask.
Runs unattended
Started by you or by an event, and it finishes on its own. Nothing waits for someone to be at a desk.
The same standard every time
The two-hundredth item is held to the bar the first one was. Consistency is the part people cannot sustain.
It cannot act on its own
Donor Retention Analyst has no path to sending, spending or committing. That limit is why its output is safe to act on.
How it runs
This agent runs server-side through the PROMIVO runtime. Each run is logged step by step and every tool call is permission-checked before it executes.
- 1InputValidated against the agent input schema
- 2Modelclaude-sonnet-5 with automatic fallback
- 3Toolsextract_structured_data
- 4PermissionsRuns READ actions automatically; anything higher waits for approval
- 5OutputStructured result matching the output schema
- 6LoggingTokens, duration and every step recorded
Demo
Demo dataIllustrative sample output, abridged.
Input
{
"period": "2022–2026",
"currency": "USD",
"supporters": [],
"suppressionThreshold": 10
}Output
{
"bySource": [
"One acquisition source costs the least per supporter and retains at 11% to year two. It is the most expensive channel you have once the second gift is counted."
],
"escalate": true,
"whatWorks": [
"Supporters who received a handwritten acknowledgement on a first gift above a threshold retained at 58%. Small volume, and worth knowing before it is discontinued."
],
"disclaimer": "An analysis of your own supporter records. No wealth, capacity or propensity score has been built for anyone; no supporter has been contacted or identified; groups below ten are suppressed; modelled uplift is derived from your own history rather than forecast; and this is not advice on fundraising regulation.",
"modelledUplift": [
"Bringing first-to-second gift conversion from 19% to the 2023 level of 26% is worth roughly 210,000 a year at your own average gift values. Modelled from your history, not a forecast."
],
"cohortRetention": [
{
"cohort": "2023",
"supporters": 4120,
"retainedYear1": 34,
"retainedYear2": 21,
"firstToSecondGiftPercent": 26
},
{
"cohort": "2025",
"supporters": 5010,
"retainedYear1": 27,
"retainedYear2": 0,
"firstToSecondGiftPercent": 19
}
],
"escalationReason": "First-to-second gift conversion is 19%, below threshold and falling across cohorts, and 23% of regular gift lapses are mechanical with no follow-up recorded.",
"groupsSuppressed": 5,
"incomeVersusBase": "Income is within 3% of four years ago. The supporter base is down 41% over the same period. New donors have been replacing lapsed ones and the income line shows none of it.",
"mechanicalLapses": "23% of regular gift lapses are expired cards or failed instructions. Nobody in that group decided to stop supporting you, and no record shows any of them being contacted.",
"stewardshipFindings": [
"Of supporters who lapsed after one gift, 71% received no thank-you within 14 days.",
"44% received a second ask before any communication about what their first gift did.",
"Supporters who received an impact update within 60 days gave again at more than twice the rate."
]
}Requirements
Integrations
No integrations required.
Before you start
- Gift history by supporter with dates and amounts
- Acquisition source and date
- Stewardship contact records: thank-yous, impact updates, asks
- Failed or cancelled regular gifts with reasons
- Requires the All-Access plan or higher
Use cases
Annual fundraising review
Retention by cohort, behind the income total.
Flat income, rising acquisition spend
The classic sign the base is shrinking.
After a campaign
Whether the donors it brought stayed.
Trustee reporting
The health of the supporter base, not just the income.
Pricing
All-Access
Billed monthly through your PROMIVO subscription. Cancel at any time.
Runs consume your plan allowance for agent executions and tokens. See plan limits
FAQ
Does it score donors by wealth or capacity?
No, and it will not. Ranking supporters by what they might be persuaded to give is a different product with its own ethical questions. This reports retention patterns and stewardship gaps.
Does it contact supporters?
No. It sends nothing and drafts nothing for sending. Fundraising communication carries consent and preference rules, and it belongs to your team.
What if we do not record stewardship contact?
Then it reports retention by cohort and says the stewardship analysis could not be performed. That gap is itself worth knowing, because it is the part that usually explains the loss.
Reviews
Reviews open once customers have run this agent.
Need this agent to work differently?
Tell us what to change and our team will scope a customised version for your business.
Customize this agent