Ignite AI Agents · Fundraising
The Prospect Research agent qualifies donors with sourced briefs built from your CRM record, integrated wealth screening, and deterministic scoring. Fundraisers start with evidence instead of a blank page, and writes back to the record wait for a person.
Qualification brief
Maria Alvarez
Household · Donor since 2015
Recommend moving to major gift qualification.
Capacity84
Affinity72
Propensity66
Linkage58
Sources usedIdentity confidence
Proposed prospect recordPending
The exact write, shown first. Waits for your approval.
Every brief carries
Ask in plain language. Every capability reads from your live record and returns work you can check, with the evidence behind each answer. The agent’s guided workflows run in the background while you keep working.
Ask whether a constituent belongs in major gift work, even when the internal history is thin. The brief states plainly what it could not establish, and closes with one of four recommendations: qualify, cultivate, monitor, or review.
Should the Thompsons move into major gift qualification?
Capacity, affinity, propensity, and linkage are scored by the platform, not improvised by the model. The same evidence produces the same dimension scores, and each score shows what supports it.
Why did this prospect score high on affinity?
The agent pairs wealth screening from WealthEngine, DonorSearch, and Kindsight (formerly iWave) with your own giving history, so external capacity signals land next to the relationship you already have.
What wealth signals do we have for Maria Alvarez?
The agent reads relationships, households, and shared history to find the warmest visible route to a prospect. It flags which relationship signals it can stand behind, and names the gaps in your record it could not fill.
What is our warmest path to Robert Kim?
Surface major gift candidates from your constituent base, or corporate and institutional prospects from sponsorship, CSR, and workplace giving signals. Candidates come back as a scored table, and the ones you keep become profiles in your research queue.
Find corporate prospects from our sponsorship and workplace giving signals.
When research is worth keeping, the agent proposes a prospect record for your research queue. It shows you the exact write first, and the write sits at the approval gates your team configures.
Add this prospect to our research queue.
Who reaches for it
The brief is one request away. What is worth keeping goes to the record once a person approves it.
How the agent works
A disciplined research workflow runs behind every request. The agent follows the same sequence, and stops when the evidence is not there.
01
Resolves the right constituent, then pulls giving history, engagement, household, and relationship context from the live record.
02
Adds integrated wealth screening once the identity match is strong. Weak matches stop the workflow, with the reason stated so a person can resolve it.
03
Runs the platform’s deterministic scoring model across capacity, affinity, propensity, and linkage. The agent is never permitted to author or edit a score. Run it again when new giving or engagement lands, and the score recomputes from the current record.
04
Presents the sourced brief with recommended next steps. Prospect records it proposes wait for a person.
Inside the qualification brief
Every brief is laid out the same way, so your team knows where to look and what to check before acting on it.
Qualification brief
Ready to reviewWho this prospect is, why they surfaced, and how confident the match is.
Four dimensions scored by the platform, with the evidence underneath.
Sources usedIdentity confidence
Want to see a qualification brief built on your own data?
Book a working sessionGoverned by design
Prospect research touches wealth data and personal context. So the hard rules live in the platform: scoring runs in a deterministic engine, and CRM writes go through the approval gates your team configures.
See the governance modelNo score without a strong identity match. No ask band without at least three independent pieces of evidence, including your own CRM record. When the agent is blocked, it says why and stops.
The write the agent proposes is a prospect record in your research queue, and it sits at the approval gates your team configures until someone says yes.
The score of record comes from the platform’s deterministic engine. The agent must present scores and evidence exactly as returned, and is never permitted to author, edit, or reclassify them.
Finished research lands in the research record and the research queue with its sources and research date, beside the notes your team writes by hand.
Start narrow. Widen the gates as trust grows. The pace is your team's call.
No exports, no side tool, no research doc to paste back in. The agent reads the same live record your team maintains, and finished research lands back in it.
Available in the Intelligence Hub, embedded in constituent records, and in the chat panel inside Ignite. The research queue filters by score, recommendation, and research date.
Hand off qualified prospects for meeting prep, ask strategy, and cultivation planning.
See the agent
Quick wealth-signal lookups and profile-gap checks, when you don’t need a full brief.
See the agent
Plain-language answers from your live data, with sources shown.
See the agent
Proven foundation
Ignite is a new platform, built by the team nonprofits have trusted with their constituent and financial data for over 15 years.
4.5/5
Average on G2.
20M+
Constituent profiles managed across the StratusLIVE platform family.
$1B+
In annual giving processed across the StratusLIVE platform family.
“A powerful tool that empowers our team members to not only enter new data but also see a historical perspective of our donors and corporate partners.”
Maria M.
Director of Investor Management
Verified review · G2
“One source of the truth about our contacts, donors, and partners that is easily kept up to date.”
Robert W.
Director of Fundraising Operations & Digital Solutions
Verified review · G2
Honest questions
Straight answers on trust, control, and your data. The full security posture, providers included, is on the Trust & Security page.
Trust here is checkable rather than assumed. Every finding in a brief is cited to its source, scoring runs in the platform’s deterministic engine rather than in the model, and the agent refuses to guess: no score without a strong identity match, and no ask band without at least three independent pieces of evidence including your own CRM record.
No. A general chat tool answers from general knowledge, cannot run wealth screening, and cannot cite your records. The Prospect Research agent has one defined job inside Ignite: it reads your CRM record and integrated wealth screening, assembles a sourced brief for review, and presents the platform’s deterministic scores exactly as returned.
The brief itself changes nothing in your record. It lands for review with its sources attached, so a wrong finding is visible where you read it. The one write it proposes, a prospect record for your research queue, waits at the approval gates your team configures until someone says yes.
Prompts and outputs are not used to train foundation models by default, and each task routes to a model matched to the sensitivity of its data. Providers, hosting, and the full data flow are documented on the Trust and Security page for your reviewer.
It qualifies the name. Ask whether a constituent belongs in major gift work and you get a sourced brief: the four dimensions scored by the platform, the evidence behind each score, the warmest visible path in, and one of four recommendations. What it cannot establish, it says. You decide whether the call happens.
Nothing on its own. Finished research lands in the research record for review. When a brief is worth keeping, the agent asks before creating a prospect record or adding it to your research queue, and that write sits at the approval gates your team configures. Scores come from the platform’s deterministic engine, not from the agent.
Book a working session and see the Prospect Research agent read a live record, evidence and all.