Civis Platform · Audience Builder

Describe the audience you want. We'll build it.

Audience Builder turns plain-English briefs into structured queries against your warehouse — so analysts stop writing SQL for list pulls, and campaign teams stop waiting three days for them.

SOC 2 Type II FedRAMP Moderate Built on Civis AI
app.civisanalytics.com/audience-builder/donors-2026-q1
Audiences · Donors > $100 — California
Donors > $100 — California
Chat Filters Statistics Export
EA
Show me Catholic donors in California who gave more than $100 last year.
AI
I parsed that into three filters on donors_fy24. Here's what I built — 23,418 records match. Shall I run baseline stats?
religioninCatholic state=CA gift_amt_ytd>$100
EA
Yes — and drop anyone who gave in the last 30 days.
Refining filters…
Audience size
23,418
3.2% of donor universe · 94% match confidence
Age distribution vs baseline
18–294%
30–4411%
45–5928%
60–7438%
75+19%
Gift amount (last 12 mo)
$100–24946%
$250–49931%
$500+23%
Trusted by the teams behind
How it works

From sentence to segment, in under a minute.

Audience Builder sits on top of your existing Redshift warehouse and your Civis Platform permissions. No new data store to maintain — the source of truth stays yours.

Describe

Write a natural-language brief.

No SQL, no query-builder UI gymnastics. Just say who you want — Audience Builder handles the translation.

Catholic donors in California
who gave more than $100
last year — but not in the
last 30 days.
Resolve

Civis AI maps it to your schema.

Each brief becomes a set of structured filters — list, boolean, or range — grounded in your real column names and descriptions.

religioninCatholic state=CA gift_amt_ytd>100 last_gift_days>30
Deliver

See the count, then export.

Streaming preview, baseline statistics, and a clean hand-off to your ESP, ad platform, or Civis campaign tooling.

23,418
matched records
What's inside

Built for analysts. Usable by everyone.

Describe the audience you want in plain English. Civis AI finds it — no SQL, no spreadsheets, no back-and-forth with your data team.

Accurate results

You describe it. We find the right people.

Just say what you're looking for — "Catholic donors in California who gave over $100 this year." Civis AI translates your request into precise targeting criteria so you always get exactly who you meant, not a rough approximation.

  • Always on-target. Civis AI works from your actual data, so every result maps to real people in your database.
  • Easy to review. Every audience comes with a clear summary of who's included — simple to share with colleagues or compliance teams.
  • Analyst-friendly. Your data team can jump in and adjust any criteria at any time without starting over.
Parsed filter manifest 4 constraints · dataset: donors_fy24
religion list value in ["Catholic"] · 1 of 7 categories selected
state list value = "CA" · 1 of 50 categories selected
gift_amt_ytd range min > $100 · max unconstrained
opted_in_email boolean equals true · auto-added by suppression policy
Live preview

See results update as you refine.

Counts update in real time as you adjust your criteria. Change your mind halfway through? Just update your description — no need to wait for the previous search to finish.

  • Ready when you arrive. Data refreshes overnight so results load fast from the moment you log in.
  • No surprise slowdowns. Long-running searches show their progress so you always know what's happening.
  • Change your mind freely. Adjust your criteria at any point without starting over.
Live query stream SSE · /api/audience/preview
→ startdataset donors_fy24 · 4 filters
← stagecompile SQL ok (182 ms)
← stagefetch universe count ok (0.6s)
← partialmatched 18,204 · streaming
← partialmatched 21,093 · streaming
← donefinal 23,418 · 12.4s · warm cache hit
Instant profile

Every audience comes with a snapshot.

Before you export, Civis AI automatically profiles your audience so you can see who you're reaching at a glance. No extra steps, no separate analysis.

  • Know your audience instantly. See age, geography, and other key traits before you export.
  • Spot surprises early. Unusual skews are flagged automatically so nothing sneaks through.
  • Share with your team. Send a link — teammates see the same view, not a screenshot.
Audience profile vs. baseline universe (donors_fy24, n = 731,208)
Size
23,418
Universe share
3.2%
Age vs. universe
18–29−65%
30–44−38%
45–59+12%
60–74+41%
75++18%
12s
Median time from prompt to audience count, on warm cache.
Internal benchmark · donors_fy24
3 days → 3 min
Typical cycle time, analyst-gated SQL vs. self-serve Audience Builder.
Pilot cohort, Q4 2025
100%
Filter manifest coverage — every audience ships with a traceable, editable constraint list.
Every audience, by design
0
New data stores to stand up. Audience Builder queries your existing Redshift warehouse.
Architecture
Who it's for

One interface. Every list-cutting job your team runs.

Audiences bind to the dataset they were built against — so each team works in their own corner of the warehouse, with their own schema and their own permissions.

Nonprofits & Advocacy

Donor segmentation without the SQL queue.

Fundraisers pull mid-donor and lapsed-donor lists in real time — instead of Slacking an analyst and waiting three days.

Lapsed donors in swing states, gave $50–500 in 2023, not contacted in 90 days.
Media & Entertainment

Subscriber targeting that moves at marketing speed.

Campaign managers cut audiences for paid social, push, and email directly against the subscriber warehouse — with baseline stats attached.

Subscribers who watched drama in the last 30 days, at risk of churn, opted in to email.
Public Sector

Outreach lists with a full audit trail.

Every audience carries its filter manifest, so compliance reviewers can inspect exactly which constituents were contacted, and why.

Residents in ZIP codes with >20% flood-risk, 65+, enrolled in the alerts program.
Healthcare & Insurance

Cohort definition for outreach campaigns.

Care teams define outreach cohorts by clinical and demographic attributes — without exporting PHI to a third-party tool.

Members 55+ with one or more chronic conditions, no PCP visit in the last year.
Consumer Marketing

Lookalikes, suppression, lift — on your terms.

Build suppression lists, VIP cohorts, and lookalike seeds against the CRM you already trust. Export to any destination.

Customers with AOV $200+, purchased in Q4, not in the VIP loyalty tier yet.
Political & Civic

Persuasion universes on election time.

Campaigns, PACs, and party committees cut voter universes live — updated against the latest file, defensible on filter-by-filter basis.

Sporadic voters 2020-forward, support score 60+, within TV market, no recent contact.
"Our campaign team used to queue up list requests three days out. Now they build and tune their own audiences while we're still in the meeting — and we see every filter they used."
DR
Director of Analytics
National advocacy organization · Civis Platform customer
Security & architecture

Deploys where your data already lives.

Audience Builder runs as a Civis Platform Service inside your org. Warehouse queries use the viewer's Civis API key — so every row access is governed by the same RBAC you already trust.

No data leaves your environment to reach Civis AI. Only schema metadata and the natural-language prompt are sent to Amazon Bedrock.

SOC 2 Type II

Annually audited. Reports available under NDA.

FedRAMP Moderate

Authorized for federal data workloads.

Data stays with you

Only schema + prompt leave your VPC — never rows.

Viewer-scoped RBAC

Queries run with the viewer's Civis API key.

Questions

Frequently asked.

Where does Audience Builder run? +

As a Civis Platform Service, inside your Civis org. It queries your existing Redshift warehouse via the Civis API — there's no second data store to provision or keep in sync.

What does Civis AI actually see? +

Your natural-language prompt, your dataset's schema (column names and remarks), and — for list filters — the distinct values for categorical columns. Row-level data never leaves your VPC to reach Bedrock.

Can I edit filters by hand? +

Yes. Every audience exposes its full filter manifest. You can edit filters in a structured UI, keep chatting, or both. The natural-language interface is a starting point — not a lock-in.

Which datasets are supported? +

Any Redshift table with a table comment and per-column remarks. Admins configure datasets per Civis org via the admin page; audiences are permanently bound to a dataset at creation.

How do exports work? +

Exports hand off to the destinations your Civis Platform org already uses — ESPs, ad platforms, SFTP, CSV. Every export carries its audience ID, so the filter manifest is traceable from campaign back to prompt.

Is there a free trial? +

Audience Builder is available to existing Civis Platform customers and to prospects as part of a guided pilot. Request a demo and we'll scope a short pilot against one of your datasets.

Get started

Cut your next list in the meeting it came up in.

We'll run a working pilot against one of your Redshift tables. You'll see your first audience in the first session.

SOC 2 Type II FedRAMP Moderate Deploy in hours

Tweaks

Hero variation
Layout + headline
A — hero-first, dark brand gradient, big product mock on the right.
B — type-forward light hero; the app mock sits below in its own band.
C — left copy, right full-bleed navy art panel anchoring the product mock.