AI at CommunityForce
AI that knows your programs, not just the internet
Phoenix Copilot answers your questions and builds your reports from your live data. Phoenix Agents keep the routine running on a schedule. AI-writing signals and automated scoring lighten review. All of it reads your data to help you — and none of it trains on your data, ever.
Illustration of a Phoenix Copilot conversation.
Here’s your briefing for today — org-wide, and the queue was checked in full.
Stalled applicants
- 793 applications started but not submitted — 1,129 of 1,922 started are in. Review applications
- 118 submitted applications have no reviewer assigned (186 awaiting review in total). Assign reviewers
Forms left active past their close date
- The Future Leaders Fellowship closed 226 days ago but is still active. Fix in General Information
All clear
Forms closing soon in the next 7 days: none.
Ask Phoenix Copilot…
Phoenix Copilot can make mistakes. Verify important information.
Phoenix Copilot
Ask once, get the report
Say what you need to know the way you would say it to a colleague. Copilot queries your live data — the whole set, not a sample — and comes back with a report you can keep, then answers what you ask about it next. Every number is looked up, never recalled.
When you ask it to change something, it shows you the result before anything lands. You keep the call.
See how reporting and Copilot work
Phoenix Agents · Now rolling out
Stop asking. It keeps arriving.
The status report you build every Monday can build itself every Monday. Tell Phoenix what you need in plain English, confirm what it sets up, and from then on the report arrives in your team's inbox — attached, on time, without anyone asking again.
Meet Phoenix AgentsIllustration of a Phoenix Copilot conversation about creating an agent.
I can help you set that up. An agent re-runs an instruction on a schedule and emails you the result — it’s read-only, so it can report on things but can’t change data or email applicants.
To propose one, I need a few details:
- What should it do? “Send me the applicant status breakdown,” “email me the forms closing this week”…
- How often, and at what time? “Every Monday at 8 AM.”
- Who should get the email? Defaults to you if you don’t say.
Ask Phoenix Copilot…
Phoenix Copilot can make mistakes. Verify important information.
Lighter review, same reviewers
Two quieter helpers work inside the review itself. Both hand reviewers a head start — neither takes the decision out of their hands.
AI-writing signals
GPTZero-powered detection flags essays that may be AI-written and surfaces the signal beside the application — a data point for the committee, not a verdict.
Automated scoring
Quantitative criteria — GPA thresholds, eligibility fields, weighted rubrics — score themselves, so reviewers spend their attention where judgment is actually needed.
Useful because it is governed
The reason your team can lean on Phoenix is that it was built inside fences, on purpose.
How we govern AINever trained on your data
The AI reads your data to answer you — your data is never used to train AI models, ours or anyone else's.
People decide
Awards, eligibility, and every decision that touches an applicant belong to your team. AI proposes and reports; it does not decide.
Off by default, on the record
Your administrators switch AI on per organization, every run is in the audit log, and any of it can be turned off with one switch.
Phoenix Copilot and Phoenix Agents can make mistakes. Verify important information.
See it working on programs like yours
Ask Copilot a question, watch an agent get created from one sentence, and judge it on your own terms.