How AI Powers FUNDesk Org: Prospect Research, Built-in Assistant, and Bot Integration

Last updated: February 2026

There are three distinct AI stories in FUNDesk Org, and each one solves a different problem for nonprofit fundraisers.

The first: the Prospect Research engine. Point it at a donor or prospect, and AI-powered research surfaces giving history, capacity indicators, prior gifts, recurring-gift patterns, and a preliminary engagement score. This replaces the manual spreadsheet work that eats hours of every gift officer's week.

The second: a built-in AI assistant inside the CRM web UI. You open the chat panel, ask a question in plain English, and the assistant queries your donor data, creates records, or updates gift opportunities. It streams responses in real time and requires confirmation before any write operation.

The third: external bot integration through the FUNDesk Bot skill file. Your AI bot, running in a terminal or connected to whatever tools you use, gets a skill file that teaches it the entire CRM API. Generate the file, drop it into your bot config, and your agent can manage donors, gift opportunities, tasks, and notes from wherever you already talk to it.

This post is a deep-dive into all three systems. If you want to understand how the AI features work before using them, this is where to start.

What Each System Does

Prospect Research (Donor & Wealth Screening)

The Prospect Research engine is the AI feature most specific to fundraising. When you are evaluating a donor or a new prospect, your team kicks off research from FUNDesk Org. The engine pulls together what it can find and produces:

Giving History: Prior gifts, frequency, and trend over time
Capacity Indicators: Signals that point to a prospect's ability to give
Recurring-Gift Patterns: Whether the donor sustains monthly or annual support
Engagement Signals: Event attendance, volunteer activity, and prior outreach
Wealth Screening Summary: Publicly available capacity markers, summarized
Preliminary Engagement Score: A simple A through D rating based on the combined signals

This research feeds directly into the grantmaker matching engine. A prospect scored as a strong major-gift candidate gets matched against grantmakers and giving circles whose priorities align. The whole chain, from research to a recommended ask, happens inside the CRM.

The engine uses your choice of LLM through OpenRouter. Claude, GPT-4o, Llama, Gemini, pick whichever model gives you the best results for your volume. Your donor records stay securely in FUNDesk Org. Only the data needed for the summary goes to the LLM.

Built-in AI Assistant (In-App)

When you are inside the CRM, the assistant lives in the chat panel. It has 13 tools: 8 read and 5 write.

Read tools (auto-execute):

search_records: full-text search across all records
list_records: list records with optional filters
get_record: get a specific record by ID
list_objects: list all object types
get_object: get object schema with attributes
list_tasks: list tasks (optionally filtered)
get_notes: get notes for a record
list_lists: list saved lists

Write tools (require confirmation):

create_record: create a new record
update_record: update an existing record
delete_record: delete a record
create_task: create a task
create_note: add a note to a record

Read tools execute immediately. Write tools show a confirmation card in the UI: you review the action, click Confirm or Cancel. No data changes without your approval.

For fundraisers, this means you can ask questions like:

"Which donors in Texas have gift opportunities over $50k?"
"Show me all gift opportunities in the Submitted to Grantmaker stage"
"What is the total pipeline value for major-gift prospects this month?"
"Find all donors who lapsed but gave more than $10k last year"

External Bot Integration (FUNDesk Bot)

When you are outside the CRM, your AI bot handles it. The bot uses a skill file that documents the full REST API: 19 endpoint categories covering workspaces, objects, records, search, tasks, notes, lists, and notifications.

The skill file is a Markdown document with YAML frontmatter. The bot reads it, understands the API structure, and makes HTTP requests on your behalf. No SDK, no special client library. Just REST calls with a Bearer token.

Here is what that looks like in practice:

> add the donor from this morning's call to the CRM

  Creating record in FUNDesk Org...

  done Mike's Family Foundation, Dallas TX
  Engagement score: B, Suggested ask: $75,000

  Want me to run the grantmaker match?

> show me all gift opportunities closing this week

  Querying FUNDesk Org...

  4 gift opportunities expected to close this week:
  - Dallas Community Fund ($45k, Pledge Signed)
  - Sunrise Family Trust ($25k, Verbal Commitment)
  - Metro Arts Circle ($120k, Pledge Signed)
  - Green Valley Foundation ($35k, Verbal Commitment)

  Total pipeline: $225k

> add a note to the Metro Arts gift opportunity about the grantmaker call

  Added note to Metro Arts Circle ($120k, Pledge Signed):
  "Spoke with the program officer. They need an updated impact
   report for February. Donor agreed to review by EOD tomorrow."

  done. Want me to create a follow-up task?

The bot chains operations naturally. It searches for "Metro Arts," finds the gift opportunity, creates a note, then offers to create a follow-up task. Multi-step workflows, no manual API calls.

How Prospect Research Works

The Prospect Research engine follows a streamlined pipeline:

Kickoff: The gift officer opens a donor or prospect record and starts research
Gathering: The system pulls giving history and engagement signals from your records and connected sources
Structuring: The gathered information is structured into a clean profile: gifts, dates, amounts, touchpoints
Analysis: The structured profile goes to the AI model via OpenRouter with a specialized prompt that asks for specific signals
Scoring: The system summarizes giving history, capacity indicators, and engagement, then assigns an engagement score
Storage: Results are stored as structured fields on the donor record, visible in both the UI and through the API
Matching: The engagement score and signals feed directly into the grantmaker matching engine

The AI model works from structured profile data, not raw documents. Donor PII can be stripped before analysis if your privacy or compliance requirements demand it.

Why AI Instead of Rules

Traditional prospect scoring uses rule-based logic: if total prior giving > $X and last gift < Y months ago, then rating = B. This works but is brittle. Edge cases break it constantly.

The AI approach handles nuance. A donor with modest prior gifts but consistent, growing support might be a better major-gift prospect than the numbers suggest. A household with seasonal, event-driven giving needs different evaluation than a steady monthly sustainer. The AI considers context that rules miss.

You can also customize the analysis. If your development office weights certain signals more heavily, the system can weight them accordingly.

How the Built-in Assistant Works

The in-app assistant follows a streamlined pipeline: you type a question, the AI processes it against your workspace data, and results stream back in real time.

Dynamic Schema Awareness

The assistant is not static. It reads your workspace schema at request time. Every object type, every attribute, every status value is available to the AI on each request.

Add a "Grantmakers" object with custom attributes for funding priorities and giving ranges, and the assistant knows about it on the next message. No configuration, no retraining. The AI automatically understands your fundraising data model, including your gift pipeline stages, engagement-score options, and program categories.

Read/Write Safety Model

Read operations (searching records, listing gift opportunities, checking pipeline status) execute immediately. Write operations (creating records, updating gift opportunities, deleting data) show a confirmation card in the UI first.

For example, if you say "Create a gift opportunity for Metro Arts Circle, amount $120k, major gift," the assistant first searches for Metro Arts Circle to check if it already exists, then presents a confirmation card: Create Gift Opportunity, Donor: Metro Arts Circle, Amount: $120,000, Type: Major Gift, Engagement Score: B. Two buttons: Confirm and Cancel. Only Confirm triggers the write.

This safety model is critical for development teams managing live gift opportunities worth tens of thousands of dollars. No data changes without your explicit approval.

Real-Time Streaming

Responses stream in real time. Tokens appear as they are generated, so the UI updates progressively instead of making you wait for a complete response. This makes the assistant feel responsive even for complex queries.

Model Flexibility

The assistant uses OpenRouter, which means you choose from Claude, GPT-4o, Llama, Gemini, and 200+ other models. Set an OpenRouter API key and pick a model in workspace settings. One integration, every model available.

How Bot Integration Works

The external bot integration works differently from the built-in assistant. Instead of being embedded in the CRM, the bot learns your CRM's API from a skill file: a structured document that teaches it how to interact with your data.

The Skill File

The skill file is generated from within FUNDesk Org and contains everything your bot needs to understand the CRM: what objects exist (Donors, Grantmakers, Gift Opportunities), what fields are available (engagement score, suggested ask, last gift date), and how to make API calls to read and write data.

The skill file includes:

Authentication details: How the bot authenticates with your CRM instance
API endpoint documentation: Every available operation with request/response formats
Schema information: Your workspace's objects, attributes, and valid values

The 19 API Endpoint Categories

The skill file documents these endpoint groups:

Category	Endpoints	Operations
Workspace	2	Get details, update settings
Workspace Members	2	List members, add member
Objects	3	List objects, get object, get attributes
Records	5	List, create, get, update, delete
Search	1	Full-text search across all records
Tasks	5	List, create, update, delete, get by record
Notes	6	List all, get by ID, get by record, create, update, delete
Lists	6	List all, get details, get entries, add entry, update entry, remove entry
Notifications	3	Get notifications, mark read, mark all read

Every endpoint includes the HTTP method, path, parameters, and expected request/response format. The bot reads this once, then makes standard HTTP requests with the Bearer token.

Environment Variables and Auth

Two environment variables power the integration:

FUNDESK_API_URL: the base URL of your CRM instance (e.g., https://crm.yournonprofit.org)
FUNDESK_API_KEY: a workspace-scoped API key (prefixed with fd_sk_)

API keys are generated in Settings > API Keys inside the CRM. Each key is scoped to a single workspace. All requests include Authorization: Bearer $FUNDESK_API_KEY.

The response envelope is consistent across all endpoints:

Success: { "data": ... }
Error: { "error": { "code": "...", "message": "..." } }

How the Bot Uses the Skill File

When you ask your AI bot to do something CRM-related, it recognizes the request matches the fundesk skill, reads the skill file, plans a sequence of API calls, executes them over HTTP, and formats the results.

For "add the donor from this morning's call to the CRM," the bot reads its call notes (from another skill or context), calls GET /api/v1/objects/merchants/attributes to learn the schema, calls POST /api/v1/objects/merchants/records to create the donor, and returns a summary.

The bot chains operations naturally because it has the full API documentation in context. Search for a donor, get the gift opportunity ID, create a note attached to it.

Setup: 2 Minutes

Go to Settings > FUNDesk Bot in the CRM
Select an API key (or create one in Settings > API Keys)
Download the generated SKILL.md
Place it in your bot's skill directory
Add the config to your bot configuration:

{
  "skills": {
    "fundesk": {
      "enabled": true,
      "env": {
        "FUNDESK_API_URL": "https://your-instance.com",
        "FUNDESK_API_KEY": "fd_sk_your_key_here"
      }
    }
  }
}

Restart your bot

The CRM generates the skill file with your instance URL pre-filled. The only manual step is pasting your API key into the config.

Why Three Systems Instead of One

Prospect Research: you need AI-powered donor and wealth screening without manual spreadsheet work. Kick off research, get an engagement score and signals.

Built-in assistant: you are already in the CRM and want to ask a quick question or create a record without navigating forms. "Show me all major-gift opportunities over $50k" is faster than clicking through filters.

Bot integration: you are not in the CRM. You are in your terminal or talking to your bot through whatever interface you use, and the bot handles CRM operations without you opening a browser.

Same underlying platform, different access patterns. Prospect Research builds donor profiles. The built-in assistant works directly within the CRM interface. The bot calls the REST API over HTTP from wherever you use it.

Challenges We Solved

Source variability. Donor data arrives in every shape: imported lists, event sign-ups, online gifts, legacy spreadsheets. FUNDesk Org's ingestion layer normalizes this variability automatically, so the AI gets clean, structured profiles regardless of the source.

AI accuracy and safety. AI models can sometimes misinterpret requests. FUNDesk Org handles this with a confirmation-before-write safety model, result capping to keep responses focused, and error recovery that lets the AI self-correct when something goes wrong.

Schema flexibility. Development offices have different data models. Some track giving circles as a separate object, others embed them in donor records. FUNDesk Org's AI automatically adapts to whatever schema you configure, no retraining required.

Skill file maintenance. The skill file is generated from your current schema. If you add custom objects or attributes, regenerate the file from Settings and your bot picks up the changes immediately.

Lessons Learned

Direct Data Access Over Search Indexes

CRM data is structured. Fundraisers ask "show me gift opportunities over $50k from major-gift prospects" or "create a task to follow up with Metro Arts." The AI queries your data directly rather than searching through document embeddings, which means more accurate results for structured fundraising data.

Schema-Aware AI Feels Smart

Users think the assistant is "learning" their data. In reality, the AI reads your current schema on every request. Add a custom object for grantmakers with funding-priority fields, and the assistant knows about it on the next message. No retraining needed.

The Read/Write Safety Split is Non-Negotiable

Read operations are safe. Worst case: wrong results, user ignores them. Write operations are dangerous. If the AI misinterprets "delete the gift opportunity" and deletes 50 records, trust is gone. Confirmation cards solve this cleanly. For development teams managing live gift opportunities worth tens of thousands of dollars, this safety net is critical.

Skill Files are a Powerful Pattern

Teaching a bot through a structured document (instead of requiring a custom integration) has advantages: it is human-readable, easy to update, and works with any bot that can read text. Simple format, powerful result.

Streaming Makes AI Feel Fast

Without streaming, users wait 3-5 seconds for a full response. With SSE streaming, tokens appear as they are generated. Users see progress. It feels fast even when total generation time is the same.

Domain-Specific AI Features Win

Prospect Research is not a generic data-lookup tool. It is specifically built for donor and wealth screening. That specificity makes it dramatically more useful than a general-purpose AI feature. Know your user, build for their exact workflow.

Try It

Prospect Research: open any donor record and click "Research." Results appear in seconds.

Built-in assistant: open the CRM, navigate to Chat, and start asking questions about your donors and gift opportunities.

Bot integration: go to Settings > FUNDesk Bot, generate your skill file, and connect your AI bot. Two minutes. For the full walkthrough, see How to Connect Your AI Bot to FUNDesk Org.

All three systems work independently. Use one, two, or all three. The CRM is the same underneath.

Start Free at FUNDesk Org | Live Demo | Documentation

Related: