Fixed quote after a free call

An AI chatbot for nonprofits that answers supporters and protects people

We build an AI assistant for your website and shared inbox that answers routine supporter questions from your own approved answers, such as how to change a regular gift, claim Gift Aid, sign up for an event or volunteer, sorts incoming email and drafts replies for staff to approve. Anything about safeguarding, complaints, hardship or a person in crisis goes straight to a person with your signposting. It tells people it is automated. Projects typically cost $2,500 to $7,500 and take five to eight weeks.

The problem

Why charity inboxes need a careful assistant

A charity inbox mixes routine questions with messages that matter enormously: a regular donor changing their gift, a fundraiser asking for a t-shirt, a beneficiary asking for help, a complaint, a safeguarding concern. Small teams read them in arrival order.

An assistant can take the routine load only if it is narrow and safe: it answers from approved wording, never offers advice, and passes anything sensitive to a person immediately with your signposting.

What we build

What our AI chatbot for nonprofits includes

Approved answer library

Giving, Gift Aid, events, volunteering, contact and policy answers written and approved by your team.

Website assistant

A chat on your site that answers from the library and links to the source page.

Inbox sorting

Incoming email sorted into giving, events, volunteering, services, complaints and sensitive, using your categories.

Draft replies

Draft answers to routine emails for staff to approve and send.

Sensitive routing

Safeguarding, crisis, hardship and complaint messages routed to named staff at once, with your signposting, never answered by AI.

Clear AI disclosure

The assistant says it is automated and offers a person at any time.

Who does what

Automation does the chasing, people make the calls.

Every step is marked: what runs on its own, what a member of staff reviews and what stays with a person who decides.
  1. 01 Automated

    Message arrives

    A supporter asks on the website or emails the shared inbox.

  2. 02 Automated

    Sorted and answered

    Routine questions are answered or drafted from approved answers.

  3. 03 Automated

    Sensitive routed

    Safeguarding, crisis and complaint messages go straight to named staff.

  4. 04 Staff review

    Staff approve

    Staff approve drafts and reply to anything the assistant could not answer.

  5. 05 Charity lead or trustees decide

    Safeguarding and complaints

    Every safeguarding concern and complaint is handled by authorised people, never software.

How it behaves

How the supporter assistant behaves

What each person sees and what runs in the background, including what happens when something goes wrong.

What supporters see

  • A note that the assistant is automated
  • Clear answers with links to your pages
  • A person straight away for anything sensitive

What staff see

  • A sorted inbox with drafts to approve
  • Sensitive messages flagged to named staff at once
  • A weekly list of unanswered questions

What the automation does

  • Answers only from approved wording
  • Routes sensitive categories to people
  • Logs every conversation for review

Edge cases and fallbacks

Message suggests someone is at risk
No AI reply; your crisis signposting and an immediate alert to named staff.
Question not in the library
The assistant says it does not know and offers a person.
Supporter asks to stop all contact
Logged as an opt-out request for staff to apply across systems.
AI provider outage
The chat falls back to a contact form and the inbox to normal order.

Architecture

An AI supporter assistant for a charity at a glance.

The setup we usually start from. We adapt it to the phone system and practice software you already use.
Supporter Web chat, email Assistant service n8n or Laravel Approved answers Charity-written Language model Claude, Gemini, GPT Answer or draft For staff to send Named staff Sensitive messages Review log Weekly gaps
  • Input
  • Logic and services
  • Data
  • AI step
  • Output
  • People

How it flows

  1. 1 A supporter asks on the website or emails, and is told the assistant is automated.
  2. 2 The service retrieves approved answers and passes them, with fixed rules, to the model.
  3. 3 Routine questions get an answer or a draft for staff; sensitive messages go to named staff at once.
  4. 4 Every conversation is logged, with a weekly list of questions to add to the library.

Project planner

How the project runs, phase by phase.

Typical durations for a first version. Your proposal lists the exact phases, dates and what you sign off at each step.

AI supporter inbox & website assistant project plan

Typical time to launch: about 6 weeks, then support

  1. 01

    Discovery

    About 1 week

    Real inbox and chat questions, sensitive categories, signposting and what the assistant may answer.

  2. 02

    Answer library

    About 1 week

    Write and approve answers, signposting and routing rules with your team.

  3. 03

    Build

    About 2 weeks

    Website chat, inbox sorting, drafts, sensitive routing, logging and admin view.

  4. 04

    Test

    1 to 2 weeks

    Real, tricky and sensitive messages tested; safeguarding lead signs off.

  5. 05

    Launch

    2 to 3 days

    Start with inbox drafts only, then switch on website answers.

  6. 06

    Support

    Ongoing

    Weekly transcript review at first, then monthly library updates.

What it runs on

Real products only, connected through the access each vendor provides. See all integrations

Claude, Gemini or OpenAI models n8n AI Agent node or Laravel Website chat widget Microsoft 365 or Gmail shared inbox Your charity CRM Teams or Slack for sensitive alerts

Cost estimate

What it costs, line by line.

Estimates to plan with. Your fixed quote follows a free call, once we have seen your systems and volumes.
  • Discovery and answer library

    Real questions, sensitive categories and approved answers.

    $500 – $1,200

  • Build

    Assistant service, chat, inbox sorting, drafts and routing.

    $1,200 – $3,900

  • Integrations

    Inbox, CRM and alerts.

    $300 – $1,000

  • Testing and evaluation set

    Real, tricky and sensitive messages tested.

    $300 – $1,000

  • Launch and training

    Phased launch and transcript review.

    $200 – $400

  • Total project estimate

    $2,500 – $7,500

Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. Model usage and hosting are billed to your accounts directly; check for nonprofit pricing from your providers.

Monthly running costs you pay directly

Estimates from the vendors' published pricing, checked November 2026. Billed to you by each vendor, never marked up.

  • AI model usage: Billed by the provider per use; usually a small monthly amount at charity volumes.
  • Hosting: n8n Cloud from about €20 a month, or your own server.

What pushes cost up

  • Systems without an API, or with integration access that must be requested from the vendor
  • Writing data back into your core system rather than only reading from it
  • Several locations, brands or very different processes to support
  • Custom apps, dashboards or a voice line on top of the workflows

What keeps cost down

  • One location and one clear process to start with
  • Cloud software with a documented API
  • Using tools you already pay for instead of adding new ones
  • Approved wording and sample data ready at the start
Get a fixed quote

Privacy and consent

Rules we design for, with the sources.

General information to plan with, not legal advice. Your counsel or data protection adviser confirms what applies to your practice.

EU: tell people they are talking to AI

Article 50 of the EU AI Act requires AI systems that interact with people to inform them, from 2 August 2026. We add the disclosure everywhere.

Source: artificialintelligenceact.eu

EU and UK: sensitive messages are special category data

Messages about health, beliefs or personal crises are special category data under GDPR Article 9, so the assistant collects as little as possible and routes them to people.

Source: gdpr-info.eu

EU and UK: AI provider under contract

The AI provider and host work under processor contracts under GDPR Article 28, and supporter data is not used beyond the task.

Source: gdpr-info.eu

How we deliver

Agile delivery, in 1 to 2 week sprints.

We deliver in short Agile sprints using Scrum, so you see working software every one or two weeks instead of waiting for a big reveal at the end.

Every sprint

  1. 1 Sprint planning. At the start of each sprint we agree which backlog items we will finish, each with written acceptance criteria you can check.
  2. 2 Daily stand-up. A short internal check-in on progress and blockers. You get a written update in your Slack or Teams channel, not another meeting.
  3. 3 Sprint review and demo. At the end of each sprint we demo what was built on test data or in a shadow run, and you accept it or ask for changes.
  4. 4 Retrospective. The team looks at what went well and what to change in the next sprint, and we share anything that affects you.

How scope stays under control

Product backlog
Every feature, fix and question in one prioritised list you can see at any time.
Acceptance criteria
Plain-language conditions for "done" on each item, agreed before work starts.
Change requests
New ideas go into the backlog with an estimate. Nothing changes scope or price without your written approval.
User acceptance testing (UAT)
Before launch your team tests the real workflow against the acceptance criteria and signs off.

Tools we use

Jira, ClickUp or Trello for the backlogSlack or Microsoft Teams for updatesGitHub for code and version historyLoom or a live call for demos

Project manager / Scrum master

Runs the sprints, keeps the backlog and timeline honest, and is your single point of contact.

Business analyst

Maps how the work runs today, writes the workflow specification and acceptance criteria with your team.

Automation engineer

Builds the n8n workflows, integrations, AI steps and error handling.

Backend developer

Writes custom code where a no-code step is not enough: APIs, data sync, secure storage.

Frontend / mobile developer

Builds forms, booking pages, dashboards, web apps or Android apps when the project needs them.

QA engineer

Tests every workflow against the acceptance criteria, including edge cases and failure paths.

DevOps engineer

Sets up hosting, access, backups, monitoring and alerts, and the deployment pipeline.

Who does what at each phase

Free call
Project manager, business analyst
Understand the problem, check it is worth automating and outline a rough range.
Discovery
Business analyst, automation engineer
Map the current process, systems and data, and agree success measures.
Design
Business analyst, automation engineer, backend developer
Write the workflow specification, data flows, compliance notes and backlog with acceptance criteria.
Sprints
Automation engineer, developers, QA
Build, test and demo in 1 to 2 week sprints; you accept or adjust after each demo.
UAT and launch
QA, DevOps, project manager
Your team tests and signs off, we switch on, monitor closely and train the team.
Support
Automation engineer, DevOps
Stabilisation window, then optional monthly care with monitoring and changes.

A point of contact

One person who can answer questions and approve decisions, with about an hour a week during the project.

Access

Admin or API access to the systems involved, created as separate accounts with the least access needed.

Sample data

Real but non-sensitive records (or de-identified ones) so we can design and test against reality.

Approved wording

Message templates, policies and consent wording (for SMS, your opt-in and opt-out text) reviewed by you.

Vendor agreements

Signed agreements with the software vendors that will handle personal data, such as a BAA or processor contract.

Time for testing

A few hours from the people who will use the system, for the demos and user acceptance testing.

Working system

Workflows, integrations and any apps running in your accounts, under your keys.

Documentation

Workflow specification, data-flow map, run book and exported workflow files.

Training

A walkthrough for the team and a short recorded video for new starters.

Handover

All access, credentials and code handed over; you can keep us or take it in-house.

Stabilisation window

Fixes for anything that does not meet the agreed acceptance criteria after launch.

Support options after launch

  • No plan

    You run it yourselves after the stabilisation window and contact us when you need a change.

  • Monthly care

    Monitoring, error alerts, small changes and updates each month, with an agreed response time.

  • Priority care

    Faster response times for business-critical workflows and a monthly review call.

How a project moves through our team

Free call PM and analyst Discovery Process and data Design Spec and backlog Sprints Build, test, demo Your review Accept or adjust UAT and launch Sign-off, go live Support Monitor and improve
  • Input
  • Logic and services
  • People
  • Output
  • Data

How it flows

  1. 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
  2. 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
  3. 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
  4. 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.

FAQ

AI chatbot for nonprofits questions questions, answered.

It can be, if it is narrow. Ours answers only from approved wording, never gives advice, and routes safeguarding, crisis, hardship and complaint messages straight to named staff with your signposting.

Yes. It says so at the start and offers a person at any time. In the EU that is a legal requirement under the AI Act from 2 August 2026, and we treat it as good practice everywhere.

It explains how and links to the right form or contact. Changes to gifts and bank details are handled by staff in the CRM.

We start with drafts that staff approve. Once the team is confident, simple acknowledgements can be sent automatically; sensitive categories never are.

Model usage is billed per use and is usually a small monthly amount at charity volumes. We estimate it from your inbox and chat volume before launch.

Inbox response time, share of routine questions answered or drafted, sensitive messages routed and time to a staff response.

Free 20-minute call

Want this for your charity?

Book a free 20-minute call. We will look at how the work runs today, tell you honestly whether it is worth building and give you a fixed quote if it is.

Book a free 20-minute call