All editions · Parish Edition

Your Community, Your AI — CC BY 4.0

What's Actually Running in Village Today

Early Days

This article is about what exists today — not what we plan to build, not what we hope to achieve, but what is running right now in production. Where something is planned but not yet live, we say so plainly. (Any unfamiliar term is defined in plain language in the glossary.)

Village AI has been running in production since 2025. It is a young system: some parts work well, some parts are still rough, and this article marks both. A community that adopts a platform on clear information makes a steadier partner than one that adopts on marketing.

What Village AI Can Do for Your Parish Today

Answer questions about your community's content. When a parishioner asks "When is the next vestry meeting?" or "What did the rector say about the building fund?", Village AI searches your community's actual records — parish bulletins, stories, event descriptions, vestry documents — and provides an answer grounded in that content. It does not guess or infer from general knowledge. If it cannot find the answer in your records, it says so.

Help with drafting. Village AI can help draft parish bulletins, event announcements, and correspondence. Because it has been trained on your community's previous content, its drafts reflect your parish's tone and style — not a generic corporate template. A moderator reviews and edits every draft before it reaches the community.

Summarise long documents. A lengthy vestry report or a series of parish announcements can be summarised into key points. This is useful for parishioners who want to stay informed but do not have time to read everything.

Translate between languages. Village supports five languages — English, German, French, Dutch, and Te Reo Māori. The AI assists with translation of community content, though human review is recommended for important communications.

Triage member feedback. When a parishioner submits feedback through the platform — a question, a suggestion, a report of something not working — the AI classifies it, investigates where possible, and notifies the member when it has been addressed. This is designed to happen without the moderator having to sort every piece of feedback by hand.

Answer questions through the Help assistant. Every Village has a built-in help assistant. A parishioner — especially a newcomer — can ask in plain language ("How do I find the vestry minutes?", "How do I add an event to the calendar?") and get an immediate answer grounded in your parish's records and the platform's own guidance, without anyone having to write a manual. The same assistant answers general questions on your shopfront before a visitor has even joined.

Prepare worship talks and reflections. For Episcopal and Anglican parishes, Village includes a dedicated Talk Preparation tool. It helps a worship leader or ordained minister move from life reflections and the week's lectionary readings to a structured talk — section by section, grounded in Scripture, in the parish's own voice. It does not write the talk for you; it helps you build it, and the keyboard stays in your hands. The drafts you keep stay within your parish.

Organise photographs and read documents. When parishioners upload photos to the gallery, Village's vision model suggests tags and descriptions so images become findable later — Easter 2025, the confirmation class, the new bell — without one volunteer captioning every picture by hand. The same capability reads scanned documents and receipts, turning a photographed page into searchable text. This runs on our own servers; your photographs and documents are never sent to a third party.

Where Village Acts, Not Just Answers

Articles 1 and 2 made a distinction worth holding onto: a chatbot answers, an agent acts. So it is fair to ask — does Village AI only answer, or does it act too?

It acts, in carefully bounded ways. The clearest example today is feedback resolution. When a parishioner marks an answer as unhelpful, Village does not simply log a complaint for a human to wade through later. It investigates the correct answer against your community's records, and where it can resolve a routine, low-stakes case on solid evidence, it does so on its own — improving the system's knowledge so the next parishioner who asks gets a better answer. This is genuine agentic behaviour: the AI takes a multi-step action, not just produces a sentence.

But notice the boundaries around it, because they are the whole point. The agent acts only inside your community's data. It acts only on routine, reversible matters. And the moment it detects a systemic problem — a pattern of related failures that suggests something deeper is wrong — it stops acting and escalates to a human, because that is no longer a routine fix but a judgment call. The design target is that the great majority of ordinary feedback is handled automatically, while anything consequential lands on a person's desk.

This is the practical shape of the principle from Article 3: an agent you control acts where action is safe and reversible, and steps back where it is not. That is the opposite of an outside agent that acts on everything with fewer chances for you to intervene.

What the AI Does Not Do

It does not make decisions for your community. When a question involves values, ethics, or judgment, the AI stops and routes it to a human. Your moderator, your rector, your vestry — the people your community trusts with these decisions.

It does not take consequential or irreversible actions on its own. As the previous section described, where Village AI acts, it acts only on routine, reversible matters inside your community's data. It does not send communications in your name, commit your parish to anything, or make changes it cannot walk back, without a human in the loop. The keys stay with your community.

It does not access content it was not given. Private content stays private. Content from other communities stays with those communities. The AI cannot reach across boundaries, because those boundaries are structural, not policy-based.

It does not operate without oversight. Every AI response passes through the independent verification layers described in the previous article. No response reaches a parishioner without being checked against your community's actual records.

It does not pretend to know things it does not know. When the AI's confidence is low, it says so. Every response carries a confidence indicator. Members can see at a glance whether the AI is drawing on solid records or venturing into less certain territory.

How Bias Is Addressed: The Vocabulary System

One of the subtlest forms of bias in AI is linguistic. When a system trained on corporate data calls your parishioners "users" and your parish bulletins "posts," it is imposing a worldview — one where communities are consumer platforms and communication is content marketing.

Village addresses this through a vocabulary system that adapts the entire platform to your community type.

When you set up a Village for an Episcopal parish, the system does not show you generic labels. It shows you the language of parish life:

• Parishioners, not "users" or "members"
• Parish bulletins, not "posts" or "updates"
• Vestry governance, not "admin settings"
• Parish stories, not "content"
• The parish, not "the community workspace"

This is not cosmetic. The vocabulary shapes how the AI understands and responds to your community. When the AI has been trained with the term "parishioner" rather than "user," it processes questions and generates responses within a parish frame of reference. It understands that "How do I reach out to new parishioners?" is a different question from "How do I acquire new users?" — even though a generic AI system would treat them identically.

Each community type has its own vocabulary. A sports club sees "club members" and "season fixtures." A family sees "family members" and "family stories." The platform is the same, but the language — and therefore the AI's understanding — is specific to your community.

How the AI Learns and Improves

Village AI is not static. It improves over time through three mechanisms:

Scheduled retraining. The AI is retrained on your community's latest content on a regular schedule. New parish bulletins, new stories, new event descriptions — they enter the AI's knowledge base so it stays current with your community's life.

Moderator feedback. When a moderator flags an AI response as inaccurate or unhelpful, that correction feeds back into the system. Over time, the AI learns what works for your community and what does not. This is not generic improvement — it is improvement specific to your parish.

Guardian-agent learning. An adaptive layer adjusts verification thresholds based on patterns of accuracy and error. If the AI consistently gets a certain type of question right, the guardian eases verification intensity for that type. If it consistently struggles with another type, the guardian tightens scrutiny. The system becomes more efficient without becoming less careful.

What Is Still a Work in Progress

A higher-capability tier. Village runs a focused open model, fine-tuned per community type, so a parish, a club, and a family each get an AI tuned to their context — for a parish, one shaped around Episcopal and Anglican life. The architecture reserves a more capable tier for harder questions; it is defined but not yet in service, so today every question is answered by the community-tuned model.

Individual personalisation — where the AI learns individual member preferences — is planned but not yet built. For now, the AI knows your parish as a community, not your individual parishioners as individuals (unless they interact with it directly).

The moderator accreditation path — structured training for parish members who take on the moderator role — is designed but being rolled out progressively. Founding communities have direct access to the founder for support.

We mention these plainly because you should know what you are adopting. This is a young platform, built by a small team and used by a small number of communities. It is functional, it is improving, and it is clear about where it stands.

AI Is Only Part of What Is Live

It would be easy to read an article about Village AI and conclude that AI is the product. It is not. The AI sits inside a full parish platform, and that platform is running in production today as well — not on a roadmap. In one private space, governed by rules your parish sets, you already have:

• Parish news and the bulletin — announcements and your weekly or monthly bulletin, kept in a permanent, searchable record rather than scattered across a Facebook feed and old emails.
• Parish chat and direct messages — encrypted private and group messaging on your own infrastructure, including voice messages, so the prayer chain or the vestry can talk without the contents being harvested.
• Video calling — face-to-face conversations with no Zoom, no Teams, and no external accounts to create.
• Calendar and events — a single source of truth for services, meetings, and activities, with the ability to indicate attendance.
• Gallery — a shared, curated visual history of parish life.
• Records — vestry minutes, the parish constitution, the safeguarding policy, financial statements, and formation materials, organised by category and findable.
• Polls — a clear, fair way for the parish to gather opinion and decide.
• Directory, ministries, and mutual aid — the parish knowing itself; space for the choir, flower guild, or outreach committee; and a way to coordinate practical care like transport and visiting.
• Shopfront and federation — a chosen window onto your parish for newcomers, and the ability to connect with a sister parish or deanery while each keeps its own data separate.

None of these require AI to work — the calendar, the chat, and the gallery all function on their own. What the AI adds is connective intelligence across them. The next and final article in this series, The Village Beyond AI, walks through each in plain terms. The point here is simply that when we say "what's live today," we mean the whole platform, not only the AI layer.

What This Means for Your Parish

If your parish is considering Village, here is what you are choosing:

Village is a platform where AI knows your community's actual content — your bulletins, your stories, your events — not the internet's idea of what a parish might be. Every AI response is mathematically verified against your records by independent watchers. The vocabulary reflects your tradition: parishioners, not users; vestry governance, not admin settings.

Your data stays within your community's boundary, is not used to train external AI systems, and can be exported or deleted at any time. The system is transparent about its limitations, improves from your moderators' corrections, and stops to ask a human when a question requires judgment rather than information.

You would also be joining as a founding community — one of a small number of parishes, clubs, families, and organisations shaping the platform in its early life.

If that interests you, the current status of the founding-community programme is on the founding-community page.

Want to use AI tools like these well, and safely? Our free courses — Working with Claude and Agents at Work — teach the practical skills, from getting trustworthy answers to deciding what to hand an agent. For the full technical architecture behind Village AI, see Village AI — Agentic Governance.