Responsible Use of AI
CE Canvas includes AI features that help you plan engagement, draft documents, and analyse community feedback. This guide explains what each feature does, where human judgement is essential, and how your data is protected.
AI in CE Canvas is a support tool, not a substitute for professional judgement or community insight. Always review what it produces.
What AI does in CE Canvas
| Feature | What it does |
|---|---|
| EVA Chat (Ask EVA) | Answers questions about your project, helps draft canvas sections, refines plan content, and suggests stakeholder approaches — conversationally |
| Extract context / Discover with EVA | Reads your uploaded project materials (or your organisation’s public web presence) and drafts Project Context fields with sources attached |
| Draft with EVA — Canvas | Drafts Engagement Canvas sections (or the full canvas) from your context and materials |
| Draft with EVA — Documents | Drafts Engagement Plan and Outcomes Report sections, with confidence and source chips on each field |
| Suggest tasks | Proposes the operational tasks to run an engagement activity — reviewed and selected before anything is created |
| Results analysis | Analyses submitted results into themes, sentiment, and representative quotes |
All AI features are optional. Nothing is published or saved without your action.
How EVA stays grounded
EVA doesn’t answer from a general-purpose memory. Before it responds or drafts, it retrieves the relevant facts from your project — uploaded materials, context, canvas, plan, and results — and from the CE Canvas product documentation, and works only from what it finds. This is called grounding.
- It uses your evidence, not invented facts. EVA is instructed not to fabricate specific dates, figures, budgets, or commitments. When the source material doesn’t support an answer, it tells you it isn’t certain rather than guessing.
- Sources and confidence are shown. Drafts and answers carry source chips (what the content is based on) and a confidence signal, so you can check the basis for anything before you rely on it.
- It asks when it lacks context. If key information is missing, EVA flags the field as needing input instead of filling the gap with a plausible guess.
- Your data is used to answer, not to train. Grounding means your materials shape this response only — see “How your data is handled” below.
EVA runs on Anthropic’s Claude models (Claude Sonnet 5, with Claude Opus 4.8 for the most demanding reasoning such as synthesis and drafting), accessed through our AI provider.
Where human judgement is always required
AI can generate plausible-sounding content that is factually wrong, contextually inappropriate, or missing crucial local knowledge. There are specific areas in community engagement where human review is non-negotiable:
What is genuinely open to community influence EVA cannot know which decisions are fixed and which are open. The Negotiables / Non-Negotiables section of the Engagement Plan and the Decision Space section of the canvas must reflect your actual project constraints — not what sounds reasonable in a draft.
Stakeholder sensitivities and community history EVA has no knowledge of historical tensions, prior broken commitments, cultural protocols, or trust issues in your community. Sensitivities captured in Project Context and the People sections of the canvas must come from your own knowledge.
The engagement level you can honestly deliver Choosing Inform, Consult, Involve, Collaborate, or Empower is a commitment. EVA can suggest a level based on the project type, but only you can confirm whether your team, timeline, and organisational mandate can genuinely deliver it.
Closing the loop commitments The specific promises you make to communities about when and how they’ll hear what happened to their input must come from you. EVA can help structure the language — the commitment itself is human.
Any content shared publicly or with communities Review all AI-generated content before it goes outside your team. Check facts, verify context, and ensure the tone is appropriate for your community.
Practical review checklist
Before using any AI-generated content:
- Does this accurately reflect our actual project constraints and scope?
- Does it match what I know about this community and its history with our organisation?
- Are the stakeholder groups correct and complete for this specific project?
- Is the engagement level one we can genuinely deliver?
- Have I removed or corrected anything that sounds plausible but is actually wrong?
How your data is handled
- Your platform data is hosted in Australia. Your projects, materials, results, and account data live in our Australian-hosted database.
- AI requests are processed by our AI provider. To generate a response, the relevant prompt content is sent to our AI provider (which runs Anthropic’s Claude models). This processing may occur outside Australia. Only the content needed to answer the request is sent — not your whole database.
- Your project data is not used to train AI models. Prompt content is used to generate your response, not to train the underlying models.
- Requests are processed temporarily. Prompt content is used to produce a response and is not retained by the AI provider to build a long-term profile of your organisation.
- Data is encrypted in transit.
- AI features follow the same access controls as the rest of CE Canvas — team members only see data from projects they have access to.
Reporting a problem
If AI generates content that is inaccurate, biased, or inappropriate, contact us at support@cecanvas.com. Include the context or prompt you used, what was generated, and why it was a problem. Your feedback directly informs how we improve and safeguard AI features.
Our principles
CE Canvas’s approach to AI is guided by the Australian Government’s AI Ethics Principles:
- Human-centred — people remain in control; AI assists, it does not decide
- Fair and inclusive — we work to reduce bias and promote equitable engagement outcomes
- Private and secure — data is handled responsibly and kept safe
- Transparent — you always know when and how AI is being used
- Accountable — we take responsibility for our AI systems and welcome feedback