AI at WeInspect — transparency
Version v1.1 — effective 2026-XX-XX
This page is a transparency commitment, not a standard legal document. It describes in plain language how AI works in WeInspect, with what data, with whom, and why you can trust us — or hold us accountable if we slip.
WeInspect AI in 30 seconds
┌─ How WeInspect AI works ───────────────────────────────┐
│ │
│ Models used │
│ ─────────── │
│ ✓ Anthropic Claude Sonnet 4.6 (generation, vision) │
│ ✓ OpenAI Whisper (audio transcription) │
│ ✓ OpenAI text-embedding-3-small (RAG public sources) │
│ ✗ No other provider, never without telling you │
│ │
│ Your data vs AI │
│ ─────────────── │
│ ✗ No training on your data (ZDR contract) │
│ ✗ Not shared with other users │
│ ✓ Encrypted transit, 0-day retention provider-side │
│ │
│ What AI does for you │
│ ──────────────────── │
│ ✓ Finding suggestions from voice + photos │
│ ✓ FR-QC audio transcription │
│ ✓ Photo classification by section │
│ ✓ On-demand targeted rewriting │
│ ⚠ BNQ + Civil Code chatbot (coming, post-launch) │
│ │
│ What AI does NOT do │
│ ─────────────────── │
│ ✗ Sign your report (it's your name, your license) │
│ ✗ Decide a property's compliance │
│ ✗ Bill you behind your back (cost shown before action)│
│ ✗ Replace your professional expertise │
│ │
│ Your powers │
│ ────────── │
│ ✓ Disable everything in one click │
│ ✓ Credits do not expire │
│ ✓ Costs capped by your credits │
│ ✓ "Report error" button on every AI output │
│ │
└────────────────────────────────────────────────────────┘Plain language: AI saves you time, doesn't replace your judgment. It suggests, you decide. Your data doesn't train anyone. And if you want to turn it off, two clicks and WeInspect works without AI.
1. What AI does for you
| Feature | Model used | When | Data sent | |---|---|---|---| | Audio transcription | OpenAI whisper-1 (online) or whisper-tiny local Expo (offline) | When you dictate a note | Dictated audio file | | Finding generation | Anthropic Claude Sonnet 4.6 | On demand, when you finish a capture | Transcription + photos + observation metadata | | Photo classification | Claude Sonnet 4.6 (vision) | On demand, single or batch photo | Photo + inspection context (section, building type) | | Targeted rewriting | Claude Sonnet 4.6 | When you select text and provide an instruction | Selected text + your instruction | | BNQ + Civil Code chatbot (coming) | Claude Sonnet 4.6 + RAG on pgvector | When you ask a question | Your question + relevant BNQ/Civil Code excerpts | | Level 2 AI review | Claude Sonnet 4.6 | Before report finalization, on demand | Report findings + terminology reference | | RAG embeddings | OpenAI text-embedding-3-small | At indexing (server-side, not in response to you) | BNQ + Civil Code + jurisprudence text |
2. What AI does not do
- AI does not sign your reports. It's your name, your license, your civil liability.
- AI does not decide a property's compliance. It suggests according to BNQ patterns; you judge.
- AI does not redistribute your data. None of your findings, photos, or transcriptions feed another user or third-party training model.
- AI does not bill you behind your back. Each action has a credit cost displayed before execution. You can disable everything.
3. Where your content transits
3.1 Anthropic (Claude Sonnet 4.6)
- Hosting: United States
- API region used:
us-east-1orus-west-2based on availability - Encryption: TLS 1.3 in transit + AES-256 at rest (ephemeral API transit, no long-term storage on Anthropic side)
- Contractual "no training" commitment: Anthropic Zero Data Retention enabled on our API account → payloads are not retained beyond the strict response generation time, and not used to train Claude.
- Policy: <https://www.anthropic.com/legal/privacy>
3.2 OpenAI (Whisper + embeddings)
- Hosting: United States
- Whisper API: we use
whisper-1with 0-day retention (API parameter) - Embeddings: applied on public content (BNQ, Civil Code) only, not on your inspections
- No training on API data: <https://openai.com/policies/api-data-usage-policies>
3.3 No other LLMs, no hidden providers
WeInspect uses only Anthropic and OpenAI for AI. No Google Gemini, no AWS Bedrock, no hidden routing to other providers. If we were to add a provider, we would tell you in advance and ask for new explicit consent.
4. Your consents
Before first use of an AI feature, we ask for explicit and separate consent for:
| Consent | Covers | |---|---| | ai_processing | All generic AI processing (generation, classification, rewriting) | | audio_recording | Recording and transcribing your voice |
You can withdraw these consents at any time from /settings/privacy/ai. Effect:
- Immediate disabling of AI features
- Deletion of raw audio within 7 days
- Retention of already-generated findings (you can delete them manually)
5. AI costs and credits
5.1 Caps per plan
| Plan | Monthly AI credits | |---|---| | Pay-as-you-go | 10 basic text messages included | | Solo Unlimited | 200 AI credits / month | | Solo Annual | 200 AI credits / month | | Team | Shared pool by number of seats | | Student | 50 credits / month |
5.2 Cost per action (indicative, adjusted to provider pricing)
| Action | Credits | |---|---| | Transcription 1 min audio | 1 | | Finding generation from capture | 5 | | Photo classification | 1 | | Short rewriting (≤500 words) | 2 | | Chatbot question | 3 | | Level 2 review (full report) | 10 |
Exact values are visible at /settings/credits and locked at the moment of action.
5.3 No expiration
Your included credits do not expire as long as your account is active (Québec Consumer Protection Act). Credits purchased à la carte: no expiration either.
5.4 Cost safeguards
If an AI provider raises prices mid-year, you are not retroactively impacted. We adjust credit costs only from the next month, with 30 days' notice.
6. Quality, hallucinations, verification
6.1 Recognizing a hallucination
LLMs may invent a BNQ reference, misremember a Civil Code article, or infer a defect from an ambiguous photo. Always verify:
- Generated BNQ references (the live BNQ gauge S06 helps)
- Civil Code citations (the chatbot displays the source text of the cited article — check it exists)
- Photo classifications (a glance at the photo + your context)
6.2 Our validation setup
- Evaluation harness: before each model or prompt update, we test on a golden dataset of 100+ real inspector cases (validated by design partners). No silent regression.
- Strict anti-invention prompt: our prompts contain the explicit instruction "never invent a BNQ reference; if uncertain, answer 'not found'".
- Sourced citations: for chatbot and AI review, each statement is accompanied by the source (BNQ section X, Civil Code art. Y).
6.3 If you spot an error
"Report" button on every AI output → the response + your feedback enter our improvement loop (anonymized, aggregated). You can also write to support@ouiinspect.ca.
7. Automated decisions and profiling
WeInspect makes no automated decision about you with legal or similar effect (Law 25 sec. 12.1). All important decisions (report publication, account suspension, refund refusal) are made by humans.
Anti-fraud risk scoring (Stripe Radar) is applied to payments. You can contest any decision by writing to support@ouiinspect.ca.
8. How to disable AI completely
From /settings/privacy/ai, toggle "Disable all AI features". Effect:
- Finding generation pipeline: disabled (manual drafting only)
- Transcription: disabled (keyboard input only)
- Photo classification: disabled (manual tagging)
- Rewriting: disabled
- Chatbot: hidden from interface
- Level 2 review: disabled
WeInspect remains fully usable: capture, manual drafting, findings library, heuristic BNQ gauge, report, client portal, multi-seat, billing — everything works without AI.
9. Evolution
If we add a new AI feature, new model, or new provider, we will notify you and ask for new explicit consent. No "silent rollout" in production. This page is updated on every substantial change.
10. Questions, complaints, suggestions
- DPO (privacy / Law 25 questions): dpo@ouiinspect.ca
- Support (AI quality, bug report): support@ouiinspect.ca
- CAI (independent recourse): <https://www.cai.gouv.qc.ca>
Last updated: 2026-XX-XX