About Truvyo

Trust is a function of evidence.

Truvyo is an evidence-grounded AI support engine. Two agents — Customer Agent and Technical Companion — answer from a verified, SKU-specific knowledge base and cite every claim. No hallucination, no extract endpoint, no sales motion.

What Truvyo is

A small, self-contained AI support platform built on Cloudflare. The product surface fits on a single architecture diagram.

ComponentWhat it does
Customer AgentEnd-user-facing. Claude Haiku 4.5. Plain-language symptom triage. Always cites sources.
Technical CompanionInstaller/operator-facing. Claude Sonnet 4.6. Multi-symptom diagnostics, install sequencing, escalation paths.
Hybrid retrievalVectorize (semantic) + D1 FTS5 (BM25) + Reciprocal Rank Fusion. Top-5 articles per turn.
Shared Knowledge LibraryCurated manufacturer and vendor documentation. Compounds across every tenant.
Tenant overlayPer-tenant private KB. Internal SOPs, brand voice, policy. Never extractable.
Cross-check auditEvery published article passed an automated audit against authoritative sources before serving.
Disposition billingEvery activated chat creates a disposition row; only the ones the agent resolved are billable.
Auto-update pipelineQuarterly ingest of new vendor docs + community evidence + audit gate. Daily aggregation of feedback and gaps.

The principles

Five rules the engine is built around. Everything else falls out of them.

Citations over confidence

If a claim cannot be grounded in an audited source, the agent does not make the claim. There is no "confident guess" mode and no fallback to model parametric memory. When retrieval comes up empty, the agent says so and escalates.

The model is the easy part

Choice of LLM is a config line. The hard work is the governance — retrieval filters that only surface published articles, an audit pipeline that benches unverified claims, disposition logic that ensures billing only fires when the work was done. Engineering time goes there.

Self-serve over sales

Documentation is the salesperson. Pricing is public. Architecture is public. Sign-up is one form. If the trial doesn't convert you, no demo would have.

Write-only data sovereignty

Tenant content goes in. It does not come out as a file. No bulk export endpoint exists; no admin route returns article bodies; no UI exposes full content. Verified in code, not just terms of service.

Outcomes, not messages sent

If Truvyo couldn't ground the answer and the conversation escalated to a human, Truvyo didn't do the work — and doesn't charge for it. Industry-standard contact-center terminology: dispositions. Billable dispositions are the ones the agent resolved.

How the company operates

HeadcountSmall, engineering-heavy team.
Sales motionNone. No outbound, no SDRs, no "schedule a demo" between buyer and product.
Pricing modelPublic, transparent, three components: basic platform fee + pooled dispositions + $45/seat. Full pricing.
Trial7 days, no credit card, self-serve via the website.
DeploymentCloudflare Workers + D1 + Vectorize. Multi-region; data resides in the tenant's selected region.
LLM providerAnthropic (Claude Haiku 4.5 and Sonnet 4.6). Provider isolated to a single module; swap is a one-line change.
Data policyNo training on tenant data. SHA-256-hashed API keys. Per-tenant row isolation. No cross-tenant queries possible.
SupportEmail-first. Docs are the first line; support@truvyo.ai when docs don't cover it.

Roadmap themes

In order of priority. The order is intentional — we ship in the order things create the most value.

  1. Domain-specific Shared Libraries. Next ones in progress: HVAC, solar, home medical devices. Each unlocks an entire industry vertical at deployment.
  2. Additional platform adapters. Zoom Contact Center and Zendesk shipped. Intercom and Drift in Q3. Salesforce Service Cloud + HubSpot after.
  3. Voice channel support. Text-side agents already work. Voice requires STT in front and TTS behind. Integration project, not a model project.
  4. Browser admin console. API-first today. Web console for non-developer operators on the way.
  5. Tighter cold-path research loop. Today the pipeline processes gaps quarterly. Target: weekly. Unanswerable questions become answerable within days.

Compliance + security posture

Contact

ForEmail
Generalhello@truvyo.ai
Engineering questionseng@truvyo.ai
Support & billingsupport@truvyo.ai
Security disclosuressecurity@truvyo.ai
Presspress@truvyo.ai
Careerscareers@truvyo.ai

Ready to send your first cited answer?

7 days free. No card. No sales call. 30 seconds to a trial API key.

Start free