Skip to content
OnticBeta

Meet Goober

A governance-grounded conversational agent built on Llama 3 8B.

Goober answers governance questions using your risk profile and 48 verified oracle sources covering GDPR, HIPAA, SOX, PCI DSS, the EU AI Act, and more. It doesn’t guess. It retrieves, cites, and stays in its lane.

Profile-grounded, not prompt-stuffed

Goober isn’t a generic chatbot with a compliance system prompt. It loads your governance profile — industry, segment, risk category, EAD scores — from the 4-question wizard you already completed. Every answer is scoped to your context before the model sees a single token.

On each message, Goober runs a hybrid vector + full-text search across 48 oracle documents (366 embedded chunks) to retrieve the specific regulatory or framework guidance relevant to your question. What it finds shapes the answer. What it doesn’t find, it says so.

Beyond the initial retrieval pass, Goober calls tools mid-conversation: search_oracles for additional context, lookup_framework_section for targeted queries, check_boundary for professional referral detection, check_claim for claim verification, and compare_frameworks for side-by-side framework comparison. These tools run server-side within the trust boundary — the model orchestrates, the oracles provide truth.

Your governance profile

Industry, segment, deployment tier, EAD risk axes, and Ontic-needed signal — all injected into the system prompt so Goober never asks you to repeat yourself.

48 oracle sources

Regulatory frameworks (GDPR, HIPAA, SOX, EU AI Act), industry standards (ISO 27001, PCI DSS, SOC 2), and 29 industry-specific oracles — all embedded with pgvector and retrieved by relevance.

Boundary awareness

18 boundary topics (legal advice, medical practice, tax guidance, etc.) are detected at retrieval time. When Goober hits a boundary, it redirects to a qualified professional instead of guessing.

Mid-conversation tool calling

Five tools — search_oracles, lookup_framework_section, check_boundary, check_claim, and compare_frameworks — let Goober retrieve additional oracle data during a conversation, not just on the initial grounding pass.

The model is the brain. The oracles are the library. Your profile is the scope. Together, the answer is grounded.

How it works

Four questions → governance profile → grounded chat.

1

Take the wizard

Four questions about your AI deployment. Takes about 90 seconds. Produces a governance profile with industry, segment, risk category, and EAD scores.

2

Chat with Goober

Your profile is loaded automatically. Ask about frameworks, compliance requirements, implementation costs, or whether you need Ontic at all.

3

Toggle oracle grounding

Turn oracle grounding on to get answers backed by verified sources with provenance badges. Turn it off for general conversation. You control the tradeoff.

4

See the sources

Every grounded answer shows which oracles were consulted, what tier they are, and how relevant the match was. No black boxes.

What Goober knows

48 oracle documents. 366 embedded chunks. 19 frameworks, 29 industries.

Regulatory frameworks

GDPRHIPAASOXCCPA/CPRAEU AI ActDOJ ECCP

Industry standards

ISO 27001ISO 42001PCI DSSSOC 2NIST CSF 2.0NIST AI RMF

Industry oracles

Financial servicesHealthcareSoftwareLegalEducationGovernmentEnergyCybersecurityand 21 more

Boundaries

Legal adviceMedical practiceTax guidanceInvestment adviceMental healthEmployment lawand 12 more

Browse the full Oracle Library →

Why 8B

Not a limitation. A design decision.

Goober is fine-tuned on Llama 3 8B Instruct. It fits on a single GPU. The model handles orchestration — conversation, structured output, routing. The oracles handle truth. You don’t need 405B parameters when the knowledge is in the retrieval layer.

The governed workload decomposes into tasks that 8B handles well: instruction following, classification, and conversational flow. The hard part — knowing what GDPR Article 35 actually says — is in the oracle, not the weights.

Cost

Everyone else is building bigger. We went the other direction.

Frontier modelGoober (8B)
TrainingTens of thousands of GPUs, months, $100M+Single consumer GPU, 120 steps, under an hour, <$1
InferenceMulti-GPU clusters, $0.01–$0.06 per 1K tokensSingle GPU via Ollama, orders of magnitude cheaper
DeploymentGPU cluster, specialized cooling, dedicated ops teamEC2 instance with Ollama. HTTPS via Caddy.
PowerMegawatts. Literal power plant negotiations.One EC2 instance. Standard compute.

If your governance stack requires a data center, you’ve built a dependency, not a solution.

Tradeoffs

You gain

  • +Answers grounded in verified regulatory and framework sources
  • +Oracle provenance on every response — see which sources were consulted
  • +Boundary detection — redirects to professionals instead of guessing
  • +Profile-scoped context — no cold start, no “tell me about your business”
  • +Transparent confidence — ungrounded responses are labeled as such
  • +Runs on a single GPU, dramatically lower cost than frontier models

You lose

  • Not a general-purpose chatbot — optimized for governance and compliance
  • Requires the wizard for full oracle grounding (ungrounded chat available to all)
  • 8B reasoning ceiling — complex multi-step analysis may need human review

We think that’s a good trade.

Try it now

Take the 4-question wizard, then chat with Goober grounded in your governance profile and verified oracle sources.