Products

Three Layers of AI Trust

Acumetry makes AI systems safe to deploy across two risk surfaces: what your AI does, and what your AI says. Three products, one thesis — control the actions, ground the answers, and keep both verifiable over time.

01

Agent Guardrails

Beta

Runtime control over what your agents can do — blocking destructive commands, data leaks, and runaway loops before they execute.

02

Grounding & Attribution

Beta

Anchors every claim to a real source, builds a citation audit trail, and flags ungrounded output before it reaches a user.

03

RAG Evaluation

Coming Soon

Continuously tests and monitors retrieval quality, answer faithfulness, and data freshness — because grounding isn't set-and-forget.

Product 01 / What Your AI Does

Agent Guardrails & Testing

A policy engine that sits between an AI agent and the actions it can take — shell, files, network, any tool — enforcing your rules before each action runs, plus an audit harness that proves the agent is safe before it ships.

I.

Runtime Guardrails

Every tool call is checked against policy first. Dangerous commands, protected paths, and unapproved domains are blocked before execution — with loop, cost, and iteration ceilings built in.

II.

Pre-Deployment Audit

Run your agent through a battery of adversarial scenarios — destructive ops, exfiltration, secret leakage, runaway loops — and get a pass/fail report before go-live.

III.

Policy as Configuration

Security teams control behavior through a readable policy file, not code. Adjust what's allowed, blocked, or flagged — and the audit re-validates instantly.

Product 02 / What Your AI Says

Grounding & Source Attribution

Ungrounded LLMs invent facts, fabricate citations, quote outdated figures, and burn tokens reasoning toward wrong answers. Grounding anchors responses to real sources — and produces an audit trail proving where every claim came from.

I.

Source Attribution

Every claim is anchored to a specific URL, document, or dataset, generating a citation audit trail — so answers are verifiable, not just plausible.

II.

Hallucination Guarding

Flags and blocks ungrounded output before it reaches a user — preventing invented facts, fabricated dosages, and outdated financial figures from slipping through.

III.

Token Efficiency

By grounding answers in retrieved context instead of letting the model reason in circles, you cut wasted tokens and improve accuracy at the same time.

The Problem

Ungrounded LLMs Are Confidently Wrong

  • Invent facts and fabricate citations
  • Quote outdated medical, legal, or financial data
  • Rely on a stale training-knowledge cutoff
  • Burn tokens reasoning toward wrong answers
  • Offer no way to verify where a claim came from
The Fix

Grounded Systems Are Verifiable

  • Anchor each claim to a real, cited source
  • Ground responses in present-moment data
  • Generate an audit trail of citations
  • Flag low-confidence or unsupported output
  • Reduce hallucinations and token waste together
Product 03 / Keeping It TrustworthyComing Soon

RAG Evaluation & Monitoring

Grounding isn't set-and-forget. Retrieval quality drifts, sources go stale, and index changes silently degrade answers. RAG Evaluation tests your pipeline before launch and keeps watching it in production.

I.

Retrieval Quality

Measures whether the right documents are actually being retrieved for a given query — relevance, recall, and ranking — the foundation everything downstream depends on.

II.

Answer Faithfulness

Checks that generated answers are actually supported by the retrieved context — catching the subtle cases where the model strays beyond its sources.

III.

Freshness & Drift

Detects stale sources and monitors quality over time, alerting you when retrieval performance degrades — so you catch decay before your users do.

Pricing

Plans That Scale With Your AI

Start free with the open-source libraries. Upgrade for hosted monitoring, team controls, and audit-ready compliance reporting across guardrails, grounding, and RAG — or bring us in to run a full safety and accuracy audit for you.

Open Source

Free

$0
Self-hosted libraries
Coming Soon
  • Runtime guardrails & policy engine
  • Grounding & source attribution
  • Pre-deployment audit harness
  • Core RAG evaluation metrics
  • Community support
Get Started
Growing Teams

Team

$99/ mo
Monitoring across multiple agents
Coming Soon
  • Everything in Pro
  • Multiple agents & projects
  • Added seats & role-based access
  • Compliance reporting (EU AI Act / NIST)
  • Priority support
Start Free Trial
Done For You

Audit Engagement

From $2.5k
We test your AI for you
  • Agent red-teaming & safety audit
  • Grounding & hallucination review
  • RAG pipeline evaluation
  • Framework-mapped evidence pack
  • Findings & remediation report
Book an Audit

Prices shown are launch estimates. Final pricing confirmed during onboarding.

Get Started

Not Sure Where to Start?

Tell us how your AI is built and deployed — agents, RAG, or both — and we'll point you to the right product or a full audit engagement.

Talk to Us