Skip to main content
Ontelis home
See a demo
Ontelis home

Every agent is tested before it runs

Evaluations tests each agent version and rule on every step it covers, before release and after any change. A failure blocks the release, and your QA team signs the evidence.

RegistryReleases
Model switch: Agency invoice agent AGT-0149
Process: Agency invoice, US · Suites rerun Wed Oct 21, 2026
Release REL-0412
Release REL-0412, model switch for the Agency invoice agent, results by step
StepResultSuitesModel
1. Read invoices from the AP mailboxPassed5 of 5 passedCleared to move to the new model
2. Classify the document: invoice or credit memoBlocked4 of 5 passedStays on the current model
3. Match the invoice to the SOW, purchase order and goods receiptPassed5 of 5 passedCleared to move to the new model
4. Propose the SAP postingPassed5 of 5 passedIn shadowon live traffic, before it moves
Blocked for step 2 only: the new model misreads one vendor’s credit memos as invoices. Other steps are cleared to move once your team adopts the release.
Suites for step 2Classify the document: invoice or credit memo
4 of 5 passed
  • ReplayCredit memos from one vendor read as invoicesFailed
  • Compliance300 planted cases, such as a new bank account in the email bodyPassed
  • Rule conformanceEach AP guidance rule in forcePassed
  • Sandbox systemFiled to the AP queue in a sandbox copy, then read backPassed
  • Synthetic pharma sandboxWhole invoice runs on synthetic vendors and contractsPassed
A model switch, gated step by step. Your QA team signs the evidence.

Trusted by 2 out of the 5 largest life sciences companies

Five tests for every step.

Each step an agent covers carries replay, compliance, rule, sandbox and synthetic suites. Any change to a model, prompt, rule or connector reruns the ones it touches.

A failure blocks only the step that failed.

When a model switch misreads one vendor’s credit memos, step 2 stays on the current model and the other steps move. Model swaps run in shadow on live traffic first.

People set the bar agents are measured against.

Two qualified people decide the same sample independently, and their agreement is the ceiling for that step. Model graders score only after they match people.

Suites are sized to the claim you make.

Zero misses in 300 clean cases supports a miss rate under 1%, and 3,000 supports under 0.1%. A weekly human audit measures the real rate in production.

Outside agents take the same tests.

Copilot, Agentforce and your in-house agents run the same step suites through the Agent Gateway. One that fails a compliance suite can only read on that step.

Your QA team signs, not Ontelis.

Each version you adopt gets a validation evidence pack for your QA team to review and sign. Ontelis staff can propose, never approve.

“The diagram used to be the thing we argued about. Now it shows us where every value came from, and it flags what our own templates got wrong.”

Senior Solution Architect, Campaign OperationsOne of the top 10 global pharma companies

What Evaluations does not do

  • Certify compliance or validated state.Your QA team reviews and signs the evidence.
  • Treat a clean pass as proof of a zero miss rate.A weekly human audit measures the real rate in production.
  • Mark an outside agent governed for a step before it passes that step’s suites.A failed compliance suite limits it to read actions on that step.
  • Test agents that do not come through the Agent Gateway.They are labelled observed and get no Ontelis checks.

Where Evaluations fits

Evaluations decides whether a version may run. Oversight shows whether it keeps working.

  1. 01TriggerAgents
  2. 02Context packageContext Graph, with IntuitionDB and Mask
  3. 03Agent draftAgents
  4. 04Govern checksGovern
  5. 05Decision cardWorkspace
  6. 06Write through ConnectConnect
  7. 07LedgerGovern
  8. 08Outcome to IntuitionDBIntuitionDB

Watch Ontelis at work

Short walkthroughs of agents doing commercial work, from the first draft to the person who signs off.

Trace a share loss to access or field

Analytics & Insights · Commercial analytics agent · 4:06

0:00 / 4:06

Customer stories

One of the top five US biopharma companies

Brand teams get HCP answers in under 30 seconds

Read the story
One of the top 10 global pharma companies

Email campaigns cut from 131 effort-days to 46

Read the story

AI agent testing and release gates

Ontelis Evaluations tests each AI agent version and rule on every step it covers, before release and after any change. Each step gets five kinds of test, including replays of your past approved decisions, planted compliance cases and writes read back from a sandbox copy. A failure blocks the release for that step only, and your QA team reviews and signs the evidence. Outside agents are tested only if they come through the Agent Gateway. Once a version is live, Oversight shows whether it keeps working.

Security and data

Data in Evaluations
The customer’s QA team reviews and signs each validation evidence pack.
Vendor documents
Ontelis provides: a SOC 2 Type II report, an ISO 27001 certificate, a HIPAA business associate agreement wherever Ontelis processes PHI, a data processing agreement with transfer clauses, and a sub-processor list.
Models
Ontelis builds no foundation model. No model is trained on customer data, except an opt-in adapter that never leaves the customer’s data plane.
Your controls
Ontelis’s posture as a vendor is kept separate from Govern, which holds your own controls.

Every agent is tested before it runs

See a demo