Skip to content
XEVRION
Get started
Menu
ProductOverviewReviewProveControlObserveImproveHow it works
TeamsEngineeringSecurityComplianceOperations
CompanyAboutContactChangelogSecurity
ResourcesDocsGlossaryFAQPricingPrivacy
Observe

What did my agents do, and did anyone check?

See every step, its time and cost, and which actions ran with no review. Test changes and version prompts before they ship.

Observe

Agent tracing

Send traces from any agent. See each model call, tool call and action with its time and cost, next to the review it needed.

  • Works with what you useSend OpenTelemetry data, or use the SDK. No new agent framework to learn.
  • Time and cost per stepYou enter your own model prices, so the cost is yours. Steps with no price are shown as unpriced, never guessed.
  • Loops caughtAn agent that repeats the same call again and again is flagged.
How Agent tracing works →
app.xevrion.co.uk / traces / t_9a41Example data

refund-agent run

3.2 s · £0.04
  • model.call plan1.1 s£0.02
  • tool.call orders.get0.3 s£0
  • model.call decide1.4 s£0.02
  • action refund.issueNeeds 2 reviewersReview

Linked review

Request
r_01HX9
Decided
Approved
Prompt
refund-triage v14
Loops caught2This week
Median run3.4 s
Cost per run£0.04

Observe

Review coverage

Match every action in your traces to a review. See which ones a person approved, which a rule passed, and which had no check at all.

  • Five clear statesApproved, auto-approved, rejected but ran anyway, ran before the answer, and unreviewed.
  • Gaps become rulesPick an unguarded action and turn it into a rule in a click.
  • Only Xevrion can show itOther tools see the run. We hold the review too, so we can join the two.
How Review coverage works →
app.xevrion.co.uk / traces / coverageExample data
Actions found4,812In traces
Person approved1,204
Rule passed3,498
No check110Needs a rule

Unchecked, most common

  • customer.email_send62 actionsAdd rule
  • order.cancel31 actionsAdd rule
  • file.export17 actionsAdd rule

Gap to rule

  1. Found in a trace
  2. Rule drafted
  3. What-if replay

Observe

Evals and release gate

Run test sets against your agent, compare runs with honest statistics, and block a release when it gets worse.

  • Honest numbersEvery score has a range. A small test set says so, instead of showing a confident number.
  • Judge, with a checkAn AI judge is only trusted once it agrees with your people often enough on enough cases.
  • A gate for CIFail the build when a run is worse than the one you trust.
How Evals and release gate works →
app.xevrion.co.uk / evals / run_41Example data

Pass rate

Baseline against this run
BaseRun 41

Gate

Rule
No drop over 3 points
Drop
−11 points
Confidence
95% interval
Result
Release blocked

In CI

$ xevrion evals gate run_41FAILED. pass rate fell 90% → 79%exit 1

Observe

Prompt registry

Keep prompts in one place with fixed versions and moving labels, so you know which prompt every trace used.

  • Versions never changeEdit a prompt and you get a new version. Old ones stay exactly as they were.
  • Labels you can movePoint production at version 7, or back to 6. Every move is logged.
  • Linked to tracesSee which prompt version was behind any run, and how it scored.
How Prompt registry works →
app.xevrion.co.uk / prompts / refund-triageExample data

Versions

Never edited
  • v15Tighten refund wordingstaging
  • v14Add order lookupprod
  • v13First review rule

Move a label

  1. Eval run 41 passes
  2. Move prod to v15
  3. Traces show v15

Used by

Traces
1,820 on v14
Agents
refund-agent

Know what your agents did.

Start free. Guard your first agent in a few minutes, and keep a record anyone can check.

Get started freeSee pricing →
  • Free plan, no card
  • Signed, chained decisions
  • Checked offline, without us