Run your agent seven times.
See how often it changes its answer.

7runs runs your AI agent N times against a golden test suite and reports what one run can never tell you: pass rate with an honest confidence interval, flakiness, and whether your last change made things worse. We publish the methodology and the data — and measure your agent for you.

open methodology · published run records · no telemetry
every number ships with a Wilson 95% confidence interval
EVERY AGENT TEAM ASKS THE SAME THREE QUESTIONS
01

Does it actually work?

Pass rate against a golden set — measured, not vibes. Deterministic matchers plus an LLM judge for the fuzzy parts.

02

How unstable is it?

Same input, N runs. Agents are non-deterministic — one run proves nothing. Flakiness is a first-class metric here, not a footnote.

03

Did I just make it worse?

Compare any two runs. Regressions beyond statistical noise turn your CI red. Noise doesn't.

A SUITE IS A YAML FILE — A REPORT IS AN ANSWER
suite.yaml
name: pr-review-inspector
adapter:
  type: claude-agent
  agent: .claude/agents/security-inspector.md
defaults:
  reps: 7
  timeout_s: 180
cases:
  - id: sql-injection-obvious
    label: positive
    input:
      prompt: "Review this diff for security issues:"
      files: [fixtures/diff-sqli.patch]
    checks:
      - regex: "VERDICT:\\s*ISSUE_FOUND"
      - llm_rubric: "Finding names the vulnerable parameter."
  - id: clean-diff-no-false-positive
    label: negative
    input:
      prompt: "Review this diff for security issues:"
      files: [fixtures/diff-clean.patch]
    checks:
      - regex: "VERDICT:\\s*CLEAN"
7runs report — what you get
pass rate 78.6%CI95 62.8–88.9
flaky cases 2 / 8same input, different verdicts
precision / recall 0.91 / 0.83over labeled cases
judge disputes 1two judges disagreed → flagged
p95 latency · cost 41s · $0.84per full run
Numbers above are an illustration of the report format. Every percentage ships with a Wilson 95% interval — a bare number would be lying.

Don't take the illustration's word for it — read a real report: 4 agents × 3 models × 336 executions →
THE FLAKINESS LEADERBOARD — PROOF, NOT PROMISES
popular open-source code-review agents · same 3 hard cases · 7 reps each · double-judged
MODEL AXISPASS RATEWHAT HAPPENED
Claude Opus100%every agent, every case — ceiling
Claude Sonnet 595–100%first cracks appear
Claude Haiku 4.567–76%collapse — concentrated on the false-positive bait

Four agents (wshobson security-auditor & code-reviewer, VoltAgent security-auditor, Claude Code) measured across three waves. The headline: the model axis discriminates where case difficulty did not — smaller models keep recall, lose precision. Every suite, fixture, raw run record and both judge transcripts are published for replay: github.com/7runs/leaderboard. Maintainers were notified before publication and given a response window.

WHAT YOU CAN BUY
AVAILABLE NOW

Agent Readiness Audit

$2,000 · fixed · 5 working days · 3 pilot slots

We turn one critical workflow of your agent into a measurable baseline:

  • ~20 golden test cases built from your real traffic
  • every case run 7× — trust score with Wilson 95% CI, flakiness, failure map
  • full report with raw outputs and both judge transcripts
  • the suite is yours to keep + a release gate for every future change
Read the full offer →
IN DEVELOPMENT

Self-serve dashboard

pay-as-you-go credits · enterprise plans for teams

Test your own agents, on your own schedule:

  • write scenarios in the browser — or let AI draft them from your description
  • buy credits, run every case N times, stop exactly at your budget
  • professional shareable report: trust score, flakiness, per-case history
  • enterprise: teams, SSO, API + CI gate, invoice billing
Get early access via demo →
BUILT ON FOUR OPINIONS

Variance is the product

Every case runs N times (default 7). Stable-pass, stable-fail, or flaky — the flaky ones are where agents burn you in production.

Never trust one judge

Every llm_rubric check is judged twice. If the judges disagree, the result is disputed — counted against you and listed separately. Raw judge output is stored for audit.

Agents, not prompts

The unit under test is the whole agent — multi-turn, tool-using, black box. First-class adapter for Claude Code / Claude Agent SDK, plus a shell adapter for anything you can invoke from a command line.

Your data stays yours

Your suite, your outputs, your report — delivered to you, retained only under the data policy we agree on. No telemetry, no training on your data, and deletion that actually deletes.

HOW WORKING WITH 7RUNS LOOKS
STEP 1 — DEMO
book a 30-min demo

We walk through a live measurement on a reference agent — real runs, real statistics, nothing staged. Bring your hardest workflow.

STEP 2 — BASELINE
we measure your agent

15–25 golden test cases built from your real scenarios, run 7×. You get the full report: trust score, confidence intervals, flakiness, failure modes.

STEP 3 — GATE
you keep the suite

The golden suite and a regression gate stay with your team — every agent change gets measured before it ships. Self-serve dashboard in development.

STRAIGHT ANSWERS

Is the engine open source? No. The methodology, the benchmark suites, and every raw run record are public and replayable — the engine that produces them is the product. Pricing? Shared at the demo — it depends on what you're measuring; no seat math, no surprises. Your data? Your suite and your results belong to you. No telemetry, no training on your data, real deletion on request.

Measure your agent before your customers do.

A 30-minute live demo: we run a real measurement in front of you and show exactly what a trust report would say about your agent. No slides, no staged output.

or write to hello@7runs.dev — replies within one business day