Early access · research tooling for futures strategies

Describe a futures strategy in plain English. Get a backtest you can trust.

VeriRun Lab is a research IDE for futures strategies. Turn an idea into a reviewable Strategy Brief and working code, then run research-grade backtests with conservative fills and an A–F scorecard that isn’t afraid to say NO-GO.

Research tooling, not trading advice.

VeriRun Lab results viewer: a graded backtest with the conservative-fills method banner, per-symbol stat grid and an F grade with a NO-GO verdict

How it works

From idea to evidence, in four steps

  1. Describe your idea

    Write the strategy the way you’d tell a colleague — “fade the opening range breakout on ES, RTH only.” The builder asks clarifying questions instead of guessing.

  2. Review the Brief & code

    Every assumption is written down in a Strategy Brief you approve first. Generated code arrives as a reviewable diff — production and tests accepted separately.

  3. Run it honestly

    Explore fast with an idealized preview, then grade with conservative fills: trade-through required, post-only makers, per-contract fees.

  4. Compare and iterate

    Every run lands in your library with its exact code version, parameters and data slice — graded, comparable and fully traceable.

The platform

A full research loop, in one place

AI Strategy Builder

Start from a plain-English idea. The builder asks clarifying questions, writes a Strategy Brief with every assumption made explicit, and only then generates code — a multi-file proposal you review as a diff.

  • Clarifying questions before code, not after
  • Assumptions labelled and reviewable in the Brief
  • Production code and tests accepted separately — nothing applies without you
The AI Strategy Builder: a plain-English idea followed by clarifying questions and a reviewable Strategy Brief

A real IDE, not a black box

The code is yours to read and change. Edit in a proper editor with Python intelligence — completions, signatures, live diagnostics — and cut snapshots you can roll back to at any time.

  • Python completions, hovers and diagnostics as you type
  • Multi-file workspaces with tests alongside strategy code
  • Versioned snapshots — every run pins the exact code it ran
The workspace IDE: file tree, Python editor with diagnostics, and run controls

Backtests that tell you the truth

Most backtests flatter you. VeriRun Lab runs two layers: an idealized preview to explore quickly, then a conservative pass — trade-through required to fill, post-only maker orders, per-contract fees — before anything gets a grade.

  • A–F scorecard with hard gates — a NO-GO verdict caps the grade
  • Fill diagnostics show the gap between idealized and conservative fills
  • “Research result — probabilities, not promises” on every report
The gates tab: an honest NO-GO verdict with the rubric, reasons, and the fill-model banner

A library of every run

Runs aren’t throwaway. Each one is saved with its grade, settings and results — searchable, taggable and comparable side by side, so last month’s experiment is still evidence today.

  • Save, label and organize runs into a research library
  • Compare runs head-to-head — charts and metrics aligned
  • Share a read-only results link when you want a second opinion
The run library: pinned, titled runs of an opening-range breakout study with search and filters

Provenance for every number

A result you can’t reproduce is a rumor. Every run records the exact dataset slice, code version, parameters and engine build that produced it — so any number on screen can be traced back to its inputs.

  • Data windows and symbols pinned per run
  • Code version and parameters recorded automatically
  • Preview chart with session structure for eyeballing behaviour
The preview viewer: a candlestick session chart with entries and exits marked

Built for research integrity

Guardrails you can feel good about

You approve every change

AI proposes; you decide. Generated code lands as a scoped, reviewable diff and nothing is applied to your workspace without an explicit accept.

Strategy code runs sandboxed

Your strategies execute in an isolated sandbox with no network access — runs are reproducible and your machine and data stay out of reach.

Spend stays capped

AI usage runs against budgets with hard caps you control. No surprise bills, and a clear view of what each strategy-building session consumed.

Honesty is the default

The grading rubric is versioned and shown with every verdict. Reports carry their method and their caveats — the scorecard can’t be talked out of a NO-GO.

Put your next idea through an honest test

VeriRun Lab is in early access. Open the app and take a strategy from sentence to scorecard.