Features

Fast is easy to fake. Reproducible isn’t.
Built for people who have to defend every number to a stakeholder, a regulator, or a reviewer.

The pipeline

AIUS works through a structured pipeline on your project, with review gates where you approve before it continues:
  1. Context — reads your brief from context/ and writes back its understanding (CONTEXT.md). You review it before anything else happens.
  2. Discovery — profiles your raw data: structure, distributions, anomalies. The findings land in output/discovery/ for you to inspect.
  3. Goals — turns the brief into explicit, measurable goals with success criteria. A hard gate: nothing proceeds until you approve them.
  4. Cleaning — produces processed, analysis-ready datasets in data/processed/.
  5. Analysis — pursues each approved goal in real Jupyter notebooks: feature work, modeling, validation, visualization.
  6. Report — packages the results into deliverables published to your dashboard.
You can chat with the agent at any point to steer, correct, or dig deeper.

Review gates & permissions

  • Three review points — your brief interpretation, the data discovery, and the goal list each pause for your input. Goals are a hard gate.
  • Permission prompts — anything that touches your machine (shell commands, file writes, access outside the project) asks first. Approve once, always, or reject.
  • Team access — colleagues in your organization can open a project’s results (read-only) with their own AIUS token or portal sign-in, so the whole team sees the deliverables without sharing a single login.

Real notebooks, reproducible by default

  • Every analysis is a Jupyter notebook under output/notebooks/ — not a hidden scratchpad.
  • Notebooks run in a curated, fixed Python environment (pandas, numpy, scikit-learn, XGBoost, LightGBM, matplotlib, seaborn, and more) — consistent results across runs and machines.
  • Re-run or edit any notebook yourself; the work is yours.

Deliverables on your dashboard

Each run can publish four deliverable types to your dashboard:
  • Report — the full findings with charts
  • Model — the trained model and its validation
  • Deck — a presentation-ready summary
  • Brief — the executive short form
You can edit a published Report directly on your dashboard — refine its headline, sections, and individual metrics or charts without regenerating the whole run. Edits are versioned, so concurrent changes never silently overwrite each other.

Fork a project

Want to explore a different direction without losing your current work? Fork any project you own from its dashboard. A fork is a point-in-time copy — its brief, artifacts, and reports are duplicated into a brand-new project (with its own lineage back to the original), so you can branch a fresh line of analysis while the original stays untouched.

Resume anywhere — your work syncs

Projects aren’t trapped on one machine. As you work, AIUS syncs each project’s state and data bundle to the cloud, so your dashboard always reflects the latest run and you can pick up from any machine.
  • Resume a sessionaius --continue reopens your last session; aius --session <id> jumps to a specific one. When a project has more than one session, AIUS offers a picker so you choose which to resume.
  • Synced, version-tracked state — stages, goals, and outputs persist between launches and sync to the backend. Sync is versioned, so a stale local copy can’t silently overwrite newer work — if the server has moved ahead, you’re told before anything is replaced. Launch aius on another machine and the project resumes right where you left off.
  • Full audit trail — every run is recorded end to end (stages, model calls, tool calls, artifacts), so there’s a single source of truth for how each insight was produced.

Models, managed for you

AIUS selects and routes the model for every run — chosen for data-science work and kept current as stronger models ship. You don’t pick a model or manage provider API keys: all model traffic runs through the AIUS service, and usage is billed in AIUS tokens. This keeps results consistent and lets us tune quality and cost on your behalf.

Works with your data formats

CSV, TSV, Excel, Parquet, and JSON — dropped into your project’s data/ directory. See Data Management for the common workflows.