Talk to your battery data.

Cliviq connects your battery test data to AI through MCP.
Ask questions in plain language, get interactive analytics instantly.

Try the demo → See how it works

claude.ai — connected to cliviq battery MCP

New conversation cliviq-battery · 7 tools

You

Show me the degradation of CX2-16.

✦

Assistant

CX2-16 shows steady capacity fade with a knee near cycle 312, and reached 80% SOH at cycle 422. Here's the interactive view:

✓ battery_cycle_analysis("CX2-16")

You

Compare it with CX2-25.

✦

Assistant

Added CX2-25. It fades more slowly — its knee doesn't appear until ~cycle 410. RPT cycles are excluded so the fade curve stays clean.

✓ battery_cycle_analysis(["CX2-16","CX2-25"])

Ask a follow-up… ↵

Degradation dashboard Live

ZoomNormalizeOverlay

CX2-16 CX2-25 Knee

Current SOH

82.3%

Knee point

Cyc 312

EOL @80% · observed

Cyc 422

How it works

Three steps to conversational battery analytics

Connect your data once. Ask questions forever. No dashboards to build, no scripts to maintain.

Step 01

Connect the MCP

Add Cliviq as a custom connector in Claude. Just one URL — no API key for the demo. Takes 30 seconds.

connector URL
https://app.cliviq.com/mcp

Step 02

Ask questions

Query your battery data in plain language. Compare cells, analyze degradation, explore dQ/dV curves.

Compare capacity fade for all NMC622 cells tested at 45°C

Step 03

Get a live dashboard

An interactive dashboard renders right inside the chat. Zoom, normalize, overlay cells, and drill into cycles — no setup.

→Fade / SOH & knee detection

→dQ/dV peak tracking

→Cross-cell distribution & compare

Capabilities

Built for battery engineers

Designed around how battery teams actually think: dataset → cell → cycle → step. Plain-language in, interactive analytics out.

Lifetime & fade

Capacity-fade and SOH curves, knee-point detection, and observed end-of-life — with reference (RPT) cycles automatically excluded so the trend stays clean. Compare across cells and conditions.

Cycle-level deep dive

Voltage profiles, dQ/dV and dV/dQ curves with automatic peak detection and shift tracking — see how a cell changes cycle by cycle.

Why it ages coming soon

Degradation-mode signatures — lithium loss vs. active-material loss vs. rising resistance — plus per-cycle internal resistance. The protocol detector tells the model which cycles are formation, regular cycling, or reference tests.

Many datasets, one interface

Bring public archives and your own test data together — across cyclers and chemistries — with build and formation context where it exists. Fast even on large, long-running tests; your private data stays your own.

Use cases

Who is this for

Any team that generates battery test data and wants faster answers.

Cell manufacturers

QC engineers compare production batches instantly. Spot anomalies in formation data before they ship.

Automotive OEMs

Validation teams query aging test data across suppliers and chemistries without writing a single script.

R&D labs

Researchers explore new cell designs conversationally. dQ/dV evolution, degradation fitting, cross-cell comparison — all from one interface.

Get started

Try it with real battery data

The demo is pre-loaded with open battery datasets. Add one connector URL to Claude — no signup, no API key — and start querying in under a minute.

Open the demo → Request early access