Early access: Agni Predict waitlist now open

Forecasts with honest ranges

Agni Predict turns your time-series data into calibrated p10 / p50 / p90 forecasts in minutes. Powered by our proprietary forecasting foundation model, deployable in the cloud or fully inside your own infrastructure.

Foundation model · UK / EU residency · Cloud or on-prem · No data egress in private mode

Interactive demonstration

Explore the Agni Predict interface

A guided walkthrough of how forecasts are presented. It runs on sample series in your browser, not on a live model. Select a series, adjust the horizon, and toggle p10 / p50 / p90 bounds.

Private deployment available: your data stays in place
Show p10/p90 BandsCalibrated uncertainty interval
Exogenous CovariatesPromo spend & seasonality
Illustrative figures only, from sample data, not a live run.
Ask us for benchmarks on your data
Three ways to deploy

Start in the cloud, move to your own infra

Same model, same API. Switch between cloud, private deploy, and your own fine-tuned checkpoint without rewriting a line of integration code.

Cloud Forecast API

Self-serve. Pay by the forecast.

  • POST a CSV or JSON of historical series
  • Receive point + p10 / p50 / p90 ranges
  • Optional covariates (promos, weather, holidays)
  • p95 latency under 3s for ≤100 series

Private Deploy

Docker image. Your VPC. Zero egress.

  • Weights baked in, runs fully offline
  • Helm chart for Kubernetes
  • Per-node annual licence with updates
  • Ideal for regulated and on-prem workloads

Domain-Tuned

Your data. Your private checkpoint.

  • Upload 6–24 months of historical data
  • Overnight LoRA fine-tune (1–4 GPU-hours)
  • Private checkpoint, served from Cloud or Private
  • Re-tune quarterly included
Capabilities

The boring stuff done properly

Calibrated ranges, not false precision

Every forecast ships with p10 / p50 / p90 quantiles. Your team sees the uncertainty, not just a single line pretending to be the truth.

Zero-shot, then domain-tuned

Start with our pretrained forecasting foundation model. When you're ready, fine-tune on your own data for a private checkpoint that beats generic baselines on your domain.

Your data stays where you put it

Cloud mode runs in eu-west with no third-party telemetry. Private mode runs entirely inside your VPC — historical data and forecasts never leave your network.

Backtest before you commit

We ship a one-click backtest notebook so you can compare Agni Predict against your current baseline on 12 months of your own history, before paying for a single seat.

Where teams use it

Built for decisions, not dashboards

Launch focus

Retail demand

Forecast SKU × location × week with promo and holiday covariates. Replace brittle Prophet pipelines with calibrated ranges your replenishment team can actually trust.

Launch focus

SaaS & fintech KPIs

MRR, churn cohorts, cash runway, treasury forecasts. Honest p10–p90 bands replace overconfident single-point projections in your board pack.

Energy & utilities load

Half-hourly load forecasting with weather covariates. Self-hostable for grid operators and regulated reporting workloads.

Field ops & logistics

Call volume, ticket volume, delivery ETAs. Plan staffing and fleet capacity from the same model your finance team uses for cash forecasts.

Pricing

Annual-first. No hidden compute charges.

A 14-day free trial on the Starter feature set. No card up front. Annual billing rewarded with the prices below; monthly available at +20%.

Starter

Single team, up to 50 series

£249/ month, billed annually
  • 25,000 forecast credits / month
  • Cloud Forecast API
  • p10 / p50 / p90 ranges
  • Email support, 1 business day
Join waitlist
Most teams pick this

Growth

Multi-team, up to 2,000 series

£999/ month, billed annually
  • 250,000 forecast credits / month
  • Covariates (promos, weather, holidays)
  • Async batch jobs
  • Shared Slack support, 4 hour SLA
  • One backtest workshop with our team
Join waitlist

Scale

Vertical specialist, domain-tuned

£2,499/ month, billed annually
  • 1,000,000 forecast credits / month
  • One LoRA fine-tune per quarter
  • Private checkpoint, served via your tenant
  • 99.9% uptime SLA, named CSM
Join waitlist

Private Deploy

Regulated and on-prem workloads

From £36k/ year
  • Docker image + Helm chart
  • Per-node annual licence
  • Quarterly model updates included
  • Named customer success manager
Talk to us

A forecast credit = one series, one forecast call, up to horizon 90 and context 1024. Larger horizons and contexts consume proportionally more credits. Full credit math published in the docs once Agni Predict goes GA.

Trust & compliance

Proven foundation. Honest posture.

Proprietary foundation model

Agni Predict runs on our own pretrained forecasting foundation model. You retain full ownership of any private checkpoint fine-tuned on your data.

UK & EU data residency

Cloud mode runs in eu-west by default. Private Deploy runs entirely inside your own infrastructure for US, APAC, or regulated workloads where data residency is mandatory.

Aligned with UK GDPR

Article 13 notices, DPA on request, SCCs for any sub-processor. We do not pursue SOC 2 or ISO certifications at launch and never claim them — we phrase posture as 'aligned with', not 'certified'.

Honest about the limits

Univariate model. Very short or intermittent series get flagged, not silently forecast. Covariate pipelines are audited against known model limits before any release.

Early access

Join the Agni Predict waitlist

Tell us about your forecasting work. Design partners get six months of Growth tier in exchange for a case study.