Predictive MaintenanceData Analytics & AI Platforms
StorkJet, a Katowice company, uses machine learning and physics models on flight data to help airlines save fuel and monitor aircraft performance.
Founded in 2018 with 11 to 50 staff, it sells FuelPro dashboards with tail-specific models, FuelPro Lab for plain-language analysis, AdvancedAPM degradation alerts and FlyGuide decision support for pilots. It reports 1,700 aircraft and 12,000 pilots on its products.
Wizz Air, Volaris, LOT Polish Airlines, Volotea and Air Astana use its tools, and Condor signed for FuelPro, FuelPro Lab and FlyGuide in February 2026. Volaris reports a 6.7 million US dollar saving in one year, a figure from StorkJet.
Aviation AI deployments and updates
01 / Deployed
StorkJet AI aircraft-performance monitoring at Air Astana, supporting up to 2% lower fuel burn
Air Astana has partnered with StorkJet to implement an AI-driven fuel-efficiency and performance-monitoring platform, the airline said in its full-year 2025 results on 13 March 2026. The airline says the platform is supporting a reduction in fuel burn of up to 2%, against a group fuel bill of USD 331 million in 2025.
A separate, non-AI fuel-tankering programme saved over USD 6m in the 12 months to mid-2025, according to Air Astana's H1 2025 results. DKNews reported the airline's fuel-efficiency figures on 27 August 2026.
Aircraft Performance Monitoring SaaS platform that automatically calculates tail-specific performance factors and idle descent factors using QAR flight data. Uses AI-driven performance models with 50+ parameters across all flight phases to determine fuel burn deviations from baseline for each aircraft individually.
The problem it addresses
Traditional APM processes rely on ACARS/ACMS messages with limited data, require different tools per aircraft type, and take weeks to update after maintenance events. AdvancedAPM unifies all aircraft types in one platform, uses higher-frequency QAR data, and provides same-day performance factor updates after engine changes or other maintenance actions, reducing fuel overburns and improving fuel planning accuracy.
Key features
Tail-specific AI performance models independent of manufacturer models
Uses QAR raw data with up to 50 stable segments per flight across all flight phases
Automatic daily performance factor calculation with no manual work
Idle Factor optimization for descent fuel efficiency
5 more features
Automatic export to flight planning systems via API
Automatic alerting on performance threshold breaches
Supports all aircraft types from turboprops to large jets
Separate tracking of engine and airframe deterioration
30+ monitoring charts and 50+ parameters for aerodynamics, engine, and air data sensors
Technical specifications (6)
SaaS delivery model
Ingests QAR, ACMS, and ACARS data sources
One-time integration, fully automatic thereafter
No hardware required
API integration with third-party flight planning systems (e.g. FLIGHTKEYS)
Machine learning and physics-based performance modeling
Web-based fuel efficiency dashboard and analytics platform that tracks and analyzes up to 48 fuel-saving initiatives across all flight phases, including fuel policy, flight planning, ground operations, APU, departure, climb, cruise, descent, and landing.
The problem it addresses
Airlines lack a unified tool to identify, monitor, and act on fuel saving opportunities across all flight phases. Fuel data is siloed across multiple systems and existing tools cannot attribute savings to specific initiatives or individual aircraft performance. FuelPro consolidates data sources and provides actionable analysis that bridges operational data and decision-making by fuel, dispatch, and flight operations teams.
Key features
Analysis and monitoring of up to 48 distinct fuel initiatives across all flight phases
Tail-specific AI performance models for scenario simulation and saving potential estimation
Pilot engagement module with fuel briefing, fuel scores, and peer comparison
Custom dashboards, charts, and reports with 600+ parameters
5 more features
Data quality checks, repair, and automated processing pipeline
Integration with FlyGuide EFB for pilot feedback loop
Off-the-shelf reports plus user-defined fuel initiatives
Statistical taxi fuel calculation with runway-specific, seasonal forecasts
Tankering optimization analysis
Technical specifications (5)
SaaS delivery model
Reads raw QAR data via StorkJet parsers for all aircraft and recorder types
Data pipeline: loading, quality check/repair, flight processing/matching, automated analysis, reporting
EFB (Electronic Flight Bag) application for pilots providing pre-flight fuel briefing, in-flight decision support, and post-flight performance feedback.
The problem it addresses
Approximately 50% of potential fuel savings depend on pilot decisions, but airlines lack effective tools to communicate fuel efficiency targets to individual pilots or provide reliable, data-driven feedback on their performance. FlyGuide closes the communication gap between airline fuel programs and cockpit crews.
Key features
Pre-flight fuel briefing with discretionary fuel guidance based on historical route data
Shortcut probability information for descent planning at specific airports
Single-engine taxi guidance
Post-flight individual pilot performance scores and phase-by-phase feedback
4 more features
Pilot comparison with peers
Knowledge base and tips for improving fuel efficiency
Fully configurable to airline SOPs and policies
Airline management of pilot targets and motivational content via FuelPro
Technical specifications (4)
EFB application (tablet-based, confirmed on iPad)
Integrates with FuelPro backend for data and configuration
Uses tail-specific AI performance models for personalized insights
Flight Path Optimization module for the FlyGuide EFB application that provides pilots with real-time, tail-specific recommendations for optimal speeds and altitudes during climb, cruise, and descent phases.
The problem it addresses
Aircraft FMS technology originates from the 1990s, uses simplified calculations and limited weather inputs, and does not provide feedback to pilots. FlyGuide FPO delivers updated, aircraft-specific, weather-aware speed and altitude optimization for every phase of flight, enabling pilots to reduce fuel burn beyond what the standard FMS recommends.
Key features
Real-time tail-specific speed and altitude recommendations for climb, cruise, and descent
High-resolution weather data integration
Cloud computing for full flight profile optimization
Cost-penalty display for alternative speed/altitude decisions
2 more features
Post-flight feedback on FPO compliance and savings
Compatible with all Airbus A320 family variants (CEO, NEO, XLR confirmed)
Advanced analytics framework within the FuelPro platform that combines fuel efficiency domain expertise with LLM-based AI to process QAR data and generate custom parameters, models, visualizations, and complex analyses on demand.
The problem it addresses
Standard fuel efficiency reporting covers known initiatives but cannot quickly generate bespoke models or answer custom analytical questions from raw QAR data. FuelPro Lab enables airlines to perform ad-hoc complex analyses without requiring manual engineering effort for each question.
Key features
LLM-powered AI for natural-language-driven fuel analysis
Custom parameter and model generation from QAR data
Notes held in the Aerostack register. Aerostack has not independently verified them.
Market context
StorkJet operates in the aircraft performance monitoring (APM) and fuel efficiency software market, a SaaS segment with strong structural tailwinds from rising fuel costs and decarbonisation pressure.
Read the rest
Its core differentiation is tail-specific, machine-learning-driven fuel modelling at a claimed error rate of a few kilograms per flight hour, significantly more precise than competitors.
Primary competitors are Airbus Skywise (for Airbus fleets), GE Aerospace analytics, and specialist vendors including OpenAirlines (also in the database) and Aviavox.
StorkJet's EU grant funding path and Polish base give it a lower cost structure than US/UK SaaS competitors.
The 2025 deployment at Wizz Air (a 250+ aircraft LCC) represents a significant scale validation.
Profile data from the Aerostack companies register; deployment records from the verified register. Evidence grades: T1 first-party confirmation, T2 credible reporting. See Our approach for how records are graded.
Aerostack companies register
Aerostack tracks AI deployments across airports and airlines, with the published evidence behind each record. Photography is real aviation imagery. Record thumbnails may show the named airport or airline; other photographs do not.
