Tasq Case Study: Sustained 10x ROI for a Major Operator
Abstract
Tasq is an AI-driven production platform designed to optimize oil and gas well operations. This case study highlights its implementation at a major operator, focusing on its impact on downtime automation, downtime reduction, and enhancing operational efficiency.
Key Results:
- Immediate $1M increase in production revenue within the first month.
- 10x ROI in the first month, scaling to a sustained 100x ROI, with the organization internally reporting a 2,000 bbl/day uplift ($36M/year).
- 2x improvement in downtime reporting, uncovering $75M/month in previously untracked opportunities.
- 30% reduction in downtime, aligning with the primary objective of automating downtime reporting and enhancing operational efficiency.
- Streamlined workflows leading to faster issue resolution and a 3x increase in operational efficiency.
This study provides a deep dive into Tasq's AI-driven automation architecture, implementation, challenges, and impact, offering insights into how AI is transforming oil and gas operations.
Introduction
Modern oil and gas operations generate enormous amounts of data, but inefficiencies in analyzing and acting on this data can lead to significant production losses. Tasq is an AI-powered operational platform designed to bridge this gap by automating production workflows and improving decision-making.
Deployed at a major operator, Tasq integrated into control rooms, assisted production engineers, and coordinated field operations to create a data-driven ecosystem. The result was a transformation from a manual, reactive workflow to a proactive, AI-driven approach, improving efficiency, production output, and cost savings.
Tasq was implemented across all wells in the basin with multiple artificial lift types and well types. Tasq connected 5 different data sources across SCADA, Artificial Lift, Production Accounting, Downtime, and WellView all into 1 system.
Problem Statement
Key Challenges in Oil & Gas Production Management:
- Wasted Time Daily - Poor data quality, increased time dealing with bad data, data entry requirement leads to everyone doing trivial repetitive work. Engineers and field operators had to manually review SCADA data, downtime logs, and work orders, leading to delayed responses and inefficiencies.
- Unreported Downtime - Manual downtime reporting missed small yet cumulative losses, leading to inaccurate production tracking and lost revenue.
- Fragmented Software Systems - Data was scattered across multiple siloed tools, requiring excessive manual consolidation.
- Reactive Decision-Making - Engineers and operators spent most of their time firefighting issues rather than proactively optimizing production.
- High Operational Costs - Inefficiencies in workflow and reporting translated to millions in lost production and unnecessary operational expenditure.
Solution Approach
By integrating AI across operational teams, Tasq eliminated redundant tasks and enhanced efficiency at every stage of production management. Tasq models were deployed to better enhance production, catch unknown issues, prioritize work, automate processes, all to reduce the need of human intervention.
Pre-Tasq vs. Post-Tasq Software Stack
Tasq's implementation streamlined operations by replacing fragmented, manual workflows with an AI-driven, automated approach.
| Function | Pre-Tasq Stack | Post-Tasq (AI-Driven) |
|---|---|---|
| Well Monitoring | SCADA alarms + Pi Screens | AI Models |
| Data Analysis | Manual Excel-based analysis | AI Prompts |
| Downtime Logging | Manual reporting (incomplete) | Auto-logged downtime events |
| Task Dispatch | Emails/calls to field techs | AI-prioritized work orders |
| Decision Making | Reactive and manual | Data-driven AI recommendations |
Pre Tasq: Every system sits apart from each other in form, increasing time to work and increasing time to resolve every issue at hand.
Post Tasq: Every system connects together through AI, where data is searchable, entries are automated, models can be created, all of which decreased time to resolve issues.
Tasq AI Models
Tasq deployed five AI models to automate the flow of work within the control room, engineers, and field operations. These models included:
- Well Target Model - Used historical trends and real-time data to set optimal production targets for each well.
- Bulk and Test Prediction Model - Predicted bulk production and test rates to identify inefficiencies in test allocation.
- Setpoint Optimization Model - Setpoint changes are recommended to optimize a well, providing value in production, while reducing human diagnosis time.
- Real-Time Model - Saving wells before they completely go down is a key aspect of enhancing performance of the asset, moving from reactive to proactive.
- Build Your Own Model - Build models 200x faster with Tasq. Below are a few examples of models that were created by the organization to reduce troubleshooting time.
- Separator Burner Issue Model - Detected and diagnosed burner inefficiencies affecting production efficiency.
- Gas Lift Paraffin in Tubing Model - Monitored and predicted paraffin buildup in gas lift wells, enabling proactive remediation.
- Dump Failure Model - Identified dump valve failures and suggested corrective actions.
- Tank Leak Model - Find leaks before they become a safety critical event.
- Arrival Sensor Model - Improved detection for arrival sensor failures, improving plunger run reliability.
The next step in operational efficiencies is changing from logic based SQL to learning systems. This is the single most important step in creating the next level of operational efficiencies. It is key that an organization know each production issue at a very detailed level, to route the right work to the right people. There is a high amount of bottleneck that occurs in (a) diagnosing any issue (b) troubleshooting the issues (c) fixing the issue and currently that process is a swiss cheese model limiting value across the organization. With Build Your Own Model, any user can create their own models to diagnose, troubleshoot, any issue type. Tasq will live classify the issue as it is occurring, moving the organization towards higher value work.
Downtime Reduction Analysis
Tasq's downtime automation provides an accurate, real-time picture of downtime events, eliminating the inefficiencies of manual reporting. Operators previously relied on manual logging, which led to incomplete or inaccurate reporting. With Tasq, every downtime event is automatically detected, categorized, and analyzed, ensuring accurate reporting across all assets.
Before Tasq: 7 Manual User Steps
Post Tasq: 1 User Step
Results & Performance Gains
Comparing Tasq's automated downtime tracking vs. manual client-reported downtime, Tasq uncovered 2x more production impact than what was previously being recorded. Upon further iteration, the AI models refined the process to identify 3x more downtime events than manual tracking.
Tasq models increase clear production opportunities on more than 2x what is being reported.
Tasq changed the slope of % downtime right from onboarding and consistently after.
Insights from Downtime Analysis
- Model Driven Approach Reduces Downtime
- Models driving work assignment decreases downtime volume across operations
- Manual Reporting is a Failed Strategy
- Reliance on employees to fill out downtime fails in many ways including incorrect underreported volume reporting, ineffective use of employees time, and missed opportunities
- Simplifies Workflows
- Tasq decreases human touch by 3x by connecting different data sources and automating workflows. This approach simplifies operations for end users and increases actionability.
Conclusion & Summary
Tasq has transformed production management by integrating AI-driven automation to improve operational efficiency and drive significant cost savings.
Key Takeaways:
- Automated Downtime Detection & Reduction: Tasq uncovered 2x more downtime events and led to a 30% reduction in downtime over six months.
- Operational Efficiency & Production Gains: Operators no longer waste time manually entering downtime data. Tasq automates the process. Engineers and control room focuses on high-impact actions rather than sifting through inconsistent data.
- Significant ROI & Production Uplift: $1M in new production revenue was generated in the first month. Sustained benefits resulted in a 10x ROI in month one, scaling to 100x ROI. 2,000 bbl/day production increase, equating to $40M/year in added value.
- AI-Driven Decision-Making & Alignment: Teams work from a single source of truth, eliminating guesswork. The platform provides real-time recommendations, ensuring optimal production outcomes.
About Tasq
Tasq is affordable and easy to use, from individual production engineers to entire production teams with tie-in to all existing corporate systems. Designed, developed and supported by production engineers with decades of production experience for major and "super independent" US-operators, Tasq is truly the system built "by production teams for production teams."