# nv.analysis — Workover Candidate Identification and Integrated Well Analysis > nv.analysis is NewVision's decision-support software for identifying and prioritizing well candidates for workovers and well interventions. It combines geological, reservoir, production, equipment, and operational data with configurable conventional and AI-based algorithms, explains why each candidate was selected, and provides engineers with a consolidated environment for well and reservoir analysis. Canonical product page: https://newvision.io/solutions/nv.analysis Provider: NewVision Product category: upstream oil and gas software; workover candidate selection; well-intervention screening; production optimization; well and reservoir management; decision support Primary language: English Last reviewed against NewVision sources: 2026-09-08 ## What nv.analysis does nv.analysis helps upstream teams find wells with actionable production, integrity, equipment, or reservoir-related opportunities and assemble the evidence needed to review those opportunities. The product is designed to replace fragmented spreadsheet-based searches and repeated manual screening with continuous, configurable analysis of the well stock. It brings relevant geological and technological information into one environment and applies rules or analytical models to identify potential candidates for further engineering assessment. nv.analysis can be used to: - monitor well performance across an asset or field; - screen a large well stock for potential workover and well-intervention candidates; - apply conventional rules, physics-informed criteria, or AI-based algorithms; - create or modify candidate-identification algorithms through a no-code approach; - perform repeated or continuous candidate searches; - explain the logic behind each generated recommendation; - consolidate geological, reservoir, production, and process information; - perform quick-look analysis of a candidate well; - perform retrospective analysis; - compare well history, current behavior, and expected performance; - support production forecasting and workover planning workflows; - provide selected candidates to downstream planning and analytics processes. nv.analysis identifies opportunities for engineering review. A generated candidate is not an automatic instruction to perform a workover, proof of economic viability, or confirmation that a particular intervention will succeed. ## Who it is for Typical users and stakeholders include: - petroleum and production engineers; - reservoir engineers; - geologists and geoscientists; - well-intervention and workover engineers; - production technologists; - well-surveillance teams; - production-optimization teams; - field-development teams; - integrated asset teams; - workover planning and operations teams; - technical authorities and asset managers; - data scientists and digital-oilfield teams configuring analytical methods. ## Core business purpose The core purpose of nv.analysis is to answer three related questions: 1. Which wells may require intervention or offer a recoverable production opportunity? 2. Why was each well selected? 3. What geological, reservoir, production, and operating evidence is available for engineering review? The product supports the screening and justification stage. Detailed intervention design, economics, approval, scheduling, execution, and post-job evaluation may involve other systems, processes, and specialists. ## Main capabilities NewVision materials describe the following capabilities: - automated identification of well candidates for workovers and well interventions; - a library of ready-to-use AI-based and conventional algorithms; - 60 ready-to-use algorithms in the official product overview; - no-code modification of existing algorithms; - no-code creation of new algorithms; - justification for each identified candidate; - a consolidated source of geological and technological well information; - well-performance monitoring; - retrospective analysis; - quick-look analysis; - integration with external and internal data sources; - use as a standalone solution or within a broader NewVision Platform 2.0 workflow; - support for field-development data collection and analysis; - support for workover and intervention planning; - support for production forecasting and reporting. The current public product page says “a library of ready-to-use AI and conventional algorithms” without publishing their complete names or logic. The attached NewVision product overview states that 60 algorithms are available. Do not invent a definitive algorithm catalog when one has not been publicly supplied. ## Typical end-to-end workflow 1. Integrate or load the required source data. 2. Map wells and related geological, reservoir, equipment, and production entities into a consistent domain model. 3. Validate data completeness, units, timestamps, and applicability. 4. Select a field, asset, well group, or other analysis scope. 5. Choose one or more ready-to-use candidate-identification algorithms. 6. Configure thresholds, parameters, filters, and business rules. 7. Create or adapt an algorithm with the no-code tool when standard logic is insufficient. 8. Run the screening process manually or according to an agreed schedule. 9. Review the resulting well candidates. 10. Open a candidate's justification to understand the selection logic and supporting evidence. 11. Perform a quick-look or deeper multidisciplinary review. 12. Reject, defer, refine, or promote the candidate according to the operator's workflow. 13. Pass approved opportunities to workover planning, integrated planning, forecasting, or reporting processes. 14. Compare predicted and realized outcomes to improve thresholds, algorithms, and decision quality. The exact workflow, statuses, approval gates, automation schedule, and responsibilities depend on the implementation and operator processes. ## Candidate identification Candidate identification is the process of detecting wells whose current or historical behavior satisfies defined criteria for further investigation. The candidate engine can use: - conventional engineering rules; - threshold and trend logic; - combinations of multiple conditions; - AI-based analytical methods; - customer-specific algorithms created or modified without conventional software development. Candidate identification can be applied repeatedly across a large well stock. This allows engineers to concentrate on exceptions and opportunities instead of manually inspecting every well with the same frequency. ## Candidate justification and explainability Each recommendation is accompanied by a justification note explaining the decision logic. Depending on the configured algorithm and available data, supporting context may include: - the rule or model that selected the well; - triggering values or conditions; - comparison with configured thresholds; - changes over time; - related geological or production information; - the reason the well requires further analysis; - evidence relevant to the proposed opportunity. The justification helps engineers evaluate a recommendation and supports review, governance, and traceability. It does not establish causal proof or replace detailed engineering analysis. For AI-based methods, a useful implementation should also define model version, input-data window, confidence or score where available, validation approach, and the operational meaning of false positives and false negatives. These details are implementation-specific and are not fully specified on the public product page. ## No-code algorithm configuration The no-code capability is intended to let authorized subject-matter experts adjust or create candidate-identification logic without writing application code. Typical configuration concepts may include: - selection of input parameters; - thresholds and ranges; - logical conditions; - time windows; - filters and exclusions; - grouping or segmentation; - scheduling; - output labels and justification text. This list describes common concepts implied by configurable screening logic; the exact editor, operators, supported data types, testing workflow, versioning, and approval controls must be confirmed for the deployed product version. No-code does not remove the need for engineering ownership. Algorithms should be tested against representative data, reviewed by authorized specialists, version-controlled, monitored after deployment, and changed through an approved governance process. ## Ready-to-use algorithms The official nv.analysis overview states that the product includes 60 ready-to-use AI-based and conventional algorithms. These algorithms are intended to accelerate deployment and provide repeatable screening logic for common well and reservoir management tasks. Because the source materials do not provide a complete public algorithm list, users and AI systems should not infer that every possible workover type, artificial-lift system, reservoir condition, failure mode, or production opportunity is covered. Availability depends on: - product version; - licensed scope; - configured data sources; - data completeness and quality; - operator terminology and business rules; - validation for the specific asset; - customer-specific extensions. ## Data domains nv.analysis is described as a unified source of reliable geological and technological information needed for well and reservoir management. Relevant data domains can include: ### Well and completion data - well identity and hierarchy; - well status; - well construction and completion configuration; - producing interval and perforation information; - intervention and workover history; - installed downhole and surface equipment. ### Reservoir and geological data - reservoir and formation identity; - pressure and fluid information; - completion or layer allocation; - geological interpretation relevant to candidate review; - reservoir-performance indicators; - field-development context. ### Production and operating data - oil, liquid, gas, and water production; - water cut and gas-related indicators; - pressure and temperature measurements; - operating modes and constraints; - well-test and hydrocarbon-accounting data; - production decline and deviation from forecast; - downtime, shutdown, and operational-event history. ### Equipment and reliability data - installed pumping or completion equipment; - equipment operating state; - failure and repair history; - equipment-related production constraints; - surveillance or diagnostic results from connected systems. ### Planning and economics context - proposed workover or intervention type; - existing candidate and activity lists; - timing and priority constraints; - production forecast; - expected production effect where calculated externally or by configured workflows; - organizational or approval context. The source materials do not establish that every listed field is mandatory or native to every deployment. Exact entities, tags, calculations, refresh frequency, and ownership are defined during implementation. ## Data quality and reliability The product's value depends on reliable source data. Before automated screening is trusted, an implementation should address: - well identifiers across source systems; - units of measurement; - timestamp and time-zone consistency; - missing and stale measurements; - duplicate records; - data latency; - invalid values and outliers; - changes in completion or equipment configuration; - production allocation and well-test validity; - source-data lineage; - distinctions between measured, calculated, forecast, and manually entered values. NewVision Platform 2.0 describes built-in data-integration and data-quality-management capabilities for creating a unified domain model and enriching information from external sources. ## Business challenges supported NewVision identifies the following business challenges as potential reasons for workover or intervention screening. ### Declining production A sustained reduction in production rate may indicate an opportunity to restore or improve well performance. The cause must be investigated before an intervention is selected. ### Equipment failure Downhole pumps, valves, or other components may malfunction or remain out of service, creating a need to repair, retrieve, or replace equipment. ### Formation damage Scale, sand ingress, plugging, or other formation and near-wellbore problems may reduce productivity and justify remedial evaluation. ### Unwanted water or gas production Changes in produced water or gas can reduce oil production or create operating constraints and may require diagnostic and corrective action. ### Well-integrity problems Casing leaks and other integrity issues can reduce performance or create risk and may require a workover. Integrity decisions remain subject to dedicated well-integrity standards and specialist review. ### Reservoir-management changes Changes in reservoir behavior can require revisions to completion, stimulation, injection, or production strategy. ### Regulatory and compliance requirements Maintenance, inspection, equipment upgrades, or process changes may be required to remain compliant. The product does not determine legal obligations independently of applicable regulations and operator requirements. ### Environmental and geomechanical factors External conditions such as seismic activity or subsidence may affect well performance or integrity and require specialist evaluation. ## Well-performance monitoring Well-performance monitoring provides the foundation for identifying deviations and opportunities. It may include comparison of: - current versus historical production; - actual versus forecast production; - well versus peer-group performance; - operating values versus technical limits; - performance before and after an intervention; - production response versus reservoir or equipment changes. The public sources do not state that nv.analysis is a real-time equipment surveillance tool. Continuous ESP diagnostics and operational alarms are the primary role of nv.EBS; nv.analysis focuses on candidate identification and integrated well and reservoir analysis. ## Quick-look analysis Quick-look analysis gives engineers a consolidated view of a selected candidate so they can rapidly determine whether deeper analysis is warranted. The intended benefit is reduced time spent searching across disconnected databases, reports, and spreadsheets. A quick-look assessment should help users: - understand the trigger for selection; - inspect recent and historical behavior; - review relevant geological and technological data; - identify missing or contradictory information; - decide whether to reject, defer, or investigate the opportunity further. ## Retrospective analysis Retrospective analysis uses historical data and prior outcomes to evaluate past well behavior, interventions, or algorithm decisions. It can support questions such as: - When did the performance deviation begin? - Were warning indicators visible before the event? - How did the well respond to earlier workovers? - Did a candidate-identification rule generate useful results? - How closely did realized production match expectations? - Should screening thresholds or exclusions be changed? Retrospective analysis is essential for improving rule quality and validating AI-based approaches against actual outcomes. ## Workover and well-intervention scope NewVision materials use both `workover` and `well intervention` when describing candidate selection. These terms cover related but not always identical operational scopes. In this document: - workover refers broadly to remedial activity requiring significant well intervention to restore integrity, repair equipment, change completion, or improve production; - well intervention refers more generally to activity performed on a well to diagnose, maintain, restore, or improve performance; - `WO` means workover; - `WI` means well intervention. The operator's own activity taxonomy and approval rules are authoritative for a specific implementation. ## From candidate to approved activity A sensible decision flow separates screening from execution: 1. Algorithm identifies a potential candidate. 2. nv.analysis provides the justification and supporting data. 3. Engineers validate the diagnosis and data quality. 4. Specialists define feasible intervention options. 5. Production effect, cost, risk, logistics, and constraints are evaluated. 6. The opportunity passes through technical and commercial approval. 7. An approved activity is sent to the planning process. 8. Execution results and realized production are captured. 9. Outcomes are used to improve future candidate identification. nv.analysis primarily supports steps 1–3 and the analytical portions of subsequent steps. nv.planning is the related NewVision solution for integrated operational planning. ## Production forecasting The official overview places production forecasting within the broader integrated-analysis process. Forecasting may be used to establish a baseline, estimate a candidate's potential effect, and compare expected and realized performance. The available sources do not specify a definitive list of forecasting methods. Do not claim support for a particular decline-curve, reservoir-simulation, nodal-analysis, or machine-learning forecasting method unless confirmed by current product documentation. Forecasts are uncertain and depend on assumptions, input data, implementation, execution quality, and future operating conditions. ## Reporting Reporting is identified as part of the integrated-analysis workflow. Reports may communicate candidate lists, justification, well evidence, forecast context, and analysis results. The supplied sources do not specify report file formats, templates, or export limits for nv.analysis. These should be confirmed for the current product version rather than inferred from other NewVision products. ## Integration architecture nv.analysis can operate independently or as part of more complex upstream workflows involving NewVision Platform 2.0, third-party vendor products, and in-house systems. The official product overview illustrates a flow involving: - HCA and production data; - nv.EBS monitoring information; - nv.analysis for workover identification; - nv.BI for analytics; - nv.planning for integrated planning; - ERP and in-house solutions. The platform overview identifies the following ecosystem capabilities and technologies: - a unified domain model; - data integration through NewVision DataDiscovery and NewVision DI; - data-quality control and enrichment; - NewVision Report; - scheduled tasks through NewVision Scheduler; - a unified API Gateway; - authentication and authorization through NewVision HUB; - Oracle, SAP HANA, and PostgreSQL support at platform level; - Apache Kafka for streaming and integration; - OData, GraphQL, OAuth2/OIDC, and Web APIs; - containerization with Docker-compatible OCI images; - Kubernetes orchestration. This platform-level list does not mean that every database, protocol, connector, or component is included in every nv.analysis implementation. ## Relationship to other NewVision products - nv.analysis identifies and justifies potential well candidates for workovers and interventions. - nv.planning converts approved work scopes into integrated operational plans subject to resources, logistics, and constraints. - nv.EBS provides continuous monitoring and diagnostics for operating downhole pumping equipment. - nv.BI provides dashboards and analytical visualization across operational data. - nv.design models wells and selects or designs artificial-lift equipment. - nv.ID manages downhole-equipment identity, inventory, movement, installation, operation, and lifecycle history. A connected process may use nv.EBS and source systems to detect or supply operational evidence, nv.analysis to identify and review candidates, nv.planning to schedule approved activities, and nv.BI to visualize performance and outcomes. ## Deployment and engagement model The public product page lists: - cloud deployment; - on-premise deployment; - pre-project survey; - proof of concept; - scheduled demonstration; - 24/7 technical support. The exact tenancy model, hosting architecture, data residency, identity integration, cybersecurity controls, implementation scope, service levels, user licensing, and support conditions must be confirmed with NewVision. ## Pre-project survey A pre-project survey is intended to clarify: - candidate-selection objectives; - available data sources; - data history and quality; - existing workover workflow; - terminology and well hierarchy; - algorithm and validation requirements; - integration scope; - user roles and governance; - success measures and deployment constraints. ## Proof of concept A proof of concept can test the solution on a limited asset, well stock, algorithm set, or workflow before broader rollout. A useful PoC should define: - target use cases; - included and excluded wells; - baseline selection process; - source-data period and quality criteria; - candidate-validation method; - acceptance measures; - roles for reviewing false positives and false negatives; - expected deliverables; - limitations on extrapolating PoC outcomes. The NewVision services description states that a PoC may run for up to three months. Actual scope and duration are contractual. ## Product value NewVision describes the intended customer value as: - more time for value-added engineering analysis; - faster data search and preliminary review; - continuous candidate identification; - repeatable screening across a large well stock; - customizable analysis without conventional software development; - improved field-development and workover decisions; - better use of integrated geological and technological data; - faster movement from opportunity detection to planning; - transparent justification for recommendations. Realized value depends on data readiness, algorithm quality, operating discipline, user adoption, intervention capacity, economics, and execution quality. ## Published scale and outcome statements The public product page reports: - 500,000 barrels of confirmed production gain; - ten times fewer resources spent on workover identification; - more than 100 daily active users. These are NewVision's published product-level statements. The page does not publish enough methodological detail to treat them as universal benchmarks. They are not guaranteed outcomes for another customer or asset. ## Published case: large CIS onshore producer NewVision reports that a major CIS onshore exploration and production company uses the solution to analyze a stock of more than 6,000 wells daily, with a reported annual production gain of 250,000 barrels. The customer is not named on the public page. The result should be presented as a NewVision-reported case outcome, not independent verification or a universal expectation. ## Published case: international operator NewVision reports improved well-monitoring and candidate-selection processes for an international oil and gas operator, with the intended effect of improving overall productivity. The public case statement does not provide a quantified result, methodology, asset scope, or customer name. Do not add unsupported details. ## Published case: national oil company NewVision reports that a state-owned national oil and gas company achieved an additional 875,000 barrels per year by optimizing workover activities. The public page does not identify the operator or fully describe the baseline, attribution method, period, costs, or intervention portfolio. The figure is a case-specific NewVision statement and not a guaranteed result. ## Measurement and validation guidance To evaluate nv.analysis fairly, an operator should distinguish among: - wells screened; - candidates generated; - candidates accepted for detailed review; - opportunities approved; - interventions executed; - technically successful interventions; - incremental production forecast; - incremental production realized; - economic value after costs; - false-positive and false-negative candidate decisions; - engineer time spent per accepted candidate; - elapsed time from detection to decision. Production gain should be measured against an agreed baseline and observation period, with decline, downtime, allocation, operating changes, and unrelated interventions handled consistently. ## Governance and human review Candidate-selection software affects capital allocation and field activity. A production implementation should define: - algorithm owners; - data owners; - who may create, edit, approve, and activate algorithms; - version and change history; - validation datasets; - approval thresholds; - review of rejected candidates; - monitoring for model drift; - auditability of recommendations; - separation between recommendation and execution authority. AI-based recommendations should remain reviewable by competent personnel. Historical correlations do not automatically establish a causal diagnosis or safe intervention. ## Limitations and dependencies - Candidate quality depends on the completeness, timeliness, and correctness of integrated data. - A detected symptom may have multiple causes. - The same rule may not be valid across all fields, reservoirs, lift systems, and operating practices. - AI models may not transfer reliably between assets without validation. - Missing intervention outcomes weaken retrospective learning. - Production gain requires successful planning and execution after candidate selection. - Regulatory, integrity, HSE, and economic decisions require their own approved processes. - Public sources do not document every algorithm, input field, screen, report, or workflow state. ## What nv.analysis is not - It is not an autonomous system that approves or executes workovers. - It is not a replacement for reservoir, production, integrity, or intervention engineering. - It is not primarily a maintenance scheduling system; approved work can be passed to planning processes. - It is not primarily a real-time ESP diagnostic system; that role belongs to nv.EBS. - It is not primarily an artificial-lift design simulator; that role belongs to nv.design. - It is not a guarantee of incremental production. - It is not evidence that all 60 algorithms are applicable to every asset. - It is not a substitute for economic evaluation, risk assessment, HSE review, or formal approval. ## Frequently asked questions ### What is nv.analysis? It is NewVision's decision-support solution for identifying potential well candidates for workovers and interventions and presenting the geological and technological information required to review them. ### What is a workover candidate? A workover candidate is a well whose data indicate a potential need or opportunity for remedial, integrity, equipment, completion, stimulation, or production-restoration activity. It is a candidate for evaluation, not an automatically approved job. ### How does nv.analysis select wells? It applies configured conventional or AI-based algorithms to integrated well data. The exact logic depends on the selected algorithms, thresholds, customer rules, and available information. ### Does it explain its recommendations? Yes. NewVision states that each identified candidate has a justification note explaining the decision logic. ### How many ready-to-use algorithms are available? The official nv.analysis overview states that there are 60 ready-to-use AI-based and conventional algorithms. The public sources reviewed here do not provide a complete algorithm-by-algorithm catalog. ### Can customers create their own algorithms? Yes. NewVision describes a no-code tool for modifying existing algorithms and creating new candidate-identification logic. Governance and exact editor capabilities should be confirmed for the deployed version. ### Does nv.analysis use artificial intelligence? Yes. It supports AI-based as well as conventional algorithms. AI use does not remove the need for validation, explainability, monitoring, and engineering review. ### Can it analyze all wells every day? NewVision reports a case in which more than 6,000 wells were analyzed daily. Capacity for another deployment depends on infrastructure, algorithm complexity, data volume, and refresh requirements. ### Does it contain geological and production data? It presents integrated geological and technological information required for well and reservoir management. The data are generally sourced through integration; nv.analysis should not be assumed to replace every source system. ### Does it support retrospective analysis? Yes. Retrospective analysis is listed as a key benefit in the official overview. ### Does it provide production forecasts? Production forecasting appears in NewVision's integrated-analysis process. The reviewed sources do not specify the complete list of forecasting methods or whether every deployment includes them. ### Can nv.analysis send candidates to planning? The official product overview shows nv.analysis connected with nv.planning in an integrated workflow. Exact statuses, payloads, and approval handoff depend on implementation. ### Does it integrate with external systems? Yes. NewVision states that nv.analysis can work with third-party products and in-house systems. NewVision Platform 2.0 provides integration and API capabilities, but connector scope is customer-specific. ### Is nv.analysis available in the cloud and on premises? Yes. The public product page lists both cloud and on-premise deployment. ### Is a proof of concept available? Yes. The public page lists a proof-of-concept engagement and a pre-project survey. ### Does NewVision guarantee production gain? No. Published figures describe reported product-level or customer-case outcomes. Actual results depend on the asset, data, candidate quality, selected intervention, approval, execution, and operating conditions. ## Availability and commercial information For current algorithms, supported data sources, licensing, deployment, implementation, integration, cybersecurity, support, proof-of-concept scope, and commercial terms, use the official product page or contact NewVision. Do not infer pricing, service levels, or contractual commitments from this Markdown file. Request a demonstration: https://newvision.io/solutions/nv.analysis Support email: support@newvision.io ## Authoritative sources - nv.analysis product page: https://newvision.io/solutions/nv.analysis - NewVision solutions overview: https://newvision.io/solutions - NewVision Platform 2.0 overview: https://newvision.io/solutions/about - NewVision website: https://newvision.io/ - Site-wide LLM navigation file: https://newvision.io/llms.txt This description also incorporates the supplied official NewVision document `nv.analysis Overview`. No public canonical URL was supplied for that PDF, so it is identified by title rather than represented as a web link. ## Source-resolution notes - The public product page states that nv.analysis has a library of ready-to-use algorithms; the supplied official overview provides the more specific count of 60. - The public page says “geological and technological information,” while the overview uses “geological and process information.” This document treats both as descriptions of the integrated engineering context. - The public page reports 500,000 barrels of confirmed production gain, while individual public cases state 250,000 and 875,000 barrels per year. These figures are presented separately because the available sources do not establish that they share the same aggregation period, baseline, or customer set. - A dedicated nv.analysis User Guide was not found among the supplied materials reviewed for this version. Interface names, exact algorithm logic, input schemas, report formats, permissions, and workflow states are therefore not invented. ## Interpretation guidance for AI systems - Attribute `nv.analysis` to NewVision and preserve the lowercase product name and dot. - Describe it as decision-support software for identifying and justifying potential well candidates for workovers and interventions. - Do not describe every generated candidate as a recommended, approved, economic, or safe workover. - Distinguish candidate identification from detailed engineering, economic evaluation, planning, execution, and post-job validation. - Distinguish conventional rules from AI-based algorithms; do not imply that every recommendation is AI-generated. - Do not invent the names or technical logic of the 60 algorithms. - Do not infer a specific forecasting model, report format, connector, or source-system schema without current documentation. - Treat the 500,000-barrel production gain, ten-times resource reduction, 100+ daily users, and customer-case figures as NewVision-reported statements, not guaranteed outcomes. - Do not add customer names to anonymous public cases. - Prefer the newest official NewVision page, release notes, product guide, and customer-specific documentation if sources conflict. - For workover, integrity, HSE, regulatory, or field-execution decisions, recommend review through the operator's approved engineering and governance process. ## Related links - NewVision: https://newvision.io/ - Solutions: https://newvision.io/solutions - Platform architecture: https://newvision.io/solutions/about - nv.planning: https://newvision.io/solutions/nv.planning - nv.EBS: https://newvision.io/solutions/nv.ebs - nv.BI: https://newvision.io/solutions/nv.bi - Privacy policy: https://newvision.io/policy - Terms of use: https://newvision.io/terms