# What changed in this research pass

One new Aramco workflow; four existing profiles clarified, including supplier-reported Exxon results already in the history; one digital-planning note and two technical publications. No named failed deployment was verified in this pass.

Three research tracks and editor review of original disclosures, the existing register and source access. Bounded research, not complete global coverage.

## Aramco — Connecting rock samples to a geological knowledge platform

Aramco describes AI-supported core analysis and a shared geological knowledge platform. Samples, images, lab results, interpretations and production outcomes are connected for geoscientists.

Digitized rock imaging feeds AI pattern recognition and geological knowledge graphs. Teams use the linked information to assess reservoir quality and development opportunities. The same article says additional ML work on integrated datasets is underway.

No AI-specific accuracy, turnaround improvement, cost or financial result is disclosed.

Published 25 August 2026. The center’s 150+ employees and archive of more than one million feet of samples are facility context, not AI deployment or validation denominators.

Issuer account with mixed technology maturity. Routine lab turnaround is not an AI-attributed result. No company-wide communications brain, executive oracle, autonomous field control or independently validated benefit is established.

[Understanding the subsurface: inside Aramco’s Core Laboratories Center](https://www.aramco.com/en/news-media/elements-magazine/2026/understanding-the-subsurface-inside-aramco-core-laboratories-center) · 25 August 2026 byline; Utilizing advanced technologies; Shaping the future of exploration

## ExxonMobil — Autonomous drilling in Guyana, with supplier-reported results

SLB’s named ExxonMobil case describes Neuro directional control and DrillOps surface-equipment automation, with shore teams monitoring the work.

Neuro updates trajectory and requests downlink commands. DrillOps controls pumps, drawworks and top drive, adjusts drilling parameters and responds to drilling dysfunction. Operations are monitored from an onshore center.

SLB reports more than 48 km of complex well paths, more than 93% of operations executed autonomously, 51% fewer controlled-ROP downlinks and 75% fewer off-bottom downlinks since implementation.

Undated case in the supplier’s 2026 URL directory. Exact start, observation period, well count and definition of the operations denominator are not supplied.

Supplier-reported operational measures, not independently audited performance or cash ROI. This substantiates the Neuro/DrillOps case, not the separate pending March 2026 first-well claim or its different vendor attribution. Existing source history is retained.

[ExxonMobil Guyana: drilling automation in deepwater operations](https://www.slb.com/resource-library/case-study-with-navigation/di/2026/exxonmobil-leverages-drilling-automation-to-set-new-performance-benchmarks-in-deepwater-operations) · Results: Autonomous drilling and rig automation drive record-setting performance in Guyana

## Ecopetrol — An operating energy desk, with a dispatch model still being built

Ecopetrol’s annual report describes CADE consolidating live operating information and supporting electricity-supply decisions with advanced analytics and generative AI.

A Rubiales dispatch-model proof of concept was developed in the first half of 2025. Work on an MVP began in the second half, using electrical signals to generate operating setpoints. That model’s construction is separate from the broader CADE platform already described in use.

No measured energy, emissions, reliability, cost or production benefit is disclosed for these AI components.

2025 operating and development activity, described in the 2026 annual-report edition. Exact publication day and MVP commissioning date are not established.

The platform’s operating status does not establish live use of the Rubiales MVP. The name “autonomous” does not establish AI control authority. Model, approval and override details are not given.

[Ecopetrol Integrated Management Report 2025](https://files.ecopetrol.com.co/web/esp/aga2026/informe-integrado-gestion-informe-anual-gc.pdf) · PDF page 90 / printed page 89: Centro Autónomo de Despacho Energético (CADE)

## PETRONAS — Deployed exploration tools and a separate equipment-development agreement

PETRONAS says AI.SEEK and Global Exploration Basin Screening & Analysis (GEB) have been deployed. The third TriCipta agreement develops a different set of surface-equipment tools.

The earlier tools unify geoscience information for geospatial analysis. IBM Malaysia and Tridiagonal.AI are partners in the new surface-equipment optimization work, aimed at production and maintenance decisions.

No measured exploration, production, maintenance, time or financial result is supplied. Deployment is a stage disclosure, not a quantified benefit.

Company release dated 8 July 2026. Earlier exploration tools came from 2025 agreements; the third agreement was newly signed.

This is already mentioned in AI-143; the update makes the split clearer. Do not transfer the earlier tools’ deployment status to the new equipment workflow or count another project from the same announcement. Asset, user and model-validation populations are undisclosed.

[PETRONAS advances TriCipta AI through the third joint development agreement](https://www.petronas.com/media/media-releases/petronas-advances-tricipta-ai-through-third-joint-development-agreement-ibm) · 8 July 2026 release: third JDA scope and final two paragraphs on earlier tools

## Chord Energy — Rod-lift AI sits inside a broader artificial-lift improvement program

Chord reports ML on about 99% of rod-lift wells and an early roughly 25% improvement in rod-pump run times. Those figures were already in the register.

The release places rod-lift ML alongside a wider artificial-lift optimization effort. It does not describe the model, vendor or approval/control interface.

The broader program reports over 50% improvement in ESP replacement cycle times, over 25% improvement in failure rates since early 2025, and about 1,200 fewer workover rig days in 2025. These are not separately isolated ML effects.

2025 results, disclosed 25 February 2026. ESP comparisons start at the beginning of 2025; an exact matched AI evaluation period is not supplied.

Keep the rod-lift result separate from ESP and workover outcomes. Do not attribute the whole continuous-improvement program or its free-cash-flow benefit to AI. No additional result profile or cash ROI is counted.

[Chord fourth-quarter and full-year 2025 results](https://ir.chordenergy.com/2026-02-25-Chord-Energy-Reports-Fourth-Quarter-and-Full-Year-2025-Financial-and-Operating-Results,-Issues-2026-Outlook-and-Declares-Base-Dividend) · Operations Update / Production and LOE; two consecutive artificial-lift paragraphs

## TotalEnergies — A 15-year agreement for a shared well-planning environment

SLB announced a 15-year DrillPlan agreement for TotalEnergies’s global upstream portfolio. The work connects subsurface information with well design and engineering.

Offset-well data, trajectories, casing, completion inputs and planning assumptions are brought into a common environment while retaining customer workflows and internal digital expertise.

No rollout population, achieved operating benefit, contract value or return is disclosed.

Agreement announced 8 October 2026; implementation and completion dates are not given.

The release does not identify an AI component. It belongs in operating-technology context, not the AI-adoption count. A 15-year term does not prove the whole portfolio is already live.

[SLB awarded digital drilling contract by TotalEnergies](https://investorcenter.slb.com/news-releases/news-release-details/slb-awarded-digital-drilling-contract-totalenergies) · 8 October 2026 release; agreement description and Key Points

## Petroleum Research — A more complicated model did not improve these forecasts

In a comparison of four production datasets and three forecast horizons, kernel-based models outperformed neural architectures. More complexity did not deliver an accuracy advantage in these tests.

The study compares ML proxies for field-scale production under operating scenarios. Its abstract also reports that spatial data coverage appeared more important for generalization than dataset size.

No company-wide deployment result, cancellation rate or project cash return is established.

Published online 21 January 2026. We reviewed the publisher’s indexed abstract; direct full-article access was unavailable.

The finding applies to the tested inputs, datasets and horizons. It does not establish that deep learning is ineffective across petroleum tasks. This is technical benchmarking, not a failed operator rollout.

[Full-field petroleum production forecasting: Is deep learning all you need?](https://www.sciencedirect.com/science/article/pii/S2096249526000074) · Publisher abstract; online publication date 21 January 2026

## Energy and AI — A good prediction is only part of a reliable control system

A surface-network review finds gaps in uncertainty, governance, transfer across fields and evidence for safe closed-loop use beyond pilots. Sensor drift and rare operating conditions can undermine an otherwise accurate model.

The authors reviewed prediction, monitoring and control literature from January 2015 through March 2026. They argue for physically defensible recommendations, oversight and protected actuation.

This review does not measure incident frequency, failure prevalence or the performance of a named operator’s deployed system.

September 2026 journal edition; literature search through March 2026. Relevant publisher text was available through the web index.

Literature synthesis is not an independent field audit. Its gaps do not show that a particular company’s controls are unsafe or that every deployment remains a pilot.

[AI and ML for production prediction and optimization of oil and gas surface networks](https://www.sciencedirect.com/science/article/pii/S2666546826000984) · Introduction and review method; sections 4.1, 4.2 and conclusions