Achieving an Agentic Back-Office in Gathering & Processing
A Prescriptive Guide to 5–10X Productivity Gains | $0.04–$0.15 Reduction in Opex per Mcf
AWS BUILDERS BLOG | GETTING STARTED ON AWS
Achieving an Agentic Back-Office in Gathering & Processing
A Prescriptive Guide to 5–10X Productivity Gains | $0.04–$0.15 Reduction in Opex per Mcf
By Rob Girvan, Swami Natarajan, and Jun Choi
Gathering and processing operators sit between upstream production and long-haul transmission, and measure their back office in cents per Mcf. For Fortune 2000 G&P operators — Targa Resources, Western Midstream, EnLink Midstream, DCP Midstream (now Phillips 66), Crestwood (now Energy Transfer), Antero Midstream, Rattler Midstream, Hess Midstream, Equitrans (gathering), Summit Midstream, MPLX (G&P segment), Enterprise Products Partners (G&P segment), and the dozens of regional gathering, compression, and processing operators — operating expense per Mcf gathered or processed typically runs $0.15 to $0.60, with field gathering and compression at the low end and full processing (cryogenic NGL extraction) at the upper end. Fee margin per Mcf is the upside metric — typically $0.30 to $1.20 — but opex per Mcf is what differentiates pacesetter operators.
Here's the opportunity: 55% to 70% of employee activities in G&P back-office functions are repetitive, manual processes — gas plant settlement statements with NGL component allocation across producer-shippers, percentage-of-proceeds (POP) and keep-whole contract administration, well-by-well allocation back to producers, shrinkage and fuel accounting, and royalty support to upstream affiliates. AWS customers are achieving 5–10X productivity improvements when applying Agentic AI to these processes, translating to potential reductions of $0.04 to $0.15 per Mcf in operating expense. For a 5 Bcf/day G&P operator, that's $73M to $275M in annual cost reduction — and because G&P operators bill back to producer-shippers under contract terms, every basis point of operational efficiency improves competitive positioning for the next acreage dedication negotiation.
This post walks you through the six mega-processes ripe for Agentic AI in gathering and processing, where to start based on a value-risk framework, the AWS services powering the transformation, and the production-ready partner platforms already delivering results.
The Six Mega-Processes Ripe for Agentic AI
G&P back-office work clusters into six mega-processes — five common to most industries plus one G&P-distinct mega-process: Gas Plant Settlement & POP/Keep-Whole Contract Accounting. Each carries a different level of manual intensity, which is the first lens for determining where AI agents deliver the fastest ROI.
Manual Intensity Rankings
| Mega-Process | Manual Intensity Level | % of Total Manual Burden | Primary Manual Burden |
|---|---|---|---|
| Gas Plant Settlement & POP/Keep-Whole Accounting | Extreme | 28% | Plant settlement statements, NGL component allocation, POP/keep-whole/fee-based contract accounting |
| Well-by-Well Allocation & Shrinkage | Extreme | 20% | Allocating gathered volumes to wells, shrinkage and fuel accounting, theoretical vs actual recovery reconciliation |
| Producer Statements & Royalty Support | Very High | 16% | Monthly producer settlement statements, royalty support data to upstream, division of interest reconciliation support |
| NGL Marketing & Frac Spread Settlement | Very High | 13% | NGL purity product (ethane, propane, butanes, natural gasoline) marketing settlement, frac spread accounting, T&F billing |
| Procure-to-Pay & Operations | High | 13% | Compressor station maintenance, plant turnaround, ROW, water disposal, FERC USOA gas plant coding |
| Record-to-Report (R2R) | High | 10% | Hedge accounting (NGL frac spread), MLP K-1 unitholder tax, segment reporting for diversified midstream |
1. Gas Plant Settlement & POP/Keep-Whole Contract Accounting — Extreme Manual Intensity | 28% of Manual Burden
This is the G&P-distinct mega-process. Gas processing plants extract NGLs (ethane, propane, normal butane, isobutane, natural gasoline) from raw gas, leaving residue gas to flow to long-haul pipelines. Settlement with producer-shippers happens monthly under one of three primary contract structures — percentage-of-proceeds (POP), keep-whole, or fee-based — each with different commodity exposure, NGL price risk allocation, and allocation methodology. POP contracts share NGL revenue with producers; keep-whole contracts return BTU equivalent in residue gas; fee-based contracts charge a flat per-Mcf fee.
• Monthly Plant Settlement Statement Production — Producing monthly settlement statements for each producer-shipper showing residue gas allocation, NGL component recovery, and theoretical recovery vs actual
• NGL Component Allocation — Allocating recovered ethane, propane, normal butane, isobutane, and natural gasoline back to producer-shippers based on their delivered gas BTU and component composition
• POP Contract Settlement — Computing producer-shipper revenue share under POP contracts with formula-based price indexes (Mont Belvieu, Conway, Henry Hub)
• Keep-Whole Contract Settlement — Reconciling BTU returned to producer-shippers under keep-whole contracts with thermal value reconciliation
• Fee-Based & Cost-of-Service Contract Settlement — Producing fee-based settlement statements with applicable fuel and shrinkage adjustments
2. Well-by-Well Allocation & Shrinkage Accounting — Extreme Manual Intensity | 20% of Manual Burden
Gathering systems aggregate production from hundreds or thousands of wells into central trunklines, with allocation back to individual wells using well tests, theoretical curves, and producer-supplied production data. Shrinkage (fuel, lost-and-unaccounted-for, NGL extraction) must be allocated proportionally, and theoretical-vs-actual recovery variance investigated continuously.
• Well-by-Well Production Allocation — Allocating gathered volumes back to individual wells using well tests, theoretical production curves, and producer-supplied lease-level production
• Shrinkage Allocation — Allocating system shrinkage (fuel, LUFG, NGL extraction) proportionally across producer-shippers
• Theoretical vs Actual Recovery Reconciliation — Reconciling theoretical NGL recovery (based on inlet GPM and plant efficiency) against actual recovery and investigating variance
• Imbalance Settlement with Producer-Shippers — Managing imbalances between scheduled and actual deliveries, with cash-out or in-kind makeup
• Compressor Station Fuel Allocation — Allocating compressor fuel to producer-shippers proportional to throughput
3. Producer Statements & Royalty Support — Very High Manual Intensity | 16% of Manual Burden
G&P operators provide essential downstream data to producer-shippers' royalty distribution processes. Royalty owners receive their checks from producers, but the underlying production volumes, NGL components, and pricing data come from gathering and processing settlement statements. Errors at the G&P level cascade into thousands of mineral-owner royalty checks.
• Monthly Producer Settlement Statements — Producing comprehensive monthly statements showing gathered volumes, processed components, settlements, and adjustments
• Royalty Support Data Files — Providing producer-shippers with detailed production-by-well allocation files for downstream royalty distribution
• Division of Interest Reconciliation Support — Supporting producer-shippers' division-of-interest changes, lease additions, and well additions
• State Severance Tax Support — Providing severance-tax-supporting data (volumes, prices, locations) to producer-shippers for state severance tax filings
• Producer Audit Response — Responding to producer-shipper audits of gathering and processing settlements (typically 2–5 year audit windows)
4. NGL Marketing & Frac Spread Settlement — Very High Manual Intensity | 13% of Manual Burden
Many G&P operators participate in NGL marketing — purchasing NGLs from producer-shippers (under POP or related contracts) and selling them to fractionators, petrochemical end-users, exporters, and bilateral counterparties. Frac spread (the differential between Henry Hub gas and Mont Belvieu NGL prices) is the underlying economic driver.
• NGL Purity Product Marketing Settlement — Settling sales of ethane, propane, normal butane, isobutane, and natural gasoline at Mont Belvieu and Conway-indexed prices
• Frac Spread Accounting — Computing frac spread economics (NGL value vs methane equivalent) and reconciling to ETRM positions
• Transportation & Fractionation (T&F) Billing — Billing transportation and fractionation services through pipelines and frac plants
• Long-Term Fractionation Contract Settlement — Reconciling long-term fractionation agreements with frac plant operators (Mont Belvieu fractionators)
• Export & Petchem Customer Settlement — Settling NGL exports (Mont Belvieu/Houston Ship Channel waterborne) and ethylene-cracker feedstock contracts
5. Procure-to-Pay & Operations — High Manual Intensity | 13% of Manual Burden
G&P P2P spans gathering line construction, compressor station maintenance, gas processing plant turnarounds, water disposal services, ROW management, and the FERC USOA gas plant accounting (where applicable for FERC-regulated portions).
• Compressor Station Maintenance Settlement — Reconciling compressor turbine and reciprocating engine maintenance contractor invoices
• Plant Turnaround Settlement — Reconciling cryo plant turnaround contractor invoices ($20M–$60M per major event) including hot tap, exchanger cleaning, and overhead replacement
• Produced Water & SWD Settlement — Reconciling produced water trucking and saltwater disposal (SWD) invoices against tickets and contracts
• FERC USOA Gas Plant Account Coding — For FERC-regulated portions, coding invoices to FERC USOA gas plant accounts; for non-FERC operations, internal CapEx classification
• Right-of-Way & Land Management — Processing ROW lease payments, easement renewals, surface use agreements, and crossing agreements
6. Record-to-Report (R2R) — High Manual Intensity | 10% of Manual Burden
G&P R2R is dominated by hedge accounting (frac spread hedges are extensive across the industry), MLP K-1 reporting, and segment reporting for diversified midstream operators that span gathering, processing, and pipeline operations.
• Hedge Accounting (ASC 815) — Running hedge effectiveness tests on frac spread, NGL component, and natural gas hedges
• MLP K-1 Unitholder Tax — For partnership operators, producing K-1s with state-by-state apportionment for tens of thousands of unitholders
• Segment Reporting — Producing segment-level P&L for diversified midstream (gathering, processing, fractionation, transportation, marketing) under ASC 280
• Producer-Shipper Receivables Aging — Managing receivables from producer-shippers (including upstream affiliates) with credit and concentration management
• Bank & Cash Reconciliations — Reconciling settlement clearing accounts and project-financing reserve accounts
Where to Start: The Standardization-Risk Framework
Manual intensity tells you where the value is. Standardization tells you where the risk is.
Standardization Rankings
| Mega-Process | Cross-Industry Standardization | G&P Standardization | Why It Varies in G&P |
|---|---|---|---|
| Record-to-Report (R2R) | Extreme | Very High | GAAP and ASC 815 hedge accounting are codified across the industry |
| Procure-to-Pay & Operations | Very High | High | 3-way match is standard, but plant turnaround OEM contracts vary by technology and operator |
| Well-by-Well Allocation & Shrinkage | N/A (G&P-Specific) | Medium-High | API allocation methods are standard, but every system's allocation logic is field-specific |
| Producer Statements & Royalty Support | Medium | Medium-High | Producer statement formats are common across operators; producer-specific data requirements vary |
| NGL Marketing & Frac Spread Settlement | Medium | Medium | Mont Belvieu/Conway pricing is standardized; bilateral marketing contracts have transaction-specific terms |
| Gas Plant Settlement & POP/Keep-Whole | N/A (G&P-Specific) | Medium | Settlement methodology is contract- specific; POP, keep-whole, and fee-based contracts have unique allocation logic |
Key Standardization Drivers
• Standards-Led (High Standardization): R2R, hedge accounting, and standard P2P 3-way match are governed by GAAP and codified rules — automation simply codifies rules that are already codified externally.
• Industry-Convention-Led (Medium-High Standardization): API measurement standards, NGL pricing benchmarks (Mont Belvieu, Conway), and well allocation methodologies follow industry conventions but with system-specific implementation.
• Contract-Bespoke (Medium Standardization): Gas plant settlement under POP, keep-whole, and fee-based contracts is highly contract-specific. Each producer-shipper agreement has unique terms requiring per-contract configuration.
Recommended Implementation Priority
Combining manual intensity (value) and standardization (risk) yields a clear roadmap for G&P operators:
• Start here → R2R and P2P: Highest standardization, lowest risk. Hedge accounting reconciliation, MLP K-1 production, and three-way match for chemicals/maintenance/SWD are externally codified.
• Next → Well-by-Well Allocation & Shrinkage: Extreme value with low-medium risk. Field allocation, shrinkage allocation, and theoretical-vs-actual recovery reconciliation are well-defined work.
• Then → Producer Statements & Royalty Support: Very high value with medium risk. Monthly statement production and royalty support data files are amenable to agentic execution.
• Then → Gas Plant Settlement & POP/Keep-Whole Accounting: Extreme value with higher risk due to contract bespoke structure. Targeted automation of POP and fee-based settlement is the right entry point — keep-whole and complex hybrid contracts require careful agent design.
• Finally → NGL Marketing & Frac Spread: Very high value with medium risk. Standard purity-product settlement is well-suited to agentic execution; bilateral marketing settlement requires more careful design.
Getting Started on AWS
AWS provides a comprehensive stack for building, deploying, and operating Agentic AI at enterprise scale. Three core services anchor the architecture for gathering and processing back-office automation:
Amazon Bedrock
Amazon Bedrock is the foundation for building generative AI applications on AWS. It provides access to high-performing foundation models from leading AI companies through a single API, along with built-in capabilities for customization, retrieval-augmented generation (RAG), and guardrails. For gathering and processing back-office automation, Bedrock powers the reasoning and language understanding that enables AI agents to read invoices and rate filings, interpret regulatory data, reconcile billing exceptions, and generate compliance reports — all with enterprise-grade security and privacy.
Amazon Bedrock AgentCore
While Bedrock helps you build generative AI applications, AgentCore provides the enterprise-grade infrastructure and operations layer for deploying and managing AI agents at scale. AgentCore handles identity and access management, code interpretation, secure execution environments, and VPC/PrivateLink integration — so your agents can access SAP, Oracle, customer information systems (CIS), and work management systems securely. Developers can stand up a working autonomous agent through configuration rather than orchestration code, dramatically reducing time-to-production.
Amazon Quick
Amazon Quick is AWS's unified AI-powered business intelligence and productivity suite. It brings together interactive dashboards, natural language querying, automated insights, and AI-driven research capabilities — enabling utility leaders to monitor back-office KPIs, track regulatory commitments, and surface anomalies across operations. Quick's agentic features — Flows, Automations, and Research — allow teams to build automated analytical workflows that complement back-office AI agents, creating a closed loop from data capture to executive insight.
Agentic AI Platforms Built on AWS
A growing ecosystem of AWS partners has built production-ready Agentic AI platforms specifically designed to tackle the back-office challenges described above. Four leading platforms:
BLP
BLP is the AI platform that transforms core business processes. Trusted by 450+ enterprises in 40+ countries and ranked among Europe's fastest-growing companies on the FT1000 (2026), BLP breaks each process into atomic tasks and assigns a specialized AI agent to each part, with orchestration across the entire workflow. Their focus areas — Finance, Procurement, Sales, and Logistics — map directly to the P2P, O2C, and R2R mega-processes where gathering and processing operators sees the highest manual burden. Founded in Zurich in 2019 and backed by a $50 million investment from Goldman Sachs Alternatives, BLP evolved from deep ERP expertise into an AI-native automation company.
Karini AI
Karini AI is natively built on AWS and holds the AWS AI Specialization in Agentic AI — distinguishing it as an AWS Partner with proven technical expertise in delivering production-ready autonomous agentic systems that reason, plan, collaborate, utilize tools, execute tasks, and continuously improve. Karini enables gathering and processing operators enterprises to build, deploy, scale, and nurture agentic workflows 20X faster, with governance, security, and business-level controls built into a single platform — particularly valuable for the regulatory variation that defines utility back-office work.
Gruve
Gruve combines infrastructure, data, and AI agents into a unified approach, helping gathering and processing operators enterprises deploy AI systems that are scalable, efficient, and aligned with real business value. Their integrated methodology addresses the full stack — from the underlying compute and data layer to the agent orchestration that drives back-office automation — making them a strong fit for utilities that need end-to-end transformation rather than point solutions.
skie.io
skie.io offers a unified cloud platform that optimizes AWS costs, manages cloud operations, and automates enterprise workflows with AI agents. Their three-lever model is particularly compelling for gathering and processing operators:
• Sage — Continuous cloud cost optimization (customers report 20–40% AWS cost reductions)
• Guardian — 24/7 automation-first managed cloud operations with enterprise-grade SLAs
• Muse — AI agents for enterprise workflow automation, including ITSM, help desk, ERP exception handling, and procurement automation
skie.io's self-funding model — where optimization savings fund managed services and AI automation — offers gathering and processing operators a low-risk entry point to agentic operations.
Calculating Value for Your Organization
Full deployment of Agentic AI across all six mega-processes could reduce operating expense by $0.04 to $0.15 per Mcf at a Fortune 2000 G&P operator. To build a defensible, process-specific ROI calculation:
• Identify high-volume manual processes (gas plant settlement, well-by-well allocation, royalty support data preparation, frac spread reconciliation, producer audit response)
• Measure current operating expense per Mcf gathered/processed by category using your latest annual operating budget
• Apply a conservative 5X productivity improvement based on AI automation
• Layer in revenue/margin recovery — recovered theoretical-vs-actual recovery variance, accelerated frac spread settlement, and producer audit defense reduce direct cost and contract risk
This bottom-up, per-Mcf approach produces a defensible business case that aligns with how G&P operators report financials and producer-shippers evaluate operator performance.
Start Building Today
The gathering and processing back office is one of the highest-ROI targets for Agentic AI. The combination of high transaction volume, codified GAAP and API standards, and the cost-of-service competition for acreage dedications makes R2R, P2P, and Well Allocation ideal starting points. With Amazon Bedrock for AI reasoning, Amazon Bedrock AgentCore for secure agent deployment, and Amazon Quick for intelligent analytics — plus production-ready platforms from BLP, Karini AI, Gruve, and skie.io — G&P operators have everything they need to begin their agentic transformation on AWS.
The question isn't whether to automate your back office. It's which process to start with first.
Sources & References
Industry Research
• Gas Processors Association (GPA) — Industry Operating Statistics and Settlement Practices
• American Petroleum Institute (API) — Manual of Petroleum Measurement Standards (MPMS)
• Council of Petroleum Accountants Societies (COPAS) — Gas Plant Accounting Bulletins
• Mont Belvieu Pricing Reports (OPIS, Argus) — NGL Component Pricing Benchmarks
• Conway, KS NGL Pricing — Mid-Continent NGL Component Pricing
• FERC — Form 2 Major Natural Gas Pipeline Annual Report (for FERC-regulated G&P)
• EPA Subpart W — Methane Emissions Reporting for Gathering and Processing
• PHMSA — Pipeline Integrity Management for Gathering Lines
• FASB — ASC 815 Hedge Accounting and ASC 280 Segment Reporting
• MLP Association — Master Limited Partnership Tax Reporting Guidance
• Alerian — MLP Sector Analysis
• Wood Mackenzie — North American Midstream Industry Outlook
AWS Services
• Amazon Bedrock — https://aws.amazon.com/bedrock/
• Amazon Bedrock AgentCore — https://aws.amazon.com/bedrock/agentcore/
• Amazon Quick — https://aws.amazon.com/quicksight/
Agentic AI Platforms
• BLP — https://blp.digital/
• Karini AI — https://karini.ai/
• Gruve — https://gruve.ai/
• skie.io — https://skie.io/
Enjoyed reading this content? Let the author know!
Your likes, comments, shares, and saves help creators reach more builders.
Loading recommendations
Loading article