Achieving an Agentic Back-Office in Liquids Pipelines
A Prescriptive Guide to 5–10X Productivity Gains | $0.10–$0.40 Reduction in Cash Opex per Barrel
AWS BUILDERS BLOG | GETTING STARTED ON AWS
Achieving an Agentic Back-Office in Liquids Pipelines
A Prescriptive Guide to 5–10X Productivity Gains | $0.10–$0.40 Reduction in Cash Opex per Barrel
By Rob Girvan, Swami Natarajan, and Jun Choi
Liquids pipeline operators move crude oil, refined products, and NGLs across thousands of miles of pipeline — and measure their back office in cents per barrel. For Fortune 2000 liquids pipeline operators — Enterprise Products Partners, Energy Transfer (liquids segment), MPLX, ONEOK (post-Magellan acquisition), Plains All American, Phillips 66 Partners, Buckeye Partners, NuStar, Colonial Pipeline, HF Sinclair Logistics, Holly Energy Partners, and the dozens of regional crude, products, and NGL operators — cash operating expense per barrel transported typically runs $0.50 to $2.00, with FERC Part 342 indexed-rate tariffs setting the maximum revenue per barrel-mile. Net margin per barrel is the upside metric — typically $0.30 to $1.20 — but cash opex per barrel is what differentiates pacesetter operators from fourth-quartile peers.
Here's the opportunity: 55% to 65% of employee activities in liquids pipeline back-office functions are repetitive, manual processes — batch scheduling and tracking across thousands of monthly batches, connection carrier settlement with refiners and terminals, FERC Form 6 reporting, tariff filings under FERC Part 342, product-quality contamination claim investigation, terminal and storage settlement, and line-loss allocation across shippers. AWS customers are achieving 5–10X productivity improvements when applying Agentic AI to these processes, translating to potential reductions of $0.10 to $0.40 per barrel transported in cash opex. For a 1,500,000 BPD liquids pipeline system, that's $55M to $220M in annual cost reduction — and because liquids pipelines operate as cost-of-service businesses where every avoided dollar flows back to shippers in indexed-rate calculations, this directly improves competitive positioning.
This post walks you through the six mega-processes ripe for Agentic AI in liquids pipelines, 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
Liquids pipeline back-office work clusters into six mega-processes — five common to most industries plus one liquids-pipeline-distinct mega-process: Batch Tracking & Connection Carrier Settlement. 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 |
|---|---|---|---|
| Batch Tracking & Connection Carrier Settlement | Extreme | 28% | Batch nominations, scheduling, tracking, connection carrier ticket reconciliation, interline settlement |
| FERC Tariff & Indexed Rate Administration | Extreme | 20% | FERC Form 6 reporting, Part 342 indexed rate filings, market-based rate proceedings, tariff amendments and committed rates |
| Terminal, Storage & Loss Allocation | Very High | 16% | Terminal inventory reconciliation, storage settlement, line-loss allocation across shippers, ullage management |
| Shipper Billing & Customer Settlement | Very High | 14% | Monthly shipper invoicing, deficiency payments, take-or-pay reconciliation, blending and product upgrade billing |
| Procure-to-Pay & Operations | High | 13% | Pump station maintenance, integrity dig and ILI contractor settlement, ROW, FERC USOA oil pipeline coding |
| Record-to-Report (R2R) | High | 9% | FERC Form 6/6-Q close, ASC 980 regulated operations, MLP K-1 unitholder tax for partnership operators |
1. Batch Tracking & Connection Carrier Settlement — Extreme Manual Intensity | 28% of Manual Burden
This is the liquids-pipeline-distinct mega-process. Unlike gas pipelines (continuous flow), liquids pipelines move discrete batches of crude grades, refined products (gasoline grades, diesel, jet, heating oil), or NGLs in sequence — typically 100,000–500,000 barrel batches that flow at 3–5 mph. Tracking thousands of batches per month, calculating interface losses (transmix between adjacent batches), settling connection carrier movements (where a batch crosses from one pipeline operator to another), and reconciling delivery tickets against shipper instructions consume substantial back-office labor.
• Batch Nomination & Scheduling — Processing monthly batch nominations from shippers, scheduling against pipeline cycle plans, and confirming origin/destination/grade
• Batch Tracking & Interface Management — Tracking each batch's position on the pipeline, calculating transmix at batch interfaces, and allocating transmix product handling
• Connection Carrier Ticket Reconciliation — Reconciling tens of thousands of monthly delivery tickets where batches transition between connecting pipelines (e.g., crude moving from a gathering pipeline to a long-haul pipeline)
• Interline Settlement — Settling pipeline-to-pipeline transfers under shared facility agreements, joint tariffs, and through-put contracts
• Connection Carrier Imbalance & Loss Allocation — Reconciling imbalances between pipeline operators and allocating cumulative losses across shippers
2. FERC Tariff & Indexed Rate Administration — Extreme Manual Intensity | 20% of Manual Burden
FERC regulates interstate liquids pipelines under the Interstate Commerce Act. FERC Order 561 (1993) established the indexed-rate methodology where pipelines can adjust rates annually based on the FERC-approved index (currently PPI-FG plus 0.78%). Beyond indexed rates, market-based rate authority, settlement rates, and committed-rate tariff structures add complexity.
• FERC Form 6 Annual Filing — Producing FERC Form 6 financial and operating report for major oil pipelines under the FERC USOA for oil pipelines
• Indexed Rate Annual Filing — Computing and filing annual indexed rate adjustments under FERC Part 342 with shipper consultation and comment
• Market-Based Rate Proceedings — Maintaining market-based rate authority documentation, market analysis, and biennial reporting where applicable
• Settlement Rate & Cost-of-Service Tariff — For pipelines using settlement or cost-of-service tariffs, producing rate-case-style cost-of-service support
• Committed-Rate & Volume-Discount Tariff — Administering committed-rate tariffs (long-term shipper commitments at discount), volume incentive tiers, and committed-shipper priority rights
3. Terminal, Storage & Loss Allocation — Very High Manual Intensity | 16% of Manual Burden
Liquids pipelines integrate with terminal and storage operations at origin, intermediate, and destination points. Terminal inventory reconciliation across hundreds of tanks (each with shipper-specific inventory), settlement of storage and terminaling fees, and the complex line-loss allocation where pipeline shrinkage is allocated proportionally back to shippers consume substantial back-office labor.
• Terminal Inventory Reconciliation — Reconciling terminal-by-terminal inventory across hundreds of tanks with shipper-specific allocations and quality differentials
• Storage Settlement — Settling storage fees (cycle storage, monthly storage, peak-injection/withdrawal) under storage agreements
• Line-Loss Allocation — Allocating cumulative line losses (crude evaporation, measurement variance, theft) across shippers proportional to throughput
• Ullage Management — Managing ullage availability across origin and destination terminals to optimize batch scheduling and avoid shipper service interruption
• Tank Quality & Custody Transfer — Reconciling custody-transfer measurement (LACT units, tank gauging) at tank movements with quality-bank adjustments
4. Shipper Billing & Customer Settlement — Very High Manual Intensity | 14% of Manual Burden
Liquids pipeline customers include refiners (crude buyers and product shippers), marketers, retail distributors, military, exporters, and bilateral counterparties. Each contract structure has different rate, deficiency, take-or-pay, and quality-bank provisions, with monthly invoicing tied to shipped volumes.
• Monthly Shipper Invoicing — Producing monthly shipper invoices under tariff rates, committed rates, or settlement rates with applicable surcharges
• Deficiency Payment & Take-or-Pay Settlement — Computing and billing deficiency payments where shippers fall short of committed throughput minimums
• Quality Bank Adjustments — Computing quality bank adjustments (API gravity, sulfur, vapor pressure, aromatic content) for crude and product batches that fall outside pipeline specs
• Blending & Product Upgrade Billing — For pipelines providing in-line blending, calculating blend value and billing shippers for upgraded products
• Shipper Credit & Collateral — Managing shipper credit, prepayment requirements, and collateral postings
5. Procure-to-Pay & Operations — High Manual Intensity | 13% of Manual Burden
Liquids pipeline P2P spans pump station maintenance (turbines and motors), pipeline integrity programs (in-line inspection, dig and validation), control systems, and the FERC USOA oil pipeline plant accounting.
• Pump Station Maintenance Settlement — Reconciling OEM and balance-of-plant contractor invoices for pump and motor major maintenance
• Integrity Management Contractor Settlement — Reconciling ILI, dig and validation, hydrostatic testing contractor invoices for the integrity management program
• FERC USOA Oil Pipeline Plant Account Coding — Coding every invoice to the right operating-vs-capital and FERC oil pipeline plant account
• Right-of-Way & Land Management — Processing ROW lease payments, easement renewals, surface use agreements, and crossing agreements
• Vendor Master & Pipeline Security Compliance — Maintaining vendor master with insurance, OQ, and TSA Pipeline Security Directive compliance documentation
6. Record-to-Report (R2R) — High Manual Intensity | 9% of Manual Burden
Liquids pipeline R2R operates under both GAAP/IFRS and ASC 980 (Regulated Operations) for FERC-regulated entities. Many liquids pipelines are organized as MLPs with K-1 unitholder tax reporting.
• FERC Form 6/6-Q Quarterly & Annual Close — Producing FERC Form 6 (annual) and Form 6-Q (quarterly) financial reports
• MLP K-1 Unitholder Tax — For partnership operators, producing K-1s with state-by-state apportionment for tens of thousands of unitholders
• ASC 980 Regulatory Asset Accounting — Reconciling regulatory asset balances for power cost trackers and stranded-cost recovery
• Intercompany Reconciliations — Reconciling intercompany balances across pipeline systems and joint-venture pipelines
• Bank & Cash Reconciliations — Reconciling settlement clearing accounts and shipper deposit/collateral 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 | Pipeline Standardization | Why It Varies in Liquids Pipelines |
|---|---|---|---|
| Record-to-Report (R2R) | Extreme | Very High | GAAP and ASC 980 are codified; FERC Form 6 schemas are highly structured |
| FERC Tariff & Indexed Rate | N/A (Pipeline-Specific) | Very High | FERC Part 342 indexed rate methodology is fully codified, applied uniformly across operators |
| Batch Tracking & Connection Carrier | N/A (Pipeline-Specific) | High | API and ASTM batch handling and quality standards are uniform; specific cycle schedules vary by pipeline |
| Terminal, Storage & Loss Allocation | Medium-High | High | API standards govern measurement; tank and terminal-specific allocations vary by facility configuration |
| Shipper Billing & Customer Settlement | Medium-High | Medium-High | Tariff rates are codified; committed rates and quality bank adjustments are shipper- and grade-specific |
| Procure-to-Pay & Operations | Very High | High | 3-way match is standard, but pump station OEM contracts and integrity programs vary by operator |
Key Standardization Drivers
• Standards-Led (High Standardization): R2R, FERC Form 6, FERC Part 342 indexed rates, and API/ASTM measurement standards are codified externally — automation simply codifies rules that are already codified.
• Tariff-Led (High Standardization): Indexed rate calculations follow FERC formula uniformly; committed-rate variations are layered on top of standard tariff structures.
• Facility-Specific (Medium Standardization): Terminal and tank configurations, batch cycle plans, and connection carrier interfaces vary by pipeline system, requiring system-specific configuration.
Recommended Implementation Priority
Combining manual intensity (value) and standardization (risk) yields a clear roadmap for liquids pipeline operators:
• Start here → R2R and FERC Tariff Administration: Highest standardization, lowest risk. ASC 980 regulatory accounting, indexed rate calculations, and FERC Form 6 preparation are externally codified.
• Next → Batch Tracking & Connection Carrier Settlement: Extreme value with low-medium risk. Batch nomination, interface management, and connection carrier ticket reconciliation are high-volume rules-based work.
• Then → Terminal, Storage & Loss Allocation: Very high value with medium risk. Terminal inventory reconciliation and line-loss allocation are well-defined work; ullage management requires more careful design.
• Then → Shipper Billing and P2P: Very high and high value with low-medium risk. Tariff-based shipper invoicing and FERC USOA oil pipeline invoice coding are high-volume rules-based work.
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 liquids pipeline 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 liquids pipeline 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 liquids pipeline 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 liquids pipeline 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 liquids pipeline 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 liquids pipeline 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 liquids pipeline 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 cash operating expense by $0.10 to $0.40 per barrel transported at a Fortune 2000 liquids pipeline operator. To build a defensible, process-specific ROI calculation:
• Identify high-volume manual processes (batch tracking, connection carrier reconciliation, FERC Form 6 preparation, indexed rate filings, terminal inventory reconciliation, shipper imbalance settlement)
• Measure current cash opex per barrel by category using FERC Form 6 (operating expense lines and throughput data)
• Apply a conservative 5X productivity improvement based on AI automation
• Layer in revenue/margin recovery — recovered connection carrier disputes, accelerated quality-bank settlement, and improved terminal inventory accuracy improve cash flow beyond pure cost reduction
This bottom-up, per-barrel approach produces a defensible business case that aligns with how liquids pipeline operators report financials and shippers evaluate carrier performance.
Start Building Today
The liquids pipeline back office is one of the highest-ROI targets for Agentic AI. The combination of high transaction volume, codified FERC and API standards, and the cost-of-service pressure on per-barrel rates makes R2R, Tariff Administration, and Batch Tracking 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 — liquids pipeline 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
• FERC — Form 6 Major Oil Pipeline Annual Report
• FERC Part 342 — Indexed Rate Methodology for Oil Pipelines
• FERC Order 561 — Establishment of Oil Pipeline Indexed Rates
• Association of Oil Pipe Lines (AOPL) — Industry Operating Statistics
• American Petroleum Institute (API) — Manual of Petroleum Measurement Standards (MPMS)
• ASTM International — Petroleum Quality Specifications and Test Methods
• PHMSA — Pipeline Integrity Management Program (PIMP) for Hazardous Liquids
• Transportation Security Administration — Pipeline Security Directives
• FASB — ASC 980 Regulated Operations Guidance
• S&P Global Market Intelligence — Liquids Pipeline Financial Benchmarks
• Alerian — Master Limited Partnership (MLP) Sector Analysis
• MLP Association — Master Limited Partnership Tax Reporting Guidance
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/
Rob is an AWS specialist focused on Agentic AI for enterprise back-office transformation. Connect with your AWS account team to schedule a back-office assessment and identify your highest-value automation opportunities.
Enjoyed reading this content? Let the author know!
Your likes, comments, shares, and saves help creators reach more builders.
Loading recommendations
Loading article