WellQuote Adapt
AI companion for oil and gas extraction teams that helps troubleshoot production well performance and adapt to evolving OTC quote formats with human-in-the-loop learning.
The Problem
“Troubleshoot underperforming wells faster and keep OTC quote ingestion accurate as formats evolve”
Organizations face these key challenges:
Different well failure modes present similar symptoms, causing slow and inconsistent diagnosis
Critical troubleshooting knowledge is trapped in senior experts and not systematically captured
Historical cases are hard to search across notes, reports, and maintenance systems
Static parsers fail when OTC quote formats change
Impact When Solved
The Shift
Human Does
- •Review SCADA trends, well tests, maintenance logs, and prior notes to diagnose production declines
- •Consult senior engineers to compare symptoms, form root-cause hypotheses, and choose next checks
- •Clean up OTC quotes in spreadsheets, map fields manually, and resolve parser failures
- •Review exceptions when quote templates change and rework records for downstream use
Automation
- •No AI-driven analysis or adaptation in the legacy workflow
- •Static rule-based parsing handles only known OTC quote formats
- •Basic search or document retrieval depends on manual keywords
- •No continuous learning from troubleshooting outcomes or quote corrections
Human Does
- •Confirm or reject suggested well root causes and approve diagnostic or remediation actions
- •Review low-confidence or novel OTC quote extractions and correct field mappings
- •Decide how to handle ambiguous cases, operational exceptions, and high-impact recommendations
AI Handles
- •Retrieve similar historical well cases and summarize likely causes, supporting evidence, and next checks
- •Monitor well performance signals for decline patterns and rank diagnostic hypotheses
- •Classify OTC quote layouts, extract structured fields, and flag low-confidence or drifted formats
- •Capture human corrections and feedback to improve future recommendations and extraction accuracy
Operating Intelligence
How it works
AI runs the first three steps autonomously.
Humans own every decision.
The system gets smarter each cycle.
Who is in control at each step
Each column marks the operating owner for that step. AI-led actions sit above the divider, human decisions and feedback loops sit below it.
Step 1
Assemble Context
Step 2
Analyze
Step 3
Recommend
Step 4
Human Decision
Step 5
Execute
Step 6
Feedback
AI lead
Autonomous execution
Human lead
Approval, override, feedback
AI handles assembly, analysis, and execution. The human gate sits at the decision point. Every cycle refines future recommendations.
The Loop
6 steps
Assemble Context
Combine the relevant records, signals, and constraints.
Analyze
Evaluate options, risk, and likely outcomes.
Recommend
Present a ranked recommendation with supporting rationale.
Human Decision
A human accepts, edits, or rejects the recommendation.
Authority gates · 1
The application must not approve a well root cause or remediation action without a production engineer's judgment. [S1]
Why this step is human
The decision carries real-world consequences that require professional judgment and accountability.
Execute
Carry out the approved action in the operating workflow.
Feedback
Outcome data improves future recommendations.
1 operating angles mapped
Operational Depth
Technologies
Technologies commonly used in WellQuote Adapt implementations:
Key Players
Companies actively working on WellQuote Adapt solutions:
Real-World Use Cases
Human-in-the-loop adaptation for evolving OTC quote formats
When traders start using new ways of writing quotes in chat, the system asks humans to review missed examples so the AI can learn the new pattern instead of breaking.
Production well performance troubleshooting with expert companion
When a well’s output drops, the system checks similar past well problems, shows what experts previously concluded, and keeps learning when engineers add new notes about what happened and how they fixed it.