PG&E
Wildfire risk and public safety power outages (PSS)
Palantir
Utilities
Typical Forward Deployed model
Standard case | Useful reference with remaining gaps
Evidence level A
In production
A
Evidence level
PG&E: Wildfire risk and public safety power outages (PSS)
Evidence level measures whether a source can be located and reviewed; it does not mean vendor-reported claims were independently audited.
Standard case | Useful reference with remaining gaps
9 / 12
Business context1 / 2
Transformation workflow1 / 2
Technical workflow2 / 2
Human roles & governance1 / 2
Measured outcomes2 / 2
Source traceability2 / 2
Remaining gaps: Business context, Transformation workflow, Human roles & governance
Business problem
Extreme weather conditions require the integration of meteorological, grid, customer and asset data over a very short period of time, precise determination of which lines are out of power and continuous notification to customers.
Solution
Foundry captures PSPS scope calculations from data intake, client notifications and external systems write back to form end-to-end auditable streams.
Technical architecture & production workflow
Step 01
Multi-source operating data and historical events
→
Step 02
Foundry harmonized data models and privileges
→
Step 03
Online map of business objects, relationships, status and executable Action
→
Step 04
AIP/rules/prediction model generation recommendations or automated steps
→
Step 05
First-line personnel confirm and execute in Workshop/Application
→
Step 06
The feedback, the results and the new facts form a closed loop.
Key technology & infrastructure components
FoundryOntologyMeteorological and asset dataPSPS workflowClient notification/writing back
Human roles & accountability
Power grid operations and emergency response teams identify power outages and high-risk operations.
FDE delivery actions
- Take a full process with the grid first-line emergency team to identify the nodes that really need to make decisions rather than display data
- Collapse decentralized data sources, competencies and business terms into a single, operational Ontology
- Combine business rules, optimization models, LLM and traditional software according to a reliable boundary, instead of letting the LLM operate
- Insert recommendations directly into existing operating workstations and design approvals, rejections, upgrades and write back to Action
- Continue to modify Ontology, rules and automation with operational KPI acceptance and feedback
Reusable delivery patterns
- Let's be clear about the client, the relationship, the state and the action, and then talk about Agent.
- The recommendation must enter the executable stream, otherwise it's just another dashboard.
- High-value deployment is often a combination of data integration + rules/ optimization + AI + Human-in-the-lop
- Continuous rewriting of the results of implementation to build cumulative operational memory
Business outcomes & delivery results
According to Palantir official sources, the platform supports PSPS and wildfire risk mitigation; the company ' s overview reports a 99 per cent decline in the area affected by wildfires in 2022 compared to 2018-2020.
Evidence boundaries & verification notes
- The official press release clearly identified the deployment of the PSPS; 99 per cent of the area indicator was derived from the Palantir official company overview and could not be considered to have been generated solely by the software.
- The source can be directly located in the case; the value remains disclosed by the source and does not represent an independent audit.