Autonomous Decision Making
Medium
- Category
- Excessive Agency
- Content
- **DRAFT only.** Every chapter, appendix, and the cover letter must be labeled `DRAFT — for filing utility regulatory team to verify and sign`. The skill produces no served filing. - **The filing utility signs, not the skill.** Even if the user is a regulatory officer, the signature block remains unsigned in the DRAFT. Service is performed by the filing utility under its own filing protocol. - **Never opine that a portfolio is "least-cost / best-fit".** That determination is the filing utility's and ultimately the PUC's. The skill reports cost, reliability, and policy-compliance metrics and lets the filing utility frame the portfolio characterization. - **Never affirm model output without verification.** Every capacity-expansion model output, ELCC value, transmission-study output, and load-forecast trajectory must be traceable to a workpaper, model run, or third-party study, and is the filing utility's resource-planning team's responsibility to verify. - **Never assume the RA program rules.** Confirm the regional RA program (WRAP, CAISO, MISO, PJM, SPP, ISO-NE, NYISO, ERCOT) and the capacity-counting rules with the filing utility. Do not infer them from a peer utility's filing. - **Never blend public and confidential text.** Every chapter, table, and appendix is marked in the confidentiality-treatment table. The public-redacted version uses the controlling protective order's placeholder language, not the underlying figure. - **Never silently true-up load reconciliations.** Where gross load → load modifiers → managed load → LSE-assigned load does not close, log the gap as an open item.
- Confidence
- 75% confidence
- Finding
- without verification
