# Con Edison — API Agent Score

> Score: 53/100 (Grade: D) | Domain: coned.com | Rubric: 1.0.0 | Checked: July 29, 2026

Con Edison scored 53/100 (D), classified "not-ai-ready".

[View full report](https://www.postman.com/ai/ai-ready-apis/company/coned)
[All organizations](https://www.postman.com/ai/ai-ready-apis/llms.txt)

## Summary

- Overall: 53/100 (D)
- Classification: not-ai-ready

## Category Scores

- API Design: 51/100 (D)
- Developer Experience: 63/100 (C)
- Agent Discovery: 55/100 (D)
- Agent Understanding: 48/100 (F)
- Agent Usability: 53/100 (D)

## Check Results

### API Design

- [pass] Example coverage — README is present and includes a runnable quickstart. Investigated: sdk 100%, docs 0%.
- [warn] Schema coverage & depth — 0/4 (0%) public params are fully typed (no any/**kwargs). Analyzer reports not all methods have a derivable input schema. Investigated: sdk 25%.
- [fail] Security & governance hygiene — No security.txt at /.well-known/security.txt or /security.txt. Investigated: wellknown 0%.
- [skip] Machine-readable, versioned contract — No surface produced evidence for this capability in this run.
- [skip] Auth declared & discoverable — No surface produced evidence for this capability in this run.

### Developer Experience

- [pass] Self-service developer portal — Self-service signup at https://www.coned.com/en/register/pre-register; no free tier or sandbox language detected. Investigated: docs 100%.
- [warn] Quickstart present — Quickstart page reachable (1 variants scanned starting at https://www.coned.com/sms/quickstart) but no runnable code sample detected in HTML or .md variant. Investigated: docs 50%.
- [warn] Description completeness — 4/6 operations lack a description. Investigated: sdk 33%.
- [fail] Code samples in docs — No detectable code samples across 3 sampled docs pages. Investigated: docs 0%.
- [skip] Changelog published — No surface produced evidence for this capability in this run.

### Agent Discovery

- [warn] Docs reachable, not hard auth-gated — Server ignores Accept: text/markdown header (0/2 pages return markdown). Investigated: docs 70%.
- [pass] Crawlable / AEO — Docs paths crawlable by all monitored AI agents. Investigated: wellknown 100%.
- [warn] Registry & SDK presence — No MCP server, tool manifest, or list-tools capability is discoverable (server entrypoint: absent, tool manifest: unknown, list-tools: unknown). Investigated: sdk 25%, docs 0%, cli 0%.
- [fail] llms.txt present, valid & comprehensive — No llms.txt found at any candidate location (https://www.coned.com/en/accounts-billing/share-energy-usage-data/become-a-third-party/llms.txt, https://www.coned.com/llms.txt, https://www.coned.com/docs/llms.txt). Investigated: docs 0%, sdk 0%.

### Agent Understanding

- [warn] Agent-navigable, token-efficient docs — No pages support .md URLs (0/2 tested). Investigated: docs 79%.
- [fail] Machine-readable errors (RFC 9457) — No single common SDK base error class was found; errors do not share one root. Investigated: sdk 0%.
- [fail] Agent instructions file (AGENTS.md) — No AGENTS.md at the site root or /.well-known/. Investigated: wellknown 0%.
- [fail] Docs structured data — Neither JSON-LD nor OpenGraph/meta tags detected across 3 assessed pages (3 JS-rendered). Investigated: docs 0%.
- [skip] Operation purpose clarity — No surface produced evidence for this capability in this run.
- [skip] Description consistency across surfaces — Only 0 surface description(s) with ≥6 tokens available; need at least 2 to compare.

### Agent Usability

- [pass] Sandbox separation — Sandbox environments are exposed (sandbox). Investigated: sdk 100%.
- [fail] Idempotency documented — No built-in retry machinery was found; transient failures are not retried. Investigated: sdk 0%.
- [fail] Runnable collection with test scripts — No public Postman workspace discovered for the org. Investigated: platform 0%.
- [skip] Rate-limit signaling — No surface produced evidence for this capability in this run.
- [skip] Pagination documented & consistent — No surface produced evidence for this capability in this run.

## Executive Summary

Coned's API program shows relative strength in doc parseability and registry presence, but faces critical gaps in agent readiness and partner self-serve onboarding that will stall integration efforts before they begin. The two weakest areas — agent understanding (missing machine-readable errors, agent context files, and structured data) and agent discoverability (no llms.txt, no AI-navigable front door) — mean that neither human partners nor their AI coding agents can reliably find, interpret, or act on your APIs today. Prioritizing a machine-readable documentation portal with agent discovery artifacts, followed by structured error contracts and runnable collections, will unlock self-serve partner onboarding and give agents the grounded context they need to integrate correctly.