> ## Documentation Index
> Fetch the complete documentation index at: https://docs.vortexiq.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI on Vortex IQ

> Monitor OpenAI health, cost and reliability signals, and catch incidents and runaway spend early.

Monitor OpenAI health, cost and reliability signals, and catch incidents and runaway spend early.

No changes are made without the configured approval policy. Read-only operations do not modify the connected system; schedules, access scopes, API usage and data handling remain governed by Vortex IQ controls.

[Connect or manage this source](https://app.vortexiq.ai/workbench/settings/sources) · [How connecting works](/integrations/connector-catalogue)

| **20**              | **3**            | **Build your own** | **27**           | **288**        |
| ------------------- | ---------------- | ------------------ | ---------------- | -------------- |
| performance signals | automated checks | automated fixes    | proven workflows | API operations |

## Monitor performance

20 performance signals. Signals with an alert band can raise Nerve Centre alerts; every signal supports a merchant-configured watcher.

| Signal                               | Outcome                 | Alert behaviour    | What it tracks                                                                             |
| ------------------------------------ | ----------------------- | ------------------ | ------------------------------------------------------------------------------------------ |
| **API Requests (30d)**               | Control risk and change | Alert band 0 / -50 | Sum of num\_model\_requests from /v1/organization/usage/completions over the last 30d.     |
| **OpenAI Spend (30d)**               | Control risk and change | Alert band 10 / 50 | Sum of /v1/organization/costs daily amounts over the last 30d. Admin API key required.     |
| **Total Tokens (30d)**               | Control risk and change | Watch only         | input\_tokens + output\_tokens summed over the last 30d.                                   |
| **Avg Cost per Request (30d)**       | Run operations          | Watch only         | 30d spend / 30d num\_model\_requests.                                                      |
| **Avg Daily Spend (30d)**            | Run operations          | Watch only         | 30d spend / days with any cost bucket.                                                     |
| **Avg Tokens per Request (30d)**     | Control risk and change | Watch only         | (input+output tokens) / num\_model\_requests.                                              |
| **Cached Input Tokens (30d)**        | Control risk and change | Watch only         | Sum of input\_cached\_tokens; prompt-cache effectiveness in absolute terms.                |
| **Cost by Line Item (30d)**          | Control risk and change | Watch only         | Costs grouped by line\_item (e.g. per-model input/output token charges).                   |
| **Daily Requests Trend**             | Run operations          | Watch only         | Daily num\_model\_requests buckets over the last 30d.                                      |
| **Daily Spend Trend**                | Run operations          | Watch only         | Daily cost buckets from /v1/organization/costs over the last 30d.                          |
| **Input Tokens (30d)**               | Control risk and change | Watch only         | Sum of input\_tokens over the last 30d.                                                    |
| **Models Available**                 | Control risk and change | Watch only         | Count of models the key can see via /v1/models. Renders with any API key.                  |
| **Output : Input Token Ratio (30d)** | Control risk and change | Watch only         | output\_tokens / input\_tokens; generation-heavy vs context-heavy workloads.               |
| **Output Tokens (30d)**              | Control risk and change | Watch only         | Sum of output\_tokens over the last 30d.                                                   |
| **Prompt Cache Hit Rate (30d)**      | Grow revenue            | Watch only         | input\_cached\_tokens / input\_tokens x 100. Higher = cheaper repeat prompts.              |
| **Requests by Model (30d)**          | Run operations          | Watch only         | num\_model\_requests grouped by model.                                                     |
| **Spend Spike Alert**                | Run operations          | Alert band 10 / 50 | Spend change vs the prior 30d; fires on a spike per the ai\_spend\_trend band.             |
| **Tokens by Model (30d)**            | Control risk and change | Watch only         | input+output tokens grouped by model.                                                      |
| **Top Cost Line Item (30d)**         | Run operations          | Watch only         | The single largest line\_item by 30d cost.                                                 |
| **Usage Stall Alert**                | Run operations          | Alert band 0 / -50 | Request-volume change vs the prior 30d; a silent stall means the integration or key broke. |

## Audit risks and opportunities

A fix status appears only where the action, inputs, approval, verification and recovery controls are mapped. Candidate remediations are never executable.

| Check                                                              | Severity | Outcome                 | Why it matters                                                                                                                                                                                 | Fix status  |
| ------------------------------------------------------------------ | -------- | ----------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------- |
| **API key invalid, expired or lacking the scopes the cards need**  | high     | Control risk and change | Once this credential fails, VortexIQ stops seeing usage, cost and health data from this platform entirely, and every finding here that depends on it goes stale from that moment, silently, un | Report only |
| **Spend up more than 50% vs the prior period**                     | high     | Run operations          | Spend on this platform rose more than 50% versus the prior period. A jump this size is either a deliberate scale-up worth confirming was intentional, or an unbounded process, a stuck job, a  | Report only |
| **Usage dropped more than 50% vs the prior period (silent stall)** | medium   | Control risk and change | Usage halving against the prior period is the earliest sign of a silent stall: a broken schedule, an expired credential, or a team that quietly stopped.                                       | Report only |

### Build your own automated fixes

3 checks report findings on OpenAI today. Turn any finding into an automated fix with a Vortex IQ workflow: **13,885 read and write operations across 229 connectors** are available as building blocks, with approval, verification and rollback on every change.

## Automate approved work

Vortex IQ is integrated with **122 read** and **166 write** operations across assistants, audiovoiceconsents, chatcompletions, evals, evalruns, organizationcertificates on OpenAI. Combine them with anything from the **13,885 operations across 229 connectors** to automate the work in your own words.

Changes follow the merchant's configured approval policy: the target, proposed change, affected records, risk, reversibility and verification plan are shown before execution. Read-only operations do not modify the connected system.

[Create a workflow](https://app.vortexiq.ai/workbench/flows/create?connector=openai)

<Accordion title="Browse the operations you can build with">
  | Resource                           | Read operations | Write operations |
  | ---------------------------------- | --------------- | ---------------- |
  | assistants                         | 2               | 3                |
  | audiovoiceconsents                 | 2               | 3                |
  | chatcompletions                    | 2               | 3                |
  | evals                              | 2               | 3                |
  | evalruns                           | 2               | 3                |
  | organizationcertificates           | 2               | 3                |
  | organizationgroups                 | 2               | 3                |
  | organizationprojectserviceaccounts | 2               | 3                |

  Signed-in users see the full catalogue in the workflow builder, filtered to the sources they have connected.
</Accordion>

### Proven workflow templates (27)

| Workflow                                 | For                               | Also available on                                                                                            | Tested alongside                                            | What it does                                                                                         |
| ---------------------------------------- | --------------------------------- | ------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------- | ---------------------------------------------------------------------------------------------------- |
| **Back-in-stock Opportunity Queue**      | CRM / lifecycle marketing manager | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | Mailchimp, HubSpot, BigCommerce, Shopify                    | identifies high-intent customers and prepares consent-safe notifications.                            |
| **Brand Voice Compliance Review**        | Product content manager           | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, Anthropic, Gemini                     | flags off-brand, unsupported or inconsistent product claims and proposes corrections.                |
| **Campaign Preflight Gate**              | CRM / lifecycle marketing manager | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | Mailchimp, HubSpot, BigCommerce, Shopify                    | validates segment, exclusions, consent, links, stock, offer dates and tracking before send approval. |
| **Catalogue Completeness Guard**         | Product content manager           | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, Anthropic, Gemini                     | scores required fields by category and routes the highest-revenue gaps first.                        |
| **Deliverability and List Health Guard** | CRM / lifecycle marketing manager | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | Mailchimp, HubSpot, BigCommerce, Shopify                    | monitors bounce, complaint, suppression and engagement shifts with safe remediation advice.          |
| **Duplicate Copy Resolver**              | Product content manager           | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, Anthropic, Gemini                     | detects reused descriptions and produces differentiated drafts from verified attributes.             |
| **Flow Performance Decay Watch**         | CRM / lifecycle marketing manager | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | Mailchimp, HubSpot, BigCommerce, Shopify                    | detects lifecycle automations whose engagement or revenue has materially deteriorated.               |
| **Frequency Pressure Guard**             | CRM / lifecycle marketing manager | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | Mailchimp, HubSpot, BigCommerce, Shopify                    | identifies over-contacted customers across campaigns and flows.                                      |
| **Metadata Optimisation Queue**          | SEO manager                       | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, Cloudflare, StagingPro                | generates evidence-based title and description improvements for approval and staged publishing.      |
| **New SKU Content Factory**              | Product content manager           | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, Anthropic, Gemini                     | turns approved source data into complete draft PDPs with a human review queue.                       |
| **Out-of-stock SEO Protector**           | SEO manager                       | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, Cloudflare, StagingPro                | detects valuable unavailable pages and prepares safe redirect, substitute or retention actions.      |
| **PDP Enrichment Queue**                 | Product content manager           | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, Anthropic, Gemini                     | finds thin product pages, generates on-brand copy, and batches changes for approval.                 |
| **Product Claim Evidence Check**         | Product content manager           | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, Anthropic, Gemini                     | identifies unsubstantiated claims and requires evidence or removal before publish.                   |
| **Schema Coverage and Validity Sweep**   | SEO manager                       | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, Cloudflare, StagingPro                | validates structured data across page types and stages theme/template fixes.                         |
| **Seasonal Content Refresh**             | Product content manager           | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, Anthropic, Gemini                     | identifies stale seasonal language and prepares date-safe updates with expiry/rollback.              |
| **Segment Drift Monitor**                | CRM / lifecycle marketing manager | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | Mailchimp, HubSpot, BigCommerce, Shopify                    | flags unexpected audience growth/shrinkage or overlap before it damages sends.                       |
| **Supplier Copy Normaliser**             | Product content manager           | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, Anthropic, Gemini                     | converts inconsistent feeds into house style while preserving factual specifications.                |
| **Technical SEO Regression Monitor**     | SEO manager                       | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, Cloudflare, StagingPro                | watches broken links, redirect chains, canonicals, robots, schema and indexability after changes.    |
| **Variant Consistency Sweep**            | Product content manager           | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, Anthropic, Gemini                     | reconciles names, options, specifications and copy across product families.                          |
| **Brief Approval Router**                | Content manager                   | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic, Gemini | sends briefs to the correct legal, SEO, product and brand approvers based on content type.           |
| **Brief-to-Draft Pipeline**              | Content manager                   | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic, Gemini | produces evidence-backed article drafts with sources, brand rules and approval status.               |
| **Campaign Asset Repurposer**            | Content manager                   | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic, Gemini | turns an approved core message into channel-specific drafts without auto-publishing.                 |
| **Content Calendar Builder**             | Content manager                   | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic, Gemini | creates a channel-ready editorial calendar from launches, seasonality and search demand.             |
| **Content Freshness Watch**              | Content manager                   | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic, Gemini | finds decaying or outdated pages, explains why they matter and opens refresh tasks.                  |
| **Editorial QA Gate**                    | Content manager                   | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic, Gemini | checks links, claims, tone, formatting, metadata and calls to action before approval.                |
| **Evergreen Refresh Queue**              | Content manager                   | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic, Gemini | schedules evidence and date checks for high-value guides.                                            |
| **Launch Story Pack**                    | Content manager                   | DigitalOcean, Google Cloud Platform, Amazon Web Services, Microsoft Azure, Anthropic (Claude), Google Gemini | BigCommerce, Shopify, HubSpot, Mailchimp, Anthropic, Gemini | creates coordinated blog, email and social drafts from verified product information.                 |

13 further designed workflows are in validation and become activatable only once proven against a live account. Prototypes are never presented as ready.

***

*Generated from the connector capability graph. Counts reflect the servable registry after alias normalisation and de-duplication, and refresh automatically when the registry changes.*
