Requests
128,400
What are we working on?
Ask a question, create an output, or build an app that works with your tools and data.
Get Started
Build an enterprise Data & AI platform dashboard
Connect to AI/ML systems and monitor model deployments, pipeline health, and transformation progress
App
Connect to AI/ML systems and monitor model deployments, pipeline health, and transformation progress
Draft an AI Governance Policy
Generate a policy grounded in your AI standards and NIST AI RMF
Document
Generate a policy grounded in your AI standards and NIST AI RMF
Build a Q3 Enterprise Transformation review deck
Pull data from Jira and Confluence into slides
Slide Deck
Pull data from Jira and Confluence into slides
Connect to our enterprise data platform and build a dashboard showing AI model deployment status, data pipeline health, and transformation initiative progress across business units.
AI
I'll need access to your enterprise data platform. Let me request that through a Gatekeeper.
Gatekeeper: Enterprise Data Platform API
Requesting read-only access to AI model registries, data pipeline metrics, and transformation KPIs. The Gatekeeper holds the credential and logs every query.
Requesting read-only access to AI model registries, data pipeline metrics, and transformation KPIs. The Gatekeeper holds the credential and logs every query.
Approved.
AI
Access granted. Pulling platform telemetry now.
Executed code
const models = await env.AI_PLATFORM.getModelRegistry({
status: "deployed",
include: ["metrics", "drift", "latency"]
});
const pipelines = await env.DATA_PLATFORM.getPipelineHealth({
scope: "enterprise",
window: "24h"
});
const initiatives = await env.JIRA.getEpics({
projects: ["TRANSFORM", "DATA-AI"],
quarter: "Q3-2026"
});
app.render(Dashboard, { models, pipelines, initiatives });
AI
Enterprise Data & AI Platform Dashboard is live. Connected via Gatekeeper -- read-only, every query logged.
I see 1 model flagging drift and 1 pipeline with elevated latency. Want me to set up Teams alerts when model accuracy drops below threshold?
I see 1 model flagging drift and 1 pipeline with elevated latency. Want me to set up Teams alerts when model accuracy drops below threshold?
+
Draft an updated AI Governance Policy for our enterprise AI systems. Base it on our current AI standards and the NIST AI Risk Management Framework.
AI
I'll pull from your company's context library to ground this in T-Mobile's standards.
Context Library: AI Governance Standards
Loading T-Mobile's current AI governance policy (v2.1), NIST AI RMF 1.0 framework, and FCC AI transparency guidelines. These are curated by your AI governance team and read-only to the agent.
Loading T-Mobile's current AI governance policy (v2.1), NIST AI RMF 1.0 framework, and FCC AI transparency guidelines. These are curated by your AI governance team and read-only to the agent.
AI
Context loaded. I've identified 3 gaps in the current policy:
1. Missing generative AI usage classification and acceptable use guidelines
2. Model monitoring SLAs not aligned with latest NIST AI RMF
3. Third-party AI vendor assessment procedures need updating for LLM providers
I'll address all three in the updated draft.
1. Missing generative AI usage classification and acceptable use guidelines
2. Model monitoring SLAs not aligned with latest NIST AI RMF
3. Third-party AI vendor assessment procedures need updating for LLM providers
I'll address all three in the updated draft.
AI
AI Governance Policy v3.0 draft is ready. Structured per NIST AI RMF with T-Mobile-specific procedures and regulatory mappings.
You can edit directly, export to Google Docs, or share for review. The document stays connected to the context library -- if standards change, I can flag sections that need updating.
You can edit directly, export to Google Docs, or share for review. The document stays connected to the context library -- if standards change, I can flag sections that need updating.
+
Build a Q3 enterprise transformation review deck summarizing our digital transformation initiatives, AI adoption metrics, and upcoming programs. Pull data from Jira and Confluence.
AI
I'll need access to your project tracking and wiki.
Gatekeeper: Jira (read-only)
Requesting access to the TRANSFORM and DATA-AI projects. Read epics, status, and completion data only.
Requesting access to the TRANSFORM and DATA-AI projects. Read epics, status, and completion data only.
Gatekeeper: Confluence (read-only)
Requesting access to the Enterprise Architecture space. Read pages only.
Requesting access to the Enterprise Architecture space. Read pages only.
Both approved.
AI
Executed code
const epics = await env.JIRA.getEpics({
projects: ["TRANSFORM", "DATA-AI"],
quarter: "Q3-2026"
});
const adrs = await env.CONFLUENCE.getPages({
space: "enterprise-architecture",
since: "2026-07-01"
});
deck.generate(TransformationReview, { epics, adrs });
AI
Q3 Enterprise Transformation Review deck is ready -- 4 slides from live Jira and Confluence data.
You can regenerate anytime to pick up changes, or edit individual slides. Export to Google Slides or PDF when ready to present.
You can regenerate anytime to pick up changes, or edit individual slides. Export to Google Slides or PDF when ready to present.
+
Gadget
Code
Connections
Enterprise Data & AI Platform Dashboard
94.7%
Pipeline Uptime
12
Active AI Models
3.2M
Daily Inferences
47ms
Avg Inference Latency
Active Alerts
Churn Prediction Model -- Accuracy drift detected (dropped from 94.2% to 88.6%). Retraining recommended.
Billing ETL Pipeline -- Processing latency at 12.4s, above 10s threshold. Investigating upstream data volume spike.
AI Model Deployment Status by Business Unit
Customer Experience AI
96%
Healthy
Network Optimization AI
92%
Healthy
Revenue Analytics
89%
Healthy
Fraud Detection
94%
Healthy
Supply Chain Forecasting
78%
Monitor
Churn Prediction
62%
Drift
Billing ETL Pipeline
45%
Delayed
Page
Source
Connections
AI Governance Policy v3.0
T-Mobile -- AI Governance Policy
1. Purpose
This policy establishes the principles, procedures, and accountability structures for the responsible development, deployment, and monitoring of artificial intelligence systems across T-Mobile's enterprise. It applies to all AI/ML models in production, generative AI applications, and third-party AI integrations, ensuring alignment with T-Mobile's values and regulatory requirements.
2. Scope
- All production AI/ML models including network optimization, customer experience, and fraud detection
- Generative AI applications and large language model integrations [NEW]
- Third-party AI vendor systems and embedded AI in SaaS platforms [NEW]
- Data pipelines feeding AI systems (training, fine-tuning, inference)
- Customer-facing AI features (chatbots, recommendations, automated decisioning)
3. AI System Classification
| Risk Tier | Definition | Review Cadence | Approval Authority |
|---|---|---|---|
| Critical | Customer credit decisioning, automated billing, network security AI | Monthly | SVP + AI Ethics Board |
| High | Customer churn prediction, personalized pricing, GenAI customer interactions | Quarterly | VP + AI Governance |
| Medium | Internal productivity AI, document summarization, code assistance | Semi-annual | Director + Data Science Lead |
| Low | Analytics dashboards, reporting automation, internal search | Annual | Team Lead |
| GenAI [NEW] | LLM-powered applications, prompt-based workflows, AI agents | Quarterly | AI Governance + Security |
NIST AI RMF 1.0 -- GOVERN 1.1: Organizations shall establish AI governance structures with clear roles, responsibilities, and accountability for AI system lifecycle management, including generative AI systems.
4. Escalation Matrix
| Role | Contact | Triggered At |
|---|---|---|
| AI Governance Lead | ai-governance@t-mobile.com | All AI incidents |
| Sr Director, AI Governance | K. Bowen | High / Critical |
| SVP, Enterprise Transformation | A. Manchireddy | Critical only |
| Chief Data Officer | cdo@t-mobile.com | Critical + regulatory |
Slides
Source
Connections
Q3 Enterprise Transformation Review
Integrations
Connect external services to T-Mobile OS. Gatekeepers govern access, scope permissions, and log every action.
Gatekeepers
Google Workspace
Gmail, Docs, Sheets, Slides, Calendar, Drive
Microsoft Teams
Chat, channels, meetings, and workflow automation
Jira
Projects, epics, issues, sprints, and boards
Confluence
Read and write wiki pages, search spaces
ServiceNow
IT tickets, change requests, CMDB, and incident management
Workday
Employee data, org charts, payroll, time off, benefits
SAP
Finance, procurement, supply chain, and billing operations
Salesforce
Enterprise accounts, subscriber CRM, and partner management
GitHub
Access repositories, create PRs, manage issues
Snowflake
Data warehouse, analytics, cross-department reporting
Splunk / SIEM
Security events, alerts, monitoring, and correlation data
Power BI / Tableau
Dashboards, executive reporting, and data visualization
MCP Servers
Remote MCP servers available to all workspaces.
Network Operations API
https://netops.mcp.t-mobile.internal/mcp
Auto
Customer Data Platform
https://cdp.mcp.t-mobile.internal/mcp
Needs auth
Billing & Revenue System
https://billing.mcp.t-mobile.internal/mcp
Needs auth
Employee Directory
https://directory.mcp.t-mobile.internal/mcp
Auto
Cloudflare API
https://mcp.cloudflare.com/mcp
Auto
Context
Curated reference documents that ground your agent in T-Mobile's knowledge. Published centrally, read-only to all agents and workspaces.
company-strategy-fy2027.md
T-Mobile's strategic priorities, Un-carrier mission, annual objectives, and key results by business unit
brand-voice-guidelines.md
Un-carrier tone, terminology, customer-facing communication standards, and approved messaging templates
security-standards.md
Security policies, CPNI requirements, FCC compliance, cybersecurity standards, and incident protocols
architecture-principles.md
Enterprise architecture standards, decision criteria, review templates, and technology radar
vendor-requirements.md
Third-party assessment criteria, scoring methodology, and risk thresholds by vendor tier
network-infrastructure.md
5G/LTE system catalog, tower inventory, ownership, SLAs, dependency mappings, and NOC contacts
customer-experience-playbook.md
Customer journey maps, NPS benchmarks, retention strategies, and service standards
network-operations-procedures.md
Network ops workflows, 5G deployment procedures, NOC protocols, and escalation procedures
hr-policies.md
Leave policies, performance review criteria, hiring procedures, and compensation guidelines
financial-reporting-standards.md
Chart of accounts, reporting cadence, audit requirements, and SOX compliance procedures
Skills
| Name | Description | Group | Source |
|---|---|---|---|
| meeting-prep | Scan calendar, gather context from connected systems, and generate briefing docs | General | T-Mobile |
| weekly-report | Compile team activity summaries from Jira, Teams, email, and calendar data | General | T-Mobile |
| incident-response | Draft or update incident response policies grounded in T-Mobile security standards and NIST frameworks | Security | T-Mobile |
| vendor-assessment | Generate vendor security questionnaires and compute risk scores against internal standards | Security | T-Mobile |
| compliance-audit | Gather CPNI and FCC compliance evidence, map controls, and generate audit packages | Security | T-Mobile |
| architecture-review | Build quarterly architecture review decks from Jira and Confluence data | Architecture | T-Mobile |
| change-impact | Analyze change impact across systems, map dependencies, and identify affected teams | Architecture | T-Mobile |
| api-catalog | Discover, document, and visualize internal API endpoints with ownership and health | Architecture | T-Mobile |
| network-health-scorecard | Generate network performance reports from NOC data, tower metrics, and coverage analytics | Operations | T-Mobile |
| cost-optimization | Cloud and infrastructure spend analysis, trend visualization, and optimization recommendations | Operations | T-Mobile |
| runbook-automation | Convert static runbooks into interactive step-by-step tools with automated pre-checks | Operations | T-Mobile |
| customer-insights | Analyze subscriber data trends, churn signals, plan migration rates, and engagement patterns | Support | T-Mobile |
| competitive-brief | Research competitors and generate comparison briefs with pricing and market positioning | Support | T-Mobile |
| ai-model-report | Generate AI model performance reports with accuracy, drift, fairness, and bias metrics | Data & AI | T-Mobile |
| data-pipeline-health | Monitor and report on data pipeline throughput, latency, error rates, and SLA compliance | Data & AI | T-Mobile |
| budget-analysis | Pull spend data from SAP, compare to budget, flag variances, and forecast quarter-end | Finance | T-Mobile |
| job-posting-draft | Draft job descriptions from role requirements, team context, and compensation guidelines | HR | T-Mobile |
| onboarding-guide | Generate new hire documentation from wikis, org charts, and system access procedures | HR | T-Mobile |
Profile
Manage your account details, avatar, and security.
Account
tulin
Click the avatar to upload a new photo
Display name
tulin
User ID
tulin@cloudflare.com
AI Gateway
Visibility and controls across every AI provider T-Mobile uses — one console.
Tokens
342M
Est. spend
$9,120
Cache-hit
27%
Error rate
0.6%
p50 latency
480 ms
Models in Use
This month| Model | Route | Tokens | Spend | Share | p50 latency |
|---|---|---|---|---|---|
| Llama 3.3 70B | Workers AI | 156M | $2,140 | 310 ms | |
| Claude | via AI Gateway | 98M | $3,980 | 720 ms | |
| GPT-4o | via AI Gateway | 61M | $2,510 | 640 ms | |
| Workers AI embeddings (bge) | Workers AI | 27M | $190 | 40 ms |
Spend vs. Budget
9 days remaining$9,120spent of $12,000 cap
76%
On track · ~$2,880 left with 9 days
Top Users
Aravind M.42M tok $1,180
Marcus R.31M tok $960
Aisha L.28M tok $840
Dev K.22M tok $610
Usage by Workspace / Team
342M tokens totalData & AI Platform
121M tokens · $3,240
Platform Engineering
89M tokens · $2,460
Customer Care Tooling
62M tokens · $1,510
Network SRE
41M tokens · $1,020
Security & Compliance
29M tokens · $890
Governance
Guardrails enforced by Gatekeepers + AI Gateway, so the security team can sleep at night.
Per-team allowed models
Restrict which providers each workspace can call.
Monthly spend caps
Hard limits per team; agents stop before overrun.
Data & AI $4,000Platform $3,000
PII redaction
Strip sensitive fields from prompts before they leave.
Enabled
Prompt / response logging
Full request logs retained for audit & review.
Enabled · 90-day retention
Rate limits
Per-team request ceilings to protect budgets.
600 req / min|burst 1,000
Raise Data & AI cap to $6,000
Change queued by an agent — needs a human sign-off.
Requires approval