Learning center

Understand the control before you connect a model.

Start with a captioned walkthrough under three minutes, read the plain-language basics, or go directly to an operator workflow. Every resource states what works today and what remains your responsibility.

  • Plain-language starting path
  • Captioned product walkthroughs
  • Operator SOPs with current boundaries
Working sandbox capture
Learn from the product you will actually operate.Guides and narrated walkthroughs use sanitized captures from the working sandbox, then connect each control to a concrete operator task.
Choose your path

Start at your level. Finish with a working boundary.

Each path moves from an understandable outcome to the exact setup, validation, and responsibility split needed to use it safely.

New to AI gatewaysPlain language, examples, and first request
Operating the boundaryReliability, budgets, and evidence SOPs
Evaluating the platformGovernance, trust, and portfolio oversight
Topic
18 resources
Video guide3 min video · Beginner
Start here

AI Gateway HQ: the control boundary in under three minutes

Watch the working product turn provider access, routes, failover, policy, hard budgets, managed billing, and evidence into one understandable operating path.

For Potential customers, first-time administrators, small teams, and non-technical decision-makersWatch with transcript
Video guide2 min video · Beginner
Start here

Send your first governed AI request

Follow the shortest safe path from approved model supply to a bounded route, hard budget, one-time workload identity, test request, and reason-coded evidence.

Video guide3 min video · Beginner
Start here

Connect your provider API key safely

Keep one encrypted provider credential at the gateway boundary, verify it without inference, and give applications separate workload identities and approved routes.

Video guide2 min video · Beginner
Start here

Start with prepaid managed Amazon Bedrock

See how purchased credit, a reviewed model catalog, explicit routes, hard budgets, and bounded reloads create a no-provider-key starting path.

For First-time administrators, individuals, small teams, finance owners, and implementation partnersWatch with transcript
Video guide2 min video · Beginner
Cost control

Set a hard AI budget before traffic starts

Set a workspace-wide ceiling, reserve exposure before provider dispatch, and keep managed credit reloads independently bounded.

Video guide2 min video · Operator
Reliability

Configure provider failover without bypassing controls

Build fallback from independent approved supply, remove unhealthy targets automatically, and fail closed when nothing qualifies.

Video guide2 min video · Operator
Cost control

Review and approve an AI cost insight

Move from retained metadata to one exact, version-bound routing change with human approval, audit evidence, rollback, and cautious outcome measurement.

Video guide3 min video · Executive
Governance

Respond to an enterprise trust review safely

See how a bounded inquiry becomes a qualified, owner-approved evidence delivery without exposing sensitive contact or AI content.

Guide11 min read · Executive
Governance

Enterprise AI gateway evaluation: 12 production tests

Use a practical scorecard to compare AI gateways on integration, routing, cost control, security, evidence, and operating fit before live traffic.

For CIOs, CTOs, CISOs, platform leaders, FinOps teams, procurement, and technical evaluatorsRead resource
Guide11 min read · Beginner
Start here

What Is an AI Gateway? A Plain-Language Guide

Learn how an AI gateway controls access, model routing, spending, and operating evidence between your applications and AI providers.

For Individuals, small businesses, executives, and first-time administratorsRead resource
SOP12 min read · Operator
Start here

Run Codex CLI through an AI gateway with Groq

Configure one governed route from Codex CLI through AI Gateway HQ to Groq, then verify model scope, tool compatibility, budget controls, and request evidence.

For Developers, platform engineers, and administrators evaluating governed coding-agent trafficRead resource
Operating brief8 min read · Operator
Reliability

Automatic AI provider failover without silent policy drift

See how health circuits, quota cooldowns, capacity evidence, and bounded fallback keep an outage from becoming an uncontrolled model change.

For Platform engineering, SRE, DevOps, and system administratorsRead resource
SOP12 min read · Operator
Cost control

AI gateway cost control: stop surprise spend before dispatch

A practical control plan for workload ownership, conservative reservations, provider limits, capped reloads, cost-aware routing, and invoice reconciliation.

For FinOps, finance, engineering managers, and account ownersRead resource
Guide9 min read · Executive
Portfolio oversight

Private-equity AI value realization

Connect portfolio-company AI spend, adoption, business results, evidence quality, and operating risk without turning activity into a fictional return.

For Business owners, finance leaders, operating partners, CIOs, CTOs, and portfolio-company executivesRead resource
Operating brief12 min read · Executive
Portfolio oversight

A measurement system for AI across a private-equity portfolio

Separate independent market context from portfolio-owned spend, controls, adoption, and value evidence so operating partners can act without blending company data.

For Private-equity operating partners, CIOs, CTOs, CISOs, and portfolio-company leadersRead resource
Guide7 min read · Executive
Governance

Govern AI without building a prompt warehouse

Use identity, policy, route, tool, cost, timing, and outcome metadata while minimizing retained content.

For CISOs, privacy leaders, risk teams, and platform ownersRead resource
SOP8 min read · Operator
Cost control

LLM cost attribution: reconcile provider bills

Compare provider financial totals with request-level gateway evidence, investigate variance, and allocate cost without uploading the source bill.

For FinOps, finance administrators, platform owners, and portfolio-company operatorsRead resource
SOP7 min read · Beginner
Start here

Use managed Bedrock without bringing a provider API key

Fund a bounded wallet, activate the approved managed model, create a safe route, and stop automatically when purchased credit is gone.