Skip to content

Learn · Track

Running AI in production

What changes when agents leave the laptop: which gateway governs which traffic, how to keep model spend under a cap, what you run when you host the platform yourself, how long to keep personal data and how to erase one person's, how to prove what an agent did, and who may build, run and approve. It helps to know how an agent loop works first.

New to agents? Start with What is an AI agent?

Guides in this track

Intermediate6 guides, in reading order

  1. LLM gateway vs MCP gateway

    An LLM gateway sits between apps and models; an MCP gateway sits between agents and tools. What each controls, where they overlap, and when you need both.

    7 min read

  2. LLM and agent cost control

    Why agent costs run away (loops, long tool lists), where to put spend and token budgets (user, project, client), warn vs block, and estimating usage.

    7 min read

  3. Self-hosting AI agents

    What a self-hosted agent platform runs (API, workers, database, models), the trade-offs against hosted tools, and a checklist for a first production setup.

    6 min read

  4. Data retention and erasure

    Where an AI app keeps personal data, how retention purges it, how to answer access and erasure requests, and how legal holds stop deletion.

    9 min read

  5. Audit trails for agents

    What an agent audit trail should record (inputs, tool calls, approvals, versions), how a signed run manifest proves it is intact, and offline checks.

    9 min read

  6. Identity for AI platforms

    Who may build, run, approve and call agents: single sign-on with OIDC or SAML, MFA per role, project roles, service accounts and scoped API keys.

    7 min read

This website (not the L2M product) uses Google Analytics, only after you accept cookies. Cookie settings