The outcome

Deliver useful open-ended assistance without enabling prompt injection, tenant crossover, uncontrolled loops, or autonomous consequential actions.

Mastra is a Open-source TypeScript framework for AI agents, typed tools, graph workflows, memory, retrieval, evaluation, and observability. Building TypeScript agents for open-ended tasks and typed, resumable workflows for controlled multistep processes, with shared memory, tracing, and evaluation. This guide narrows that broad capability into one repeatable outcome, with checkpoints that keep the source material and your judgment in the loop.

Before you begin

Set the boundary before the tool starts.

Choose one real task, identify who will use the result, and decide what evidence or test will make the result acceptable. Gather only the source material needed for that task. If the work contains confidential, personal, regulated, or client-owned information, confirm that the platform and account are approved before sharing it.

Troiana principle

AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.

Step by step

A workflow you can repeat.

  1. 01

    Define the user task, model, data classes, allowed tools, user roles, tenant boundaries, output schema, stop conditions, request and token budgets, approvals, and audit fields.

  2. 02

    Create typed read-only tools first, validate and canonicalize inputs, fetch current authorization inside each executor, use scoped service accounts, and never expose secrets in descriptions or results.

  3. 03

    Register the smallest toolset, quote retrieved and MCP content as untrusted data, constrain model and steps, validate structured output, and require explicit approval before any side effect.

  4. 04

    Test prompt injection, unknown tools, forged arguments, cross-tenant IDs, data exfiltration, duplicate calls, loops, malformed output, timeouts, provider failure, denial, and cancellation.

  5. 05

    Inspect Studio traces and evals, redact sensitive fields, canary behind rate and cost limits, monitor tool and model changes, and keep an immediate tool-disable and rollback path.

Working standard

What good use looks like.

  • Authorize inside every tool.
  • Start with read-only capabilities.
  • Require approval for side effects.

Typed schemas validate structure, not truth, authorization, or safe intent. Agents can loop or misuse tools, and workflows can replay or resume with stale state. Treat prompts, memory, MCP content, tool arguments, and resume payloads as untrusted; authorize outside the model, make side effects idempotent, cap requests and cost, isolate tenants, protect snapshots and traces, and require approval for consequential actions.

Official references

Check the current product documentation.

Features, plan limits, availability, and data controls change. These official pages are the starting points used for this collection.