10xGraph blog

Engineering notes

Engineering notes from the 10xGraph team on production AI agents: replay-safe tools, two-tier memory, auth, deployment and release news.

The blog has three kinds of posts. Tutorials build one real use case from an empty folder, with working code that was run before it was published. Engineering notes explain how 10xGraph behaves when things go wrong: a process killed mid-tool, two runs on one thread, a hung node, a stale cache. Release posts say what changed in a version and how to upgrade.

It is written for Python developers who are moving an agent from a demo to a service other people depend on, and for the platform engineers who run it. Every version is listed in the changelog. For reference material, use the docs.

5 min read

A prompt-injected model cannot skip your approval step

How 10xGraph keeps handoffs, tool visibility, tool results and interrupt resumes under the graph's control, so a steered model cannot walk around a human approval.

  • security
  • interrupts
  • human-in-the-loop

4 min read

Logs that are safe to ship

What 10xGraph keeps out of logs, traces and Sentry: hashed user ids, redacted Redis URLs, tool error references, escaped client values and generic errors in production.

  • observability
  • security
  • logging

5 min read

How 10xGraph keeps your customers' data apart

How 10xGraph keeps users and tenants apart for teams shipping AI to their customers: verified identity, roles with reach, 404 outside reach and tenant columns.

  • security
  • authorization
  • multi-tenant

Browse all 15 posts in the archive