Blog

Notes from building an agent runtime.

Engineering deep dives, product updates, and field reports from running teams of AI agents in production.

EngineeringMay 14, 20268 min read

Designing checkpoints for resumable agent workflows

Long-running agent runs fail in the middle. Here's how we model checkpoints so a 30-step workflow can resume from step 18 instead of starting over.

Read article →

Product6 min read

Human-in-the-loop, without stalling the run

Approval gates and ask-for-input tools let an agent pause for a human and pick up exactly where it left off. A look at the pause/resume model behind it.

May 2, 2026

Product5 min read

What counts as a workflow step (and why we meter it that way)

Usage-based pricing only works if the unit is honest. We break down what a step is, how it's measured, and how to keep runs predictable.

Apr 21, 2026

Engineering7 min read

Debugging a multi-agent run like a stack trace

Per-step traces turn an opaque agent loop into something you can actually read. A walkthrough of the trace format and the questions it answers.

Apr 9, 2026

Product9 min read

Bring your own connectors: Gmail and Salesforce in a workflow

Agents are only as useful as the tools they can reach. How BYO OAuth connectors let a crew act on your real systems, with tokens encrypted at rest.

Mar 27, 2026

Engineering6 min read

Routing steps across models without rewriting your workflow

Not every step needs your most expensive model. How per-step model routing trims cost and latency while keeping the same workflow definition.

Mar 12, 2026

Get new posts in your inbox

Occasional updates on the product and what we're learning. No spam.