AI Agent Crash Recovery: Why Durable Execution Still Creates Duplicates
Watch now (28 mins) | What AI engineers and AI Forward Deployed Engineers should understand before an agent writes to a customer’s system twice.
Read the issue →A gated home for the good stuff: talk recordings and slide decks, every newsletter issue, the full event archive, and the playbooks we've shipped. Free for subscribers. Unlock it with your email.
Talk recordings, slide decks, event archives, and downloadable playbooks, free for subscribers. Drop your email to unlock the full channel.
Already subscribed?
Free. No spam. Unsubscribe in one click.
The full archive of talks from our meetups, abstracts, slide decks, and recordings as they go up. Browse the people behind them on the speakers page.
Beyond the problems of accuracy and cost, AI agents are challenged by long-running execution processes, human-in-the-loop approval logic, non-deterministic call paths, and upgrade…
Once agent and workflow state live in your database, three questions become sharper: what happens when a database server goes down, what happens when the fleet grows 100x, and how…
Opening the build night: The AI Runtime, the format for the evening, and what a good show and tell looks like.
The featured talk of the build night: how builders use Apify actors to give agents live web data and real tools, setting up the hands-on workshop that followed.
AI has reshaped individual productivity. We write, research, code, and ramp up faster than ever. But collaborative workflows haven't kept pace. Teams still run on pre-AI processes…
AI is no longer just a tool for automation. It is becoming an active teammate in the software development lifecycle. By embedding AI into daily workflows, teams can reduce time…
Everyone can now build impressive AI demos in a weekend. Almost none of that work ever makes it into production at a real organization. This session walks through the three…
As AI agents increasingly become first-class actors on the internet, every existing auth model breaks down, they all assume a logged-in human at the start of the flow, but agents…
Practitioner-grade resources we've built. Subscribers get them first. See all resources →
A guided reading path through The AI Runtime for AI practitioners. The essential reads on AI engineering, Model Reliability Engineering, and vertical agents, in the order that builds real production intuition. Free download, no email required.
A practitioner-grade checklist for agentic system design, identity, trust, tool access, eval coverage, observability, and the failure modes that take down production agents. Free PDF for subscribers.