The Praxen blog: self-operating software, observability, and the end of on-call.https://getpraxen.app/enhttps://getpraxen.app/blog/how-to-build-a-memory-system-for-proactive-agents/https://getpraxen.app/blog/how-to-build-a-memory-system-for-proactive-agents/Proactive agents run without a prompt, so each run has to start from what earlier runs learned. How we built memory for Praxen's agents on git: one repository per team, a nightly clean-up, and lessons from merged pull requests.Thu, 22 Oct 2026 00:00:00 GMTBoris TaneEngineeringhttps://getpraxen.app/blog/nobody-reads-pull-request-descriptions-so-we-made-videos/https://getpraxen.app/blog/nobody-reads-pull-request-descriptions-so-we-made-videos/Almost none of the pull requests Praxen opens were asked for by an engineer, and a longer description does not make them easier to review. We are experimenting with a narrated video for every fix. Why, what it looks like, and what happened to merge rates.Wed, 14 Oct 2026 00:00:00 GMTVi TranBoris TaneEngineeringhttps://getpraxen.app/blog/turn-your-app-into-a-context-graph/https://getpraxen.app/blog/turn-your-app-into-a-context-graph/Agents that run software need a context graph of the app: every resource, what it connects to, the repository that deploys it and the team that owns it. How we built one on Durable Objects, keep it fresh across every provider without polling AWS, decide what counts as a change, and delete from it safely.Mon, 05 Oct 2026 00:00:00 GMTBoris TaneEngineeringhttps://getpraxen.app/blog/we-swapped-our-llms-for-jev/https://getpraxen.app/blog/we-swapped-our-llms-for-jev/Our agent makes thousands of small decisions a day. We moved them from LLMs to Jev, a model that doesn't write text, and cut the cost by 39%.Fri, 25 Sep 2026 00:00:00 GMTVi TranBoris TaneEngineeringhttps://getpraxen.app/blog/how-we-prevent-slop-from-hitting-prod/https://getpraxen.app/blog/how-we-prevent-slop-from-hitting-prod/Nothing in your pipeline asks whether a change is safe for prod. This is the check we built that does, and how we got it to finish before your tests do.Mon, 21 Sep 2026 00:00:00 GMTVi TranBoris TaneEngineeringhttps://getpraxen.app/blog/sub-agents-are-just-wrong/https://getpraxen.app/blog/sub-agents-are-just-wrong/Praxen's autofix used to be a workflow of multiple agents, each responsible for a single task, with an orchestrator managing state between them. We moved to a single agent which does the entire job, from evidence gathering, hypothesis testing to pull request.Mon, 14 Sep 2026 00:00:00 GMTAleksandr DiamondBoris TaneEngineeringhttps://getpraxen.app/blog/how-we-fixed-our-cloudflare-durable-objects-memory-exceeded-errors/https://getpraxen.app/blog/how-we-fixed-our-cloudflare-durable-objects-memory-exceeded-errors/Cloudflare Durable Objects run in V8 isolates with a hard 128 MB limit. Ours idled at ~140 MB and was reset ~300 times a day. 130 MB of zod schemas were built at module load, most of them by code that was never called. How we profiled the production bundle, the two fixes, and the numbers, 218 MB to 82 MB and resets to zero.Wed, 26 Aug 2026 00:00:00 GMTAleksandr DiamondBoris TaneEngineeringhttps://getpraxen.app/blog/proactive-agents/https://getpraxen.app/blog/proactive-agents/Agents can do almost anything you ask. That's the problem, you still have to ask. The next evolution is agents that figure out the job to be done. I started with operations, because nobody should be on-call in 2026.Sun, 05 Jul 2026 00:00:00 GMTBoris TaneIdeas