Ready to move your coding agent workflows to the cloud?
Here's an open source software factory you can self-host on @render!
The repo also demonstrates how to build secure, production-ready agentic applications.
Fork it, bring your own agents, and extend with custom flows!
Jacob Prall retweeted
Prompt of the day:
Let's assess the XState v6 beta.
1. Research what it does and the problem it solves.
2. Find the gnarliest problem in our application that it might assist with
3. Create a proof-of-concept implementation in a draft PR
4. Fully verify the results
5. Grade it on:
5a. How much nuance there is in the API (more is worse, agents perform better with fewer choices)
5b. How typesafe it is
5c. How easy-to-test it is
5d. How much cyclomatic complexity it introduces
5e. The quality of docs provided
5f. What changes to deployment will be needed
6. Give me your overall recommendation
Drop in a technology you're interested in, and see if it's any good
Giving a talk at the AI Engineer Code Summit on refactoring in the era of coding agents.
If you’re in town, would love to see you there and trade notes!
1
20
Jacob Prall retweeted
Folks, I’m growing the DX team at Render!
I’m hiring 4 super talented people to build cool projects and get developers (and their agents) excited to ship on Render too.
The roles:
- Developer programs lead
- DX Engineer
- Developer Relations Engineer
- Content Engineer.
Remote or in SF office.
Links in 🧵
If you're at @WeAreDevs in San Jose today, stop by the Render booth for cool swag and cooler conversations with our DX team about hosting your AI and agent workloads.
Come check out the @render booth at @WeAreDevs and chat with the DX team today and tomorrow!
Agent workloads are unpredictable by definition. Is the next request 3 tasks or 400?
Provisioning compute assumes you know the answer.
Our answer is Application-Defined Compute. Render CEO @anuraggoel explains it tomorrow at @WeAreDevs. 11 AM, Stage 1.
Find us at booth #734 after.
Research agents split complex questions into multiple subtasks. But what happens when a branch fails?
Our latest open-source template uses @p0 's Search and Extract to research topics in parallel, fanning out subtasks on Render Workflows to provide isolation and retries.
The agent synthesizes successful results into a cited report.
Deploy with one click → render.com/templates/paralle…









