My current dev loop- bug bash or parse calls to pull out requirements and make tickets, run an autopilot skill which attacks entire epics or large groups of tickets, come back to full PRs with evidence (screenshots / vids), auto approval, merge automatically verified in dev env.
@jeffrey_way Systems matter and principles matter. IMO the code itself.. does not matter. Even the systems at some point soon will be trivial for AI to handle at scale. Need to focus our efforts on finding where we still provide unique leverage as humans.
I’m significantly older than you. I started coding in the late 60s. My current strategy is to not read any of the code written by my agents. That’s the only way I can take advantage of their productivity. What I do instead is to surround the agents with extreme constraints. Unit tests, gherkin tests, QA procedures, quality metrics, mutation testing, test coverage, and a plethora of others. In the end, I have very high confidence in the code they produce because they’ve had to run the gauntlet of all of my constraints and tests.
Excited to try this. When I was building an agent platform at my last company I similarly felt there was a need for a workspace for agents. We built something different but I like this approach
Introducing Cursor Router, our intelligent model router that selects the right model for the task at hand.
Router delivers frontier-quality results at 60% lower cost.
Introducing Vendo (YC S26), the customization layer that lets your users build their own features and micro-apps on top of your product
For 50 years, software has been shipped one way for everyone. That era is over.
With Vendo, every user shapes your product into exactly what they need. This is what software of the agentic era will look like. This is Vendo.
One command to install. Open source.
@runvendo@nourzahzah
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
@morganlinton Listen, competition's good, so I'm definitely not discouraging you. I just think, in my mind, when I think of, "Is this model good on real engineering tasks?" I think of DeepSWE right now.