We strongly believe that the future will be orchestrated, and in that future harnessing the multi agent workflows will be crucial. But yes, sometimes simple solutions work.
Verdent Deck (the desktop app) could be considered as a recommended way to start. You can have multiple agents run in parallel, code review, code diff explained, etc. Then if needed you can jump into VS Code and work on specific parts with our extension.
Thansk for the comment. Planning and verifiability is crucial for any serious coding task. Through our early access program we have been providing free credits and we have used that insight to structure the pricing plan. ATM we are not offering free plan as we are focusing all of our efforts to create the best possible experience for engineers.
Thanks for explaining this! I just think of a new developer experience that wants to try out Verdent and pay after. I usually do not pay for a tool that I have not tried and see what it does. Showcasing content or demos is not enough. Take the example of Lovable, they offer 5 credits to send few prompts and if you want to continue, you need to pay.
Thanks for sharing. I’m Zhijie Chen, founder of Verdent and formerly Head of Algorithms at TikTok. Verdent is built for larger, production-grade tasks: it plans before coding, runs agents in parallel, tests results, and explains diffs. Our north star is a full Plan Code Verify loop, and we are building toward that. Curious what kinds of tasks you would actually trust an AI to handle end to end.
Do you have a benchmark of how many tokens Verdent agents can save for complex asks? For example, I stopped using Cline because it consumes quite a lot of tokens for bigger projects just to analyze and provide context.
Hi, atm we can say that it's moderately less than Cline but we need more testing to give exact numbers. We have plans for testing by users and 3rd parties in future, for full transparency.
