Viewing profile — rajit

It is possible to do it (ex: run a background process that analyzes memories across customers and updates the system prompt based on the findings). A specific implementation would …

Yes by using us developers are deferring the harness engineering onto us, and they can spend time writing code for their business logic. We are closer to infrastructure than a libr…

Good question. There a few differences between our approach and shipping an agent with the Claude agent sdk. 1. Our approach has cron-based or trigger-based automations built-in. B…

Developers with customer-facing chat products are the ideal customer. If a startup has a specific flow they want the agent to take and their traffic is bursty, then I'd recommend u…

> what are the cost and security implications? Cost is the token usage and container uptime. > One Docker container per-customer sounds like it would be really expensive. The advan…

The most valuable pieces of information an AI agent startup can gather is access to their customer's proprietary data and knowledge of their customers preferences (memory + self-le…

Thanks for the feedback. The main idea is that today to built a best-in-class agent, developers build the agent loop, session management, tools, memory, skills, automations (cron +…

when will the graph memory layer be available?

Yes, email me at rajit@prismvideos.com, and I can connect you. Their pricing page is here https://fal.ai/pricing .

Prism and Higgsfield are both similar in that we bring many AI models into one place. Higgsfield is focused on a number of different use cases - storyboarding, ai filmmaking, and v…

We support Kling 3.0 on our platform, similar to Higgsfield. You can see some presets here: https://prismvideos.com/workspace/templates .

This is a great point, and I agree with you. If a weight loss supplement brand were to use an AI influencer to market their product, it does raise questions about whether their sup…

This is a great point. It is challenging to know which models are good at what. We've found that Seedance is good at photorealitic faces, Kling is fantastic at generating audio (hi…

We access models through Fal ( https://fal.ai ). We offered day 0 support for Kling 3.0 and launch models on our platform the day they are live. Would be curious to see your script…

[dead]

How do you identify "wrong tool" invocations (how is the "wrong tool" defined)?

We spoke to a number of browser agent companies who said deterministic RPA with an AI fallback was their "secret" :)

Code Compass is an AI agent that helps engineers determine the best task to work on next, given the codebase context from the engineer’s current task. - Code Compass indexes a GitH…

This is a great point. I'm assuming when you mention blast radius you're mentioning the risk of the account being banned for being a bot. One risk with these new standards for agen…

Feel free to reach out. I'm rajit [at] prismai [dot] sh.

We setup an agent mailbox with Agentmail ( https://agentmail.to/ ). Whoever owns the account (likely the developer) sets up a forwarding rule to this account. When our agent signs …

We enable stealth mode on Kernel (onkernel.com), which is a great piece of infrastructure.

This is a great question. We are broadly interested in the agent access problem (which in some cases may involve solving Captchas). Right now, we're focused on building connectors …

It's a pleasure to work with you. Excited to expand to more login cases and support login to more websites.