Agentplace AI Agents - Create specialized AI agents for real tasks and workflows

@ermakovich_sergey Thanks! Good question. On our side, we have internal benchmarks for the Builder agent, so when a new model drops we can test and adapt pretty quickly, usually a day or two. As for the agents users have already built, we don't remove access to older models, so everything keeps working as before. If a user wants to switch to a newer model, we'd recommend testing it on their end to make sure things behave as expected. But nothing breaks automatically.

@ermakovich_sergey, adding to Boris's comment, you can connect any eval tool to enable a controlled change.

@ermakovich_sergey Thank you for support us!

@jean_bonnenfant2 Thank you! I know I know I'm biased but my favorite one was a Christmas agent with ElevenLabs voice that we made in team internally. You pick a character like Grumpy Santa or Hip Hop Elf, it talks to you in real time, roasts you a little, and makes a personalized postcard you can send to friends :)

For more serious stuff, there's a competitor researcher agent that goes out, gathers intel on your competitors and comes back with a positioning brief ready to use

@jean_bonnenfant_tinct means a lot! Honestly, some of the most fun ones are the weird playful agents people build first, and then a lot of them end up turning into something surprisingly useful.

@elv1s42 Thanks a lot we felt it was important that people can actually try it before committing.

@elv1s42 Thank you, we really wanted people to be able to try it properly before paying for anything!

@athsara Agentplace can plug in natively, so no need to adapt. That being said, AI is a different animal, and we found that to use it to its full power, the process should be different and in many cases simplified.

@athsara Each agent is also an MCP server so you can just make a small one that does one thing and plug it into what you already have. Or if MCP doesn't fit you can add custom API endpoints since it's a full Node.js app under the hood. Either way you don't need to rebuild anything

@systerr  @tim_ep1 Thank you so much, would love to hear what you think once you’ve had a chance to try it.

@tim_ep1 Thank you. Hope you will enjoy it! Feel free to reach us on any questions!

@mykyta_semenov_ We’re much more focused on this idea of AI teammates inside a shared workspace.

Where agents actually run work end-to-end, coordinate with each other, and people stay in the loop to guide and make decisions.

Feels like the real unlock is not trading agents, but making them actually useful in daily workflows.

@mykyta_semenov_ That’s a fair first impression 🙂 We’re focused right now on helping people create and improve agents for real workflows

@shalini_umrao Thank you for bringing this up. That's actually who we built this for. The whole point is that an ops person can build and update agents on their own. There's no code to write, you describe what you want the agent to do in plain text, test it in the same window, and hit publish. If something needs fixing you just open the editor, change the prompt, test, publish again. No pull requests, no deploys, no waiting for engineering

@shalini_umrao Exactly. If every small change needs engineering, adoption usually stalls.

@ikalimullin Thank you, that means a lot. That’s exactly the direction we’re aiming for: agents that actually help with real work, not just something fun to try once.

@ikalimullin That’s our goal. It becomes super easy to use if you can interact with it in the same way you interact with humans. And you can expect the same things, plus more: 24/7 work, bigger short term memory, and no fatigue.

@ikalimullinThanks really glad it comes across that way. That’s exactly the bar for us.

@mssulthan Thanks a lot! Really happy to hear it feels easy to use and launch.

@mssulthan Really glad it feels easy to get started with.