Plane Agents join your workspace as members. Assign them work items, tag them, trigger them when work changes, or run them on a schedule. They triage requests, draft specs, run standups, flag delivery risks and a lot more. Agents run on the AI credits included in every paid plan.
You can now add an agent to your Plane workspace the same way you'd add a team member. It gets a name, a set of projects it's allowed to work in, and work assigned to it like anyone else.
What an agent is made of:
• A playbook, which is the plain-language description of what it's responsible for and how it should go about it
• Skills, which you build yourself and attach to an agent. A skill is a reusable way of doing a specific job, so once you've defined one, any agent you give it to can do that job the same way
• Tools, connected over MCP, which let it reach systems outside Plane when the job needs it
• A scope, which is the list of projects it can act in and nowhere else
• Triggers: you assign it a work item, you mention it in a thread, or you put it on a schedule and it runs on its own
• Memory, so it carries context between runs instead of starting cold each time and updates after each run.
What it can do with that: read and update work items, create new ones, comment, tag, move work between projects, and post summaries back to the team. Triaging incoming requests, running a standup, drafting a spec from a rough note, watching for work that's stalled. If a person can do it inside Plane, an agent can be given that job.
Every action an agent takes shows up in the same activity history as your team's. And agents use the AI credits already included in paid plans, so there's no separate subscription and no per-agent seat.
Very excited for everyone to try this out, we have a generous free tier to experiment with.
i can already think of a few repetitive workflows i'd happily hand over to an agent, reallyyy looking forward to seeing where it goes!!
My devs are going to lose their minds if a bot starts messing with their ticket tags so how do I introduce this without a riot?
No extra seat fees sounds awesome but I'm just waiting for the catch how fast do you actually burn through the included AI credits?
Been waiting for this one. The fact that agents can be assigned work directly is what I’m really excited to try 🚀
The idea of agents joining a workspace like team members is genuinely interesting. Great launch!
The reusable skills part stood out to me. Teach an agent a process once, then reuse it across different agents. That could be really useful for my team workflows 🚀
I like that Plane Agents can work from the same projects, work items, and docs we already use. There is a lot of repetitive upkeep around all of that, so having an agent take some of it off the team’s plate would be a big help.
Wow, just tried it and I am honestly loving this! 😄 Being able to get through my day with agents handling things feels pretty amazing. Now I just need an agent squishy ball on my desk to make it feel even more real 😂
Really nice work! Thanks for giving me a whole squad of cute little agents. ❤️
Half the feedback I get is basically a screenshot and “this looks off.”
I’d probably use an agent to clean that up into an actual work item with the URL, repro steps, and priority. Memory will be useful too, mostly so it doesn’t keep treating the same page or component like it’s brand new every time.
This is going to serve so many use cases for me personally. Can't wait to get my hands dirty with it. Go, team Plane 🚀
Giving agents real work items, triggers, and schedules is a smart direction. Congrats Plane team!
Excited to see what all i can do with agents. The workflow looks really promising.
About Plane Agents on Product Hunt
“Assign work to AI agents, like any teammate”
Plane Agents launched on Product Hunt on September 22nd, 2026 and earned 111 upvotes and 15 comments, placing #8 on the daily leaderboard. Plane Agents join your workspace as members. Assign them work items, tag them, trigger them when work changes, or run them on a schedule. They triage requests, draft specs, run standups, flag delivery risks and a lot more. Agents run on the AI credits included in every paid plan.
Plane Agents was featured in Productivity (661.3k followers), Task Management (84.3k followers), SaaS (44.3k followers) and Artificial Intelligence (479.2k followers) on Product Hunt. Together, these topics include over 353.4k products, making this a competitive space to launch in.
Who hunted Plane Agents?
Plane Agents was hunted by Devanshu Arora. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Plane Agents stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Hello everyone. I’m Vamsi, the creator of Plane.
We're excited to launch Plane Agents today.
You can now add an agent to your Plane workspace the same way you'd add a team member. It gets a name, a set of projects it's allowed to work in, and work assigned to it like anyone else.
What an agent is made of:
• A playbook, which is the plain-language description of what it's responsible for and how it should go about it
• Skills, which you build yourself and attach to an agent. A skill is a reusable way of doing a specific job, so once you've defined one, any agent you give it to can do that job the same way
• Tools, connected over MCP, which let it reach systems outside Plane when the job needs it
• A scope, which is the list of projects it can act in and nowhere else
• Triggers: you assign it a work item, you mention it in a thread, or you put it on a schedule and it runs on its own
• Memory, so it carries context between runs instead of starting cold each time and updates after each run.
What it can do with that: read and update work items, create new ones, comment, tag, move work between projects, and post summaries back to the team. Triaging incoming requests, running a standup, drafting a spec from a rough note, watching for work that's stalled. If a person can do it inside Plane, an agent can be given that job.
Every action an agent takes shows up in the same activity history as your team's. And agents use the AI credits already included in paid plans, so there's no separate subscription and no per-agent seat.
Very excited for everyone to try this out, we have a generous free tier to experiment with.
Live on Plane Cloud now: plane.so/agents