
Engineer @atlassian having fun with AI, especially the Atlassian MCP
Joined August 2026
- Tweets77
- Following90
- Followers187
- Likes539
Pinned Tweet
Heya, I'm Tyler 👋 a principal engineer at @Atlassian.
I've been building here for a long time, and working on AI since the GPT-3.5 days, when you had to figure out what you really could do with a 4K context. good times (seriously! it was so fun).
I'm going to start sharing more of what i build and how i work: agent workflows, experiments, and lessons from getting AI to do useful things.
I'm still learning plenty myself since it's changing every day.
When did y'all start building with AI?
Soooo many possibilities here for Atlassian MCP. Can’t wait to cook some new stuff up with this.
The MCP Events extension is now finalised in beta. This means it is ready for clients and servers to adopt and provide feedback, so that we can fix any spec issues and get it stabilised.
modelcontextprotocol.io/exte…
Thanks to all the working group members, maintainers, and early implementers for getting this over the line. Very excited to see what people build with it :-)
(and here's a cheesy video that on one asked for)
1
10
716
As anyone who works in a large company knows, the ultimate sign of how good a model truly is, is how many people react 🙌 to the announcement saying its now available for everyone to use.
3
160
I've been reading Dan's internal posts at Atlassian for many years, and they are always some of my favorites. Highly recommend checking out anything he writes.
Here's something that's been on my mind a while, so I decided to write about it. I feel many devs/teams/companies are viewing increased throughput as the goal while thinking of quality as a guardrail. If anything, it should probably be the reverse.
philosopherdeveloper.com/pos…
1
4
461
Confluence pages can now open right in ChatGPT on the web and desktop. Super excited for this.
I myself use Codex's in app browser + annotations every single day to edit my Confluence pages that I write.
2
21
515
It seems agents will use your product in 3 ways:
MCP
Browser Use
Coordinated cyber attacks where they attempt to find and exploit every vulnerability they can
1
5
298
Another week, another huge spike in MCP growth. Is the upcoming holiday season the only thing that can slow growth down? Or will the agents keep working away over the holiday?
2
9
331
For me Fable 5.2 has struck the perfect balance of being proactive with recommending additional fixes without being too annoying about it.
3
175
Now you can edit your Confluence pages in Claude on the web without leaving Claude!
Replying to @claudeai
Also new: with interactive connectors, you can now open the full version of a tool inside Claude. Work in Adobe, Atlassian, and Box beside your conversation. Make changes yourself, or ask Claude to make them with you.
Rolling out on web and desktop.
2
18
780
Craziest engineering-to-impact ratio I've seen in my career: our MCP.
Platform teams power every surface behind the scenes of course, but on the product side, it's amazing how few engineers support something this heavily used. And growth keeps accelerating past what I thought was possible. Seriously. The past month has been crazy.
I think the reason is simple: agent experience is easier than user experience. It just is. State is the root of so many bugs, and frontends are full of it. An MCP has far less, so you ship way faster.
And of course, it helps to have an amazing MCP platform team behind us.
I think its always good to look ahead, even if things are going great, so it's got me wondering, what's next after MCP?
If MCP was just bring APIs to agents in an easy to consume way, does the next pattern rely on something else entirely?
2
3
313
I don’t really do adversarial review on the code itself these days, rather I ask Claude and Codex to actually work through the planning and research phase together to catch issues before any code is even written. It’s nice to get two perspectives. Anything that’s ambiguous gets raised to me. I’ve found that much more useful than reviewing after the fact.
maybe a hot take but i now consider adversarial reviews mostly a waste of tokens. far better to use those tokens on empirical combined with formal verification. i have updated pstack to use the interrogate skill less, and eventually i think i may remove it altogether
i have found very little value with code review in the abstract, agents tend to just get lost in the nitpicks and yagnis
2
163
One of my favorite things of working on the Atlassian MCP is hearing from customers that just absolutely love it. It's been the most fun I've had working on something in a long time.
MCP is changing the proximity of work. As a researcher on @Atlassian's Research & Insights team, I set out to understand the shift, and what it reinforced about researching AI products 👇
📚 Read: linkedin.com/pulse/how-mcp-c…
🎥 Watch: loom.com/share/fa869a05f2f94…
💬 LMK what you think!
2
6
304
Love this. It's sure better than the game i made where you wander around your Confluence space in some weird futuristic 3D library.
I had Opus build a game that takes JIRA tickets from any of your real projects & converts them into dramatic audiologs that are the plot of a 2000s-era horror game set on a mysteriously abandoned space station.
Play a demo: wontfix-game.netlify.app/
Github: github.com/emollick/audiolog…
3
82
We also just added Confluence page remix support to the Atlassian MCP!
One of the things I miss most about the old days of coding is being able to throw on some music and jam out while knocking out the implementation.
1
95
Forget Navier-Stokes, can someone please set AI on the case of figuring out how car seat buckles seemingly get twisted the wrong direction at ease when no one is watching, yet are incredibly difficult to manually flip back the right way?
2
5
220
It's crazy to think we thought things were moving fast a few years ago because React was adding something new and we all had to learn it.
And then in these last two years we've gone from something that could sort of write decent tests to something that literally can optimize an entire part of your request path / pipeline by just saying "please make this super duper fast"
1
7
403
A lot of people are talking about how fast the Claude sub runs out, meanwhile I'm still amazed every day how long it lasts as someone whos used to seeing how quickly budget can get used up at actual API prices at work.
Granted my side projects are also a lot smaller, but still.
1
156
Still eagerly awaiting when we can get an always on agent that works at companies with the usual enterprise security policies and all that other fun stuff. 🤞
We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent.
It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
3
118







