
Product & Engineering @BetterStackHQ, the company with the best MCP server. Stop micromanaging your agents.
Prague
Joined October 2015
- Tweets2.5K
- Following1.1K
- Followers234
- Likes7.5K
Simon Let retweeted
opus 5.5 is incredible
i know the models are gonna get better than this, but man, it really feels like it can do anything
i would be too embarassed to post this
Background subagents in Claude Code now use less of your usage limit.
A running subagent updates its status line every 30 seconds, and each update used to re-read its whole conversation. Now Haiku 5.5 writes it from short notes instead, so each update costs about 99% less.
53
i'm not big on using skills made by others but i did steal /merge-risk from @mattpocockuk. it's great.
the only AI skills repositories I personally endorse are @mattpocockuk and @poteto
99% of skill repos are slop which doesn't hold up to even the barest of evals or even common sense, but those two are doing great work you should pull into your own setup
54
are you still copy-pasting errors and incidents to Claude? good news, you can stop now.
auto-fix your errors and auto-investigate your incidents. get ready-to-use prompts in the post ↓
This just in: Better Stack AI SRE now works right inside Claude
Add a Claude scheduled task that checks your errors in Better Stack every 4 hours and fixes the obvious ones with pull requests. It runs in Anthropic's cloud, so you can close your laptop and merge the pull requests later from your phone. 📲
How to set up: betterstack.com/docs/getting…
1
1
88
Simon Let retweeted
"Agents aren't good at this thing I'm working on"
Then why are you working on it?
Simon Let retweeted
I don't think writing a spec and splitting it into tickets is how you should use agents since Sol 5.6/Opus 5. Just tell the agent what you want to do and it will do it.
If the task is large, discuss with the agent how to split it in several shippable PRs and do it one at a time.
mattpocock/skills v1.3 is out!
- /pr (new) writes easy-to-read PR bodies, showing hard evidence that the changes work and assessing merge risk
- /implement-spec (new) takes in a spec and tickets, and implements them with subagents
- CONTEXT.md renamed to GLOSSARY.md
- /retro (new) reviews recent coding agent sessions and suggests repo improvements
/retro, especially, feels like a huge upgrade. Enjoy!
Simon Let retweeted
We unfortunately have decided that we cannot continue providing access to our models through Cursor and are ending our partnership. It boils down to trust and we’ve asked that this takes effect on November 12 to give you some time to plan.
Many have used the GPT models through Cursor and here are options we know should work in the future:
- We will continue to allow using your own OpenAI API key and similarly will continue to provide access through our IDE extensions for Cursor.
- We will keep working with the broadest range of tools and harnesses, some of which are OSS, but also many many closed-source ones.
We are as committed as ever to continue supporting developers and the flourishing ecosystem of tools, harnesses and products. We will also continue to invest in our own open-source initiatives and believe in broad optionality for developers.
You can read more about our decision in the blog:
openai.com/index/our-decisio…
We’re ending our partnership with Cursor following its acquisition by SpaceX. Under our proposal, Cursor’s direct access to our models would end on November 12.
We know that the people most affected by this decision are the developers who rely on OpenAI models in Cursor. We care about their experience in this transition and we’re ready to go above and beyond to support them.
openai.com/index/our-decisio…
extremely eye opening how much worse every model performs in chat vs in code
no agetic harness
poor prompts
->
recipe for disaster
1
118
Simon Let retweeted
I've started a new company: @superlogical! We're going to begin by building a terminal multiplexer. The entire vision is much larger, but the multiplexer is the foundation. Sign up for the newsletter to get beta access and devlogs (product updates only I promise).
superlogical.com/
why does someone still uses @datadoghq in 2026 - there event based pricing is absolutely ridiculous.
we got ~500$ bill for a month, where we recorded ~168 million of logs and it was just about 40gbish.
I shifted our whole logging infra to @BetterStackHQ , took <1hr, our last month bill was ~45$.
and betterstack mcp is such god tier, datadog mcp is also bad.
Simon Let retweeted
There's no full-window "Chat" mode in the new ChatGPT app for Mac. Don't upgrade.
Come chat about observability, eBPF, automated AI incident resolution, and everything in between.
We're heading to WeAreDevelopers World Congress Europe!
If you're in Berlin on July 9–10, stop by Hall 2, Booth 27, to see a radically better approach to observability for modern engineering teams. Meet the team, catch a live demo, and grab some swag.
#WeAreDevelopers #wearedevs #observability
1
73
MCP's still carry SO much friction
i want to
1) ask my agent to "integrate tool X"
2) hand it a token
-> start using X
no session restart
no /mcp command that my agent can't use directly
this is why i just run with API's 99% of the timef
1
44

















