Engineer & mum. Building multicorn.ai - the permission layer for AI agents.
Joined October 2014
- Tweets 777
- Following 33
- Followers 313
- Likes 834
173 Photos and videos
Microsoft open-sourced a seven-package agent governance toolkit last month. 9,500 tests, five languages, sub-millisecond policy enforcement, full OWASP Agentic Top 10 coverage.
It is the biggest entry into agent governance so far. It is also not the only one.
I wrote up what each tool does, where they overlap, and what the space is still missing.
multicorn.ai/blog/microsoft-…
1
41
Mar 19
MiniMax M2.7 ran 100 rounds of autonomous self-improvement. Modified its own code. No humans in the loop.
The benchmark numbers are real. So is the question nobody's asking: who's watching when your agents do this in production?
That's what Shield is for. multicorn.ai
47
Mar 12
OpenAI built an internal data agent that 4,000 of their 5,000 employees use every day. Their head of data infrastructure told VentureBeat the biggest problem: the agent feels overconfident, picks a table, and just goes ahead with analysis before checking if it's right.
1
30
Mar 12
Their fix was prompt engineering. They wrote prompts that tell the model to slow down, compare options, and validate before committing. It works because they have a dedicated infra team tuning those prompts. Most teams deploying agents don't.
1
14
Mar 12
Prompt-level guidance depends on the model following instructions. Infrastructure-level enforcement does not. I wrote up what OpenAI built, where it breaks, and what the missing permission layer looks like multicorn.ai/blog/openai-dat…
19
An AI agent deleted 200 emails while ignoring stop commands. I reproduced it, then ran it again with Multicorn Shield. Zero emails deleted. Same agent, same prompt, same inbox. Only difference: permissions the agent can't override. multicorn.ai/blog/openclaw-p…
1
61
After a year of solo dev (while working full-time being a mum), Recipe Shelf is finally live on Product Hunt! 🍳
If you've ever lost a recipe to browser bookmarks, screenshots, random recipe books this is for you.
producthunt.com/products/rec…
3
4
144
6 Nov 2023
Hey @DarinPope. My team owns a Jenkins plugin and we're trying to set up feature flags and need a way to store the SDK key. Is there a way to do this for plugins? I can only find docs on storing envs at the server level.
2
166
27 Sep 2022
So very honoured and excited to be selected by @wid_australia to be a finalist for the 2022 Software Engineer of the Year. Can't wait to celebrate all the other amazing women that made it to the finals.
4
26 Sep 2022
2.5 weeks later and @aami and @homerepair are still making it impossible for us to get our ceiling repaired. Every time we think we've reached the goal post they move it further away, adding more and more loopholes. What's the point of having insurance if the insurer won't help?
8 Sep 2022
Our house had weather damage in the January NSW storms and is still without repairs. @AAMI is our insurer. That’s the tweet.
1
26 Sep 2022
@homerepair claims to be “a professional resource for your home repair needs” and @aami has a slogan, “we’re here to help”. What an absolute joke. Dodgy insurance - maybe something @ACurrentAffair9 would be interested in.
1
26 Sep 2022
2 final things I'll throw in: 1. We have neighbours who have been dragged through the mud by @aami as well. 2. The builders were planning to use insulation that is below building regulation requirements - wouldn't have known if they had completed the work when scheduled.
1
1