Ask anyone at your company why they do something that way. Most of the time the honest answer is “I don’t know, it was like that when I joined.”
The person who knew left. The reasons left with them.
I’ve seen it in code.
A setting says “wait 5 seconds, retry 3 times.” Nobody knows who picked that or why.
It’s the same everywhere else: a pricing rule, a refund policy, a step in a process that everyone follows and nobody can explain.
And now people ask an AI. It never says “I don’t know.” It gives a smooth reason that no one ever said, and the team starts believing it.
I think that’s worse than having no answer.
So for the Flip the Switch hackathon I built Whylog. It’s three AI helpers in one team chat, on @switch_ai_ :
One writes down each decision while it’s being made, and marks anything nobody said as “not stated.”
When I said I was leaving, it found the gaps in my notes and interviewed me before I went.
The third answers questions only from those notes.
Then I asked it something we never wrote down: why didn’t we use a message queue?
“This was not recorded.”
No guess. No invented reason. A tool you can trust is one that tells you where its knowledge ends.
What I didn’t prove: it ran on one computer, and I played the engineer myself. The people and reasons in the demo are made up.
What was rough in Switch: setup shows a time-out error while it’s still working, and the helpers take 30 to 90 seconds to reply.
Video below.
#HowISwitch @WeMakeDevs
✨IbnWeb3👑 retweeted
I asked an AI agent a question no single dataset can answer. It went and found the data itself.
This is Fieldwork, my solo build for the #OpenAgentHackathon by @GenAI_Now .
My track
Track 1: Solving Fragmented Intelligence.
The problem:
Ask "which Montgomery neighborhoods have high asthma rates and a lot of housing code violations?" The asthma data is on the CDC site, the violations are on the city portal, the neighborhood map is from the Census. No one has that table.
What Fieldwork does:
You type the question in plain English. It searches public data portals live, connects the sources through @Zetaris without copying any data, checks they really match up, and answers on a map. Every number links back to the real rows it came from. If the data doesn't exist, it says so.
In the demo I also point it at Louisville, a city it had never seen. It found the sources and answered in 92 seconds.
What I enjoyed most:
Seeing my work help the sponsor directly. While building, I hit data sources on Zetaris's own "known to fail" list, so I fixed them and sent pull requests. Both were merged by Zetaris's CTO:
- PR #36: Singapore air quality, now working
github.com/zetaris/gettin…
- PR #39: CDC health data + Census maps, added as new sources
github.com/zetaris/gettin…
"Super helpful… always great to add another confirmed data source into the set of known to work."
After the hackathon I kept going. Using the @cursor_ai agent, PR #43 (merged this week) took the known-to-fail list from 6 sources to 1
github.com/zetaris/gettin…
I also had the Cursor agent check Fieldwork's answers. It used only Zetaris and never saw Fieldwork's answers. On 5 of my questions it got the same numbers on 4, and the same top 5 on the last, with a few counts off by 1 or 2.
Tools that made the biggest difference:
- Zetaris: one SQL query across live CDC data and my own database, with every answer saved back as a reusable view
- Meterless engines: H-MEM so the agent remembers which sources worked, World Model to track each run, Scout Intent to block poisoned source text
- @nvidia Nemotron: writes the SQL and the answers
What I learned, and what I'd do differently:
Testing beats demos. On 25 real questions my first full run passed 12. The final run passed 25 of 25, about 47 seconds per answer. The same AI model on its own answered 0 of 20; Fieldwork answered 18. Next time I'd start that full test on day one, not day three.
Thank you @GenAI_Now , @Zetaris and Meterless for a great week📌🔥
Try it: askfieldwork.space
Code: github.com/Jennycruzy/fie…
Montgomery, Alabama's neighborhood data is spread out. Code violations and 311 requests are with the city, health data with the CDC, and boundaries with the Census Bureau. None of it lines up.
So I built Fieldwork for the @GenAI_Now Hackathon Track 1; Solving Fragmented Intelligence
Ask a question in plain English. Seven agents find the right public data, join it in @Zetaris , and check every number before you see it. Click any figure to see the record behind it.
What it found: 10 of Montgomery's 71 tracts hold 48% of 2025 code violations.
It scored 23 of 25 on a fixed test, and every run is published. The same model without the agents answered 0 of 20.
Built with @nvidia Nemotron, Zetaris and Meterless.
Try it: fieldwork.38-49-216-59.sslip…
it has been a busy week ngl.. i am building an idea for the swich hackaton..
it is simple but a bit tricky to setup haha..
GmGM
✨IbnWeb3👑 retweeted
This Monday, you could win an iPhone Duo worth $2,000! 📱🔥
Just take a quick 1-minute survey about how you use AI to enter the giveaway.
Take the survey here: forms.gle/xHFL98C88C9mmwQN8
✨IbnWeb3👑 retweeted
Playground is live on Xavainf.
Get access to 230+ Models using One key.
Motion Design video for @XavaInference
This was designed using After Effects.
SFX pack - Botanica
✨IbnWeb3👑 retweeted
Theft doesn't always begin with a stolen key. It can begin when an agent treats access as permission.
That is the problem Assertara is being build to address.
Assertara investigates actions proposed by autonomous
AI agents, checks them against independently authorized mandates and security policies, and controls whether they can proceed to signing or execution.
The agent may have the ability to act but Assertara checks whether it has the authority.
Built for the Meta Global AI Developer Hackathon.
Demo: youtu.be/hkaHx460N5s?si=YUg2…
✨IbnWeb3👑 retweeted
We're giving away an iPhone Duo worth $2,000! 📱
All you need to do is tell us how you use AI through a quick, 1-minute multiple-choice survey.
We'll be announcing the winner next Monday!
Take the survey here: forms.gle/xHFL98C88C9mmwQN8
What a time to be alive!
These whole hack feels like a movie script ngl..😅
✨IbnWeb3👑 retweeted
your opening act cancels. who can replace them without losing the crowd you planned for?
I built MEND to help cultural event organizers compare repairs using @Qloo audience insights, practical constraints and human approval.
Try it: usemend.vercel.app
Alfredo made huge bags from $wif and it been a while he shared any alpha..
If i were you, i will be here😉
✨IbnWeb3👑 retweeted
Apple Inc. AAPL. Apple. 🍎
Three names shouldn't mean three nodes.
Entity resolution in GraphRAG-SDK brings them together with finalize(). 🧩
In tests on graphs up to 50k entities, 99% of merges were correct.
See how 👇
falkordb.com/blog/knowledge-…
