Top Tweets for #NeatHack
two weeks ago i built friction fixer for #neatHack
analytics can see people leaving your page. it still can't change the page
so i built an agent that edits the page, watches who shows up, and only keeps the change if more people stay
builders, what's the one thing you'd want it to fix on your site first?
The project we built for #neatHack, Kedge, came 14th out of 205 projects.
@faroukobayanju and I developed the idea and built it within the 48-hour limit.
Kedge checks every step of an AI coding agent against the plan, and when the agent does an unfinished job, Kedge catches it and makes it try again until the fix is proper.
Proud of what two people got done in one weekend.
Congratulations to the top 3 projects. Thank you @neatlogs , @EntireHQ and @arithecfo for a great hackathon.
our coding agent told us “all tests pass.” it had deleted the test file.
that’s why we built Kedge for #neatHack. dependabot and renovate PRs break all the time and more teams hand them to coding agents to fix unattended. when a fix gets hard, the agent deletes tests, edits files it was never asked to touch, or says it’s done when it isn’t.
kedge supervises the agent. It plans the fix, lets the agent take one step, runs the tests, and checks for drift: tests lost, files outside the plan, a repeated attempt, a claim that doesn’t match the results. On drift it rolls back to the last good commit, tells the agent why, and retries. In our demo the agent deleted a test file at step 1. Kedge rolled it back and step 2 fixed the real bug, 5 of 5 tests passing. With no supervisor, the same agent shipped 2 of 5 tests and called it fixed.
@neatlogs showed us our own blind spot first: 0 errors across 33 traces. Kedge wasn’t reporting its failures at all. After we fixed that, the daily digest flagged the error rate on the next run. The trace pointed to the exact step where the agent deleted the test, and the Execution Failed detection and error analysis group every failure by cause. Kedge also reads its past runs back from neatlogs before it plans, and writes its verdict onto each trace.
@EntireHQ checkpoints every commit the agent makes. Before a new fix, Kedge searches past checkpoints for the same failure and gives the agent what worked. It skips any old fix that touched tests.
@arithecfo set the budget. We built the business plan with Ari: $10 per green PR at a 92.5% margin leaves $0.45 for the model. Kedge reads that from pricing.json and stops before any step it can’t afford. We learned why the hard way: on one batch, OpenCode estimated $1.57 and the real bill was $5.70. Ari’s stress case put uncapped runs at $2.85 a PR and a 68.5% margin. Now Kedge meters the real bill, and our demo fix cost $0.12.
one more rule: Kedge opens no PR without proof, meaning a neatlogs trace, an Entire checkpoint and the cost.
Team: Farouk + Haikeys (@Haikeystweett )
Repo: https://t.co/u8ONll7guv
kedge came 14th out of 205 projects at #neatHack (tied on 85.5), which gets us 3 months of neatlogs Pro.
congrats to @Milliebanned (Veritas), @jennyoliver57 (Trueup) and @chiraghonnyal (Mend). the top two built a dependency upgrade agent and a trace checker, close to what we were going for.
thanks @neatlogs, @EntireHQ and @arithecfo. Built with Haikeys (@Haikeystweett ).
our coding agent told us “all tests pass.” it had deleted the test file.
that’s why we built Kedge for #neatHack. dependabot and renovate PRs break all the time and more teams hand them to coding agents to fix unattended. when a fix gets hard, the agent deletes tests, edits files it was never asked to touch, or says it’s done when it isn’t.
kedge supervises the agent. It plans the fix, lets the agent take one step, runs the tests, and checks for drift: tests lost, files outside the plan, a repeated attempt, a claim that doesn’t match the results. On drift it rolls back to the last good commit, tells the agent why, and retries. In our demo the agent deleted a test file at step 1. Kedge rolled it back and step 2 fixed the real bug, 5 of 5 tests passing. With no supervisor, the same agent shipped 2 of 5 tests and called it fixed.
@neatlogs showed us our own blind spot first: 0 errors across 33 traces. Kedge wasn’t reporting its failures at all. After we fixed that, the daily digest flagged the error rate on the next run. The trace pointed to the exact step where the agent deleted the test, and the Execution Failed detection and error analysis group every failure by cause. Kedge also reads its past runs back from neatlogs before it plans, and writes its verdict onto each trace.
@EntireHQ checkpoints every commit the agent makes. Before a new fix, Kedge searches past checkpoints for the same failure and gives the agent what worked. It skips any old fix that touched tests.
@arithecfo set the budget. We built the business plan with Ari: $10 per green PR at a 92.5% margin leaves $0.45 for the model. Kedge reads that from pricing.json and stops before any step it can’t afford. We learned why the hard way: on one batch, OpenCode estimated $1.57 and the real bill was $5.70. Ari’s stress case put uncapped runs at $2.85 a PR and a 68.5% margin. Now Kedge meters the real bill, and our demo fix cost $0.12.
one more rule: Kedge opens no PR without proof, meaning a neatlogs trace, an Entire checkpoint and the cost.
Team: Farouk + Haikeys (@Haikeystweett )
Repo: https://t.co/u8ONll7guv
WE WON at #neatHack 🏆 3rd place!!
built Mend, an agent that reads its own @neatlogs traces, patches its own code, and only keeps a fix if a full rerun proves it
team: @chiraghonnyal @AyushUpadhye @Bhumika_808_
thanks @bettersayAJ @simranrambles @mufassirkazi @akshay_hangloo @EntireHQ @arithecfo
we won #neatHack
we built Mend, an agent that debugs itself: it read its own @neatlogs traces, patches its code, keeps a fix if a full re-run proves it. it rejected more of its own fixes than it kept
W @abhijeetsharma_ @Bhumika_808_ @AyushUpadhye
shoutout @EntireHQ @arithecfo
Loved building benana for #neatHack
Really appreciate the honorable mention @akshay_hangloo and @neatlogs
Our #neatHack submission
Presenting Benana!
Turn an idea into a playable Minecraft mod.
Agents write the code, test it on a real server, and use failed playtests to fix it.
Built with @arithecfo @EntireHQ @neatlogs
Had fun building for #neathack
Thanks to @akshay_hangloo and @neatlogs for the recognition and all the people in my dm that noticed and liked Tally :)
Trueup won #neatHack! 🏆 Tied at the top with Veritas, both scoring 90.5/100.
48 hours of solo building, head to head with 200+ builders, too much coffee 😃 and one agent that checks if your AI's traces are telling the truth.
Huge thanks to the @neatlogs team for the platform and for hosting this. I honestly couldn't have built it without seeing every run in there, including my own agent messing up 😅
@EntireHQ kept a record of every coding session, so you can see exactly how each fix got made, and Trueup even runs as an Entire command.
@arithecfo turned my real run costs into an actual business plan, which was a fun reality check.
It's open source, so anyone building on neatlogs can use it to check their own traces.
https://t.co/NC3wT1XDjs
Congratulations to Veritas and the other winners!!
Your dashboard said OK. Your agent crashed.
This weekend @neatlogs' daily email told me 6.2% of my test runs had failed. I checked all 81: 9 had crashed, 11.1%. Four crashes were recorded as SUCCESS. (Test runs I crashed on purpose, with the tracing tools as anyone downloads them.) The email added up what it was given. The tracing code that writes the record got it wrong, and nobody checks the checker.
So I built Trueup.
Trueup Witness is a second sensor for your AI agent, in two lines of code. It watches what really happened on the connection and compares it with the neatlogs record. When they disagree, it writes a red TRACE DISAGREE step into that same record. Then Trueup's agent finds the cause in the tracing code, writes the fix with tests, proves it and sends it upstream.
neatlogs:
Live, with real Claude calls through the neatlogs model key: I cut the connection mid-reply and crashed an agent run. Before my fixes, neatlogs recorded SUCCESS. After, ERROR. 2 wrong records to 0, and no false alarms in 40 normal calls.
I also traced Trueup's own agent in neatlogs, and its alert rules caught my mistakes: 31 replies the AI sent in the wrong format, 27 false alarms from a bug in my own comparison, and 13 failed fix attempts. Each was fixed and kept on record.
@EntireHQ:
Trueup was built in recorded Entire sessions, and each fix links to how it was made. The session where the fixer wrote and proved its first fixes: https://t.co/G6qR2kLkCk
It uses Entire's code graph to find the faulty code and check what a fix could break, and runs as an Entire command: entire trueup.
https://t.co/8lK2jGgZ3n (@arithecfo):
Ari built the business plan and a financial model with me, on costs I really measured: a Witness check costs $0, a fix about $0.52. It got one number wrong, I corrected it, it re-ran the plan. In the forecast, at $199 a team 94 paying teams break even, while $99 runs out of cash. Rule from the slow-growth case: pilots first, hire later.
https://t.co/AvrdcATB9M
Fixes sent upstream:
To Arize, Traceloop and neatlogs. Arize's head of open source reviewed mine: fixing it is "the right goal". neatlogs runs that same Arize code for agents, so one fix repairs both.
https://t.co/95AOFG5SNS
https://t.co/zFSJ2qFSff
https://t.co/lhVcYlxGlm
Built in public all weekend:
The thread Arize's maintainer replied to: https://t.co/sbsY6On3rU
12 Oct update: https://t.co/9OLdgsryMt
11 Oct update: https://t.co/lWNqUzmSC6
Crash it yourself: https://t.co/B2MYfoUb1S
Code and every number: https://t.co/NC3wT1XDjs
@neatlogs @EntireHQ @arithecfo @akshay_hangloo #neatHack
Huge thanks to the organizers, sponsors, and everyone involved who made #neatHack so good 🙏
@simranrambles @bettersayAJ @thevibefounder @HaimantikaM @akshay_hangloo @agent_wrapper @chetan_raj @roerohan @ankushdharkar @karan_pargal @BngRithvik
@EntireHQ @arithecfo @neatlogs
GGs to everyone who took part in #neatHack!
Didn’t win anything this time, but it was super fun.
Can’t wait for the next one... hopefully it’s in person!!
@neatlogs @simranrambles @bettersayAJ @thevibefounder
JUST 30 MINUTES TO GO #neatHack
who won neatHack? find out today, 6 PM IST
https://t.co/vJY6fgqDqU
#neathack winner announcement today!!!
@neatlogs traced every run and caught my own agent failing steps that actually worked. @EntireHQ recorded the session behind every commit. @arithecfo showed that my old spending cap would run out of cash in month 14.
Thank you to the judges and mentors who shaped this: @bettersayAJ @akshay_hangloo @agent_wrapper @HaimantikaM @chetan_raj @roerohan @ankushdharkar @karan_pargal @BngRithvik and @simranrambles for being the best host!
your quickstart is the only part of your product tested by people who leave instead of filing a bug 🫠
so for #neatHack i'm building FirstRun 🛠️
give it a docs URL. it runs every step in a clean container, like a brand-new dev.
a step breaks → it finds the cause, fixes the docs, proves the fix in a second clean run, and opens the PR ✅
break. fix. prove.
the stack:
🔍 @neatlogs traces every run
🧠 @EntireHQ records every session that built it
📊 @arithecfo turns the cost per run into a business plan
i build all of it in public until monday ⏱️
cc @HaimantikaM @thevibefounder @simranrambles @bettersayAJ
Last Seen Hashtags on Sotwe
Trends for you
Most Popular Users
Elon Musk 
@elonmusk
241.5M followers
Barack Obama
@barackobama
118.8M followers
Cristiano Ronaldo
@cristiano
114.5M followers
Donald J. Trump
@realdonaldtrump
111.9M followers
Narendra Modi
@narendramodi
107.1M followers
Rihanna
@rihanna
98.7M followers
NASA
@nasa
92.3M followers
Justin Bieber
@justinbieber
91.8M followers
KATY PERRY
@katyperry
90M followers
Taylor Swift
@taylorswift13
84M followers
Lady Gaga
@ladygaga
75.5M followers
Virat Kohli
@imvkohli
73.5M followers
Kim Kardashian
@kimkardashian
70.9M followers
YouTube
@youtube
68.8M followers
Neymar Jr
@neymarjr
66.5M followers
Bill Gates
@billgates
65.3M followers
Selena Gomez
@selenagomez
63.1M followers
The Ellen Show
@theellenshow
62.2M followers
CNN
@cnn
61.7M followers
X
@x
60.7M followers