We make agents Failproof. Observability tools observe. Guardrails block and quit. Failproof enforces and corrects. Open Source: https://xitter.cf/t.co/SfwWX15zmx
United States
Joined April 2025
- Tweets158
- Following8
- Followers276
- Likes205
Pinned Tweet
Your AI agent is one tool call away from an unauthorized refund or doing something totally stupid.
Failproof blocks the call, shows the agent the right policy, and finds similar failures hiding in past traces.
More than 10M Agentic events per day at the time of recording. Now 15M🤯
20 people opened our dashboard at once. Every page returned a 504. A few weeks later, the same 3 CPUs serve 200 concurrent users with zero errors.
@SiddarthAhhaaa walked through exactly how in our latest engineering session. The fixes, with the numbers 🧵
Failproof AI retweeted
20 people opened our dashboard at once. Every page returned a 504. A few weeks later, the same 3 CPUs serve 200 concurrent users with zero errors.
@SiddarthAhhaaa walked through exactly how in our latest engineering session. The fixes, with the numbers 🧵
Failproof AI retweeted
got my own ticket for hacktober hack 🎟️
this sunday, 100+ builders, one ai agent. every team gets the same one and has under two hours to make it something you'd actually ship.
sun 25 oct · 4:30 pm · quad ai, hsr bengaluru
@failproofai @digitalocean @MLHacks
Failproof AI retweeted
Hacktober Hack 🔥
700 signups. 100 spots.
Everyone gets the same flaky AI agent. 2 hours to make it shippable. Then a hidden eval suite runs it 3 times per task. Pass all 3 or it doesn’t count.
HSR Layout, Bengaluru.
Failproof AI retweeted
Your AI model can't actually do anything. The harness does.
The model writes text. The harness runs it: on your machine, with your keys, against your real database.
The one moment you can still stop it: after the model asks, before the harness acts. Steer there.
Failproof AI retweeted
OR you could be using @failproofai so your agents are taken care of and you can get some sleep
Failproof AI retweeted
AI moves so fast that we have newspapers covering it now.
Got my copy of The Token Times: a pretty cool way to document everything happening at the frontier.
Shoutout to @failproofai and @niveditjain for this one! 🗞️
Failproof AI retweeted
"Just put it in the prompt" is a polite request.
A prompt is a polite request competing with thousands of other words.
Logs? After the damage.
A human? Not at 3am.
Steering is a decision between the model and the tool, before anything runs. Every single time.
Failproof AI retweeted
peak database maxing at @failproofai
join in for the most whack technical session where we look at how to cutely scale @ClickHouseDB
Failproof AI retweeted
handling 10 million agent traces a day!
Anyone can build an agent tracing demo at 1,000 traces a day.
Plenty of tools look great until the traffic shows up. We’re at 10M agent traces a day, and getting there was not child’s play.
@SiddarthAhhaaa is breaking down how we store and query at that scale, including what broke along the way.
Oct 20, 6pm PT, Gmeet!
Failproof AI retweeted
Agent's done != done
Finishing is an action, so a policy can check it. Before the loop ends, the agent must ask GitHub. APPROVED: done. Anything else: blocked.
And if GitHub can't be reached, it blocks too. Steer on what's true, not what agents remember.
More at befailproof.ai/events
Our AI agent said the PR was approved. It wasn't.
Our Hermes agent had one rule: review the PR and don't leave the loop until it's approved. The GitHub token had expired and the request timed out, but the agent saved "approved" to its memory and moved on. The loop believed it, because the agent was the only thing it was listening to.
Nobody did anything wrong. The outcome was still wrong. Part 2 shows the fix.
From our engineering session "How We Steer Hermes" with @Chhhee10
Failproof AI retweeted
The Token Times by @failproofai , everywhere. Latest techy news, delivered the good old-fashioned way.
Failproof AI retweeted
500+ registrations.
MLH said 50 check-ins. 😭✌️
We said… nah. 💀
Somehow got 150+ builders into the venue, shipped crazy shit, and ran 3 sessions on Hacktoberfest, Open Source & Devcon.
Hosted this absolute chaos with FAIR and had the time of my life.
Crazy successful.
🤖 Made with AI
Failproof AI retweeted
The Token Times by @failproofai ♥️
Just wrapped up a lovely evening at the Figma Config Party - great vibe, arcade games, super chill people, nice drinks & music! 😊
With @SamarthJoshiSJ
Hosted by @accio_ai_ , @kushagra_swami1 & @byakankshaaa
#social #BangaloreTwitter
Failproof AI retweeted
want to read X posts/news on newpaper?
found "The Token Times" at Hacktoberfest Mumbai by @failproofai
an actual newspaper covering AI news, model releases and research
Failproof AI retweeted
New engineering session: How We Steer Hermes
@Chhhee10 on steering AI agents that run when nobody's watching.
Eg: our agent marked a PR as approved. GitHub never got it. The token had expired, the call timed out, and the agent saved "approved" anyway.
How we fixed it 🧵