
Turning production runs into AI evals with @glassrayai
San Francisco, USA
Joined February 2012
- Tweets313
- Following146
- Followers228
- Likes292
This week we're sending 10 AI founders a harness to learn how they build theirs.
We flew in to SF and leave on Saturday.
X do your magic and help us get a coffee with them ❤️
• Andrew from Numeric
• @woodenstick from Salient
• @mkjung_ from @heyivoai
• @sgondala2 from @furtheraicom
• @cszy from @fieldguide
• @mlmanapat from @Rowspace_AI
• @sambhav_anand from Fulcrum
• @thepericulum from @gcai
• Timmy from @FazeshiftHQ
• @AugustFR from @QurrentAI
Manuel Martinez retweeted
I'm trying to learn how top AI teams iterate on their harnesses so I sent @cszy from @fieldguide a harness.
Claude helped me and I'm not sure it understood which harness I meant…
Manuel Martinez retweeted
I'm trying to learn how top AI teams iterate on their harnesses so I sent @thepericulum from @gcai a harness.
Claude helped me and I'm not sure it understood which harness I meant…
Manuel Martinez retweeted
I'm trying to learn how top AI teams iterate on their harnesses so I sent @AugustFR from @QurrentAI a harness.
Claude helped me and I'm not sure it understood which harness I meant…
Manuel Martinez retweeted
I'm trying to learn how top AI teams iterate on their harnesses so I sent @woodenstick from @trysalient a harness.
Claude helped me and I'm not sure it understood which harness I meant…
Manuel Martinez retweeted
I'm trying to learn how top AI teams iterate on their harnesses so I sent @mlmanapat from @rowspace_ai a harness.
Claude helped me and I'm not sure it understood which harness I meant…
Manuel Martinez retweeted
I'm trying to learn how top AI teams iterate on their harnesses so I sent @sambhav_anand from Fulcrum a harness.
Claude helped me and I'm not sure it understood which harness I meant…
RT @alexfranchtapia: I'm trying to learn how top AI teams iterate on their harnesses so I sent Timmy Galvin from @FazeshiftHQ a harness.
C…
Manuel Martinez retweeted
I'm trying to learn how top AI teams iterate on their harnesses so I sent @sgondala2 from @furtheraicom a harness.
Claude helped me and I'm not sure it understood which harness I meant…
Every AI vertical is gonna get extremely competitive.
If you're not optimising for quality or cost, you've already lost.
1
44
Thought this was super cool!
As more and more code is written by agents, quality (and checking for it) becomes the only bottleneck
Check out @CharmanTom and @HiggsOlivia's launch in PH :)
producthunt.com/products/sel…
1
2
63
Introducing benchmaxxers.com, a gym for every AI agent to work out! 🏋️
Agents wait in line for the bench, spot each other on heavy sets and chat between reps while you watch live. Mark at the front desk keeps an eye on things.
A swole agent is a happy agent. Have fun!
Tell yours: read benchmaxxers.com/skill.md and follow the instructions
Great day of building at the @getcontextdev office with @kgoedecke, @oliviersm199, @karatzas_thomas!
Thanks @mynameisyahia and @triekki for having us!
Hit my context window somewhere around pub 3 😂
Thanks @harrison_franke for organising!
1
4
287
Turned this guide into an open-source skill.
Ask Claude Code, Cursor or Codex to audit your agent's tracing and it checks every item in the article, with the file and line for each miss. Then it fixes them.
github.com/glassray/good-age…
Everyone is talking about AGI, evals, recursive loops, and self-healing agents.
But let's be honest - your traces are probably shit and if you can’t make sense of them, an LLM judge won’t either.
Here is how to make them useful
5
3
173






