@dreamsofcode_io 1. I despise have to argue with, teach, and guide agents. its sooooo mentally taxing.
I've been amazed to see none of the agent products I use have correction detection and automatic optimization based off of user guidance. (so we're building it)
@emollick the standards of measurement are flimsy at best for 90% of ROI calculations. Most companies don't even have a metric to track agent roi to cost
@GaryMarcus 0. Agents still suck 99% of the time - the hype veneer will wear off, consumers are discerning. Build better agents NOW or prepared for the wave of churn
@bendee983 turns out hype and doom are both toxic. reality is somewhere in the middle. the sooner we talk about realistic expectations for ai (good and bad) - the faster it will deliver on more realistic (and still astounding) expectations
@Jabaluck the problem isn't that we don't want ai to solve our problems. its that its NOT solving the problems we were originally promised. We were promised utopia, cancer cures, ubi - and now we just get ai used as cloud cover for layoffs while ai costs are higher than the ppl it replaced
Im blown away by how terribly craptastic Gemini Enterprise Pro is.
Just spent an hour helping a global bank customer troubleshoot their system.
The model speed is atrocious, tools aren’t transparent, agent builder wizard cant build agents, context pollution was rampant… yeesh
We made the news last week, right alongside Sam Altman's mic-drop offer at Y Combinator and SpaceX's record-breaking IPO.
Featured in @StrictlyVC's VC/startup funding roundup for our $2.2M pre-seed round led by @ycombinator and @FundersClub.
I've talked to a lot of founders on Built to Ship about building AI agents.
The conversation always goes the same way.
Me: "How do you know when your agent is broken?"
Them: "We dig through logs manually."
Me: "How do you evaluate quality?"
Them: "We just... look at the outputs."
This is the state of agent observability in 2026.
@voker_ai built the monitoring layer agents actually need.
Huge week for @voker_ai
- Ranked top 10 on Product Hunt
- 70k LinkedIn impressions in the last week
- 10k website visits
- 60 customers onboarded
- Written up by @kytsune at @SiliconANGLE & @theCUBE
- Got 25 pies thrown in my face
- Threw a RAGER to celebrate our new Agent Analytics Platform with 150 of our supporters, customers and friends
- Hosted events at Lightfield and Corgi Cafe
- Met up with new customers at ProductTank San Francisco, Cursor and WorkOS
Appreciate all of you.
Had the pleasure of hosting an event at Lightfield on Monday, with CTO's @vesko_st, Adit Sanghvi (from @getdecisional), and @bertie_ai, to talk about what it takes to go from shipping your first agent to being the best in your category.
Today, I'm thrilled to disclose Voker’s $2.2M in pre-seed funding from @ycombinator and @FundersClub.
I’ve watched product teams ship AI agents with zero visibility into whether they're actually working.
Logs don't tell you if your agent is helping users. You can't review 10,000 conversations manually. And metrics don't appear on their own.
That's why we built Voker.
The proof is in the pie.
Yesterday @voker_ai launched on Product Hunt, and we finished in the top ten. As promised... for every 10 upvotes I got pied in the face.