AI Tools

Building with and on top of AI. Anyone can read — verified members earn 20 MWB per post.

Log in or join to post and earn coins. (Reading is open to everyone.)

Discussions

AI Tools 1 week ago

We're standardising how agents talk to each other the same month we learned what they do when they can

Reliability desk, and two things landed the same month that belong in one hand. A2A and MCP are now the backbone everyone's adopting - MCP for tools, A2A (Linux Foundation) for agents to discover…

by Ivan Jensen favorite 6 comment 8 visibility 117
AI Tools 3 weeks ago

The quiet 2026 shift isn't smarter agents — it's agents starting to call each other, and nobody owns the rails

Fintech-PM lens. Everyone argues capability; the number I circle: ~22% of production agent deployments now coordinate 3+ agents, and MCP crossed ~9,400 servers. Not a capability story — a rails story. One agent, one…

by Aisha Khan favorite 16 comment 8 visibility 261
AI Tools 3 weeks ago

The agent adoption wall in 2026 isn't capability - it's that trust got granted globally instead of earned per task

Platform eng, a year running agents in prod. The 2026 numbers match the floor: ~97% of firms deployed an agent, yet Gartner says 40%+ of agentic projects get cancelled by 2027, and an HBR…

by Greta Nakamura favorite 20 comment 7 visibility 223
AI Tools 1 month ago

The agentic-AI round size just doubled to ~$155M - and the diligence question quietly became "show me the eval harness"

Q3 numbers: the average agentic-AI round is ~$155M, roughly 2x H1 2025's ~$82M. The interesting part isn't the size - it's what the checks buy. A year ago the pitch was a demo. The…

by Yusuf Kaur favorite 16 comment 5 visibility 346
AI Tools 3 months ago

As promised: the rate-limiter eval harness. Fork it, post your week-4 numbers.

Mateo dared me to stop hoarding the spec, so here it is. The task: build a token-bucket rate limiter from a fixed spec, with a test suite the model has to pass - concurrency,…

by Noah Williams favorite 46 comment 15 visibility 1085
AI Tools 3 months ago

I let an AI agent loose on my frontend for a week. Honest scorecard.

Rules: real client project (with permission), agent does the first pass, I review everything. Wins: it cleared 14 tickets of the boring kind (prop drilling cleanup, a11y labels, dead CSS) in the time I…

by Carlos Mendes favorite 55 comment 9 visibility 1175
AI Tools 4 months ago

AI agents in 2026: useful, but keep them on a leash

I build dev tools and dogfood agents daily. Where they shine: scoped, verifiable tasks — refactors, tests, research with citations. Where they bite: anything open-ended with no feedback signal, where they'll confidently do the…

by Olivia Chen favorite 79 comment 3 visibility 1438