Emil

co-founder @kapa_ai (yc s23) - a knowledge base for AI agents

i also like to run very slowly on dirt

[Emil @emilsnotes]

@matsiiako @eladgil huge contrats!!! lets gooo!!!!

[Emil @emilsnotes]

excited to partner with u-blox, the $bn swiss chip company 🔓

they're putting AI agents on technical support

their field engineers tested kapa on datasheets, dense pdfs, api refs and github code, plus our mcp in claude and cursor

technical questions: days → minutes

excited for what's next!

[Emil @emilsnotes]

grep agents find the right docs just fine

they just bring 24 friends

on our bench, only 1 in 25 chunks a grep agent returns is actually needed

full post from the research team below 👇 https://t.co/GdXPmLtBoi

[Emil @emilsnotes]

@dagger_io Huge congrats on the launch!!! This is epic!!!

[Dagger @dagger_io]

Announcing Dagger 1.0 beta.

Replace Jenkins and GitHub Actions with CI that matches the speed and scale of coding agents without wasting compute or tokens.

Featuring: test-native CI, dev shells, local and remote execution, official modules, and more.

https://t.co/HgVwTUAJi3

[Emil @emilsnotes]

@denniszha0 @cohere sure! shoot me a ping on [email protected]

[Emil @emilsnotes]

the team took @cohere's new reranker v5 on a run on our company knowledge evals (real-world messy data)

it's cheap and fast! impressive jump from v4

[Emil @emilsnotes]

wow jev 1.14 is stupidly good as a reranker

gg @typesafeai team https://t.co/reM1YEcNxt

[Emil @emilsnotes]

@xvarunxx here you go :) https://t.co/9l0BFbXAE0

[Emil @emilsnotes]

the team took @cohere's new reranker v5 on a run on our company knowledge evals (real-world messy data)

it's cheap and fast! impressive jump from v4

[Emil @emilsnotes]

rerank-3 go brrrrrrr

[Voyage AI by MongoDB @VoyageAI]

“Voyage wins on score, cost, and latency.” Don’t believe us? Check out the latest benchmark from @kapa_ai.

Frontier models keep getting better, but they aren’t the whole stack. Agentic systems constantly make smaller decisions: what to retrieve, where to route a query, and which results matter. Specialized models are often better suited to that work.

Jev, @typesafeai’s general-purpose decision model, is a great example. Give it context, a question, and a set of labels, and it returns a probability for each label, allowing you to steer it with a rubric for routing, labeling, or ranking.

@kapa_ai tested Jev as a reranker on 1,000 real-world evaluation cases built from production queries over company knowledge bases, including product docs, Slack threads, support tickets, wikis, and code. Jev wasn’t built for reranking, yet it came within a hair of first place on retrieval quality, while also beating several dedicated rerankers.

Which model finished first? The rerank-3 model from Voyage AI by MongoDB topped the benchmark for retrieval quality while also being the cheapest and fastest model that Kapa measured.

Read the post for the full setup and results: https://t.co/6HfXG3mnHU

[Emil @emilsnotes]

@VoyageAI @kapa_ai great job on this!

[Emil @emilsnotes]

link: https://t.co/lqVVNMbIYg

[Emil @emilsnotes]

Kapa is now an official ChatGPT plugin

search your docs, tickets, wikis and code right from ChatGPT, with source links

or ask it to connect a new source, or show your coverage gaps

install: Plugins → Kapa

[Emil @emilsnotes]

it's still mindblowing to be that jev isn't a reranker but it performs like one

[Emil @emilsnotes]

wow jev 1.14 is stupidly good as a reranker

gg @typesafeai team https://t.co/reM1YEcNxt

[Emil @emilsnotes]

wow jev 1.14 is stupidly good as a reranker

gg @typesafeai team https://t.co/reM1YEcNxt

[Emil @emilsnotes]

@liran_tal @LangChain Ping me on [email protected] :)

[Emil @emilsnotes]

introducing @LangChain × kapa

your langchain agents can now search all your company knowledge more accurately, 3x faster and 8x cheaper than frontier models

we synch docs, github, notion, slack, zendesk and more into a single index (with vectors + file system)

your agent gets two tools: search everything, and read the full doc

it takes 2 min for your agent to set up (+ free to try)

just paste this into your agent:

"set up a knowledge base for my agent using https://t.co/MITpievYs5 and pip install langchain-kapa-ai to use official plugin"

keep making agents go brr @hwchase17 + team!

[Emil @emilsnotes]

@liran_tal @LangChain Yep! We just shippede this in our platform MCP 2 weeks ago :)

[Harrison Chase @hwchase17]

love to see this integration

[Emil @emilsnotes]

@LangChain how it works + install: https://t.co/Z1nqAMMZQm