Replying to @JDArmada
@JDArmada Thanks for organizing luma.com/mistral-elastic yesterday. Had lots of fun. The tool I built using @elastic and @MistralAI at the hackathon is live at sfpermits.53bits.com.
You have a specific visual in your head, but have no idea which file it’s in.
This walkthrough uses Jina embeddings + Elasticsearch to search video by describing what you’re looking for, in natural language: go.es.io/4siXJBX
You receive back the matching scene with timestamps.
we're headed to agntcon & mcpcon tomorrow!! we'll see you at booth 43
& you're invited to the best afterparty:
join us, @elastic, and @apollographql tomorrow evening for drinks, laughs, and networking with fellow founders and agent builders
7.30pm, san jose 🍸
rsvp below
JD retweeted
📣 Attention #DevRel friends!
@elastic are hiring Senior Developer Advocates in NYC, US and Sao Paulo, Brazil. Job specs 👇 .
jobs.elastic.co/jobs/marketi…
jobs.elastic.co/jobs/marketi…
If you are based in these locations and have a background in #DevRel or software engineering, apply!
JD retweeted
tired: AI generated slides
wired: mastra's @abhiaiyer live drawing his
time to find more engaging formats when generating stuff is cheap (and boring)
JD retweeted
Tomorrow evening in SF @TryArcade, @Mastra, and @Elastic are partnering to host an MCP for GTM workshop on October 8th during #SFTechWeek.
I'll be joined by @abhiaiyer, Co-Founder and CTO at Mastra, and @JDArmada, Developer Rel at Elastic.
Four hours, hands-on.
We'll build an agent an account executive would ask to approve a discount and to double-check its work, to enterprise grade standard.
You'll start from scratch and leave with a template you can keep building on.
Mastra runs your agent, Elastic teaches the grounding, and Arcade handles the governance.
Link to register in the comments!
JD retweeted
if you’re not at @posthog then where tf you attttttttt
@waynesutton kicking us off tonight – at San Francisco, CA
JD retweeted
On October 8th in SF @TryArcade, @Mastra, and @Elastic are partnering to host an MCP for GTM workshop on October 8th during #SFTechWeek.
Well be joined by @abhiaiyer, Co-Founder and CTO at Mastra, and @JDArmada, Developer Rel at Elastic.
Four hours, hands-on.
You'll build an agent an account executive would ask to approve a discount and to double-check its work, to enterprise grade standard.
You'll build the whole thing and leave with a template you can keep building on. Mastra runs your agent, Elastic teaches the grounding, and Arcade handles the governance.
Link to register in the comments!
JD retweeted
Tapez une description, retrouvez la seconde exacte du plan vidéo 🎬🔍
@jdarmada explique comment combiner #Elasticsearch, @JinaAI_ et PySceneDetect pour révolutionner la recherche B-roll.
🔹 Découpage par scène
🔹 Vectors 1024D
🔹 kNN Search
👉 elastic.co/search-labs/blog/…
When you create a recipe, you try a few tweaks and combinations before landing on the final version.
Creating an embedding model is no different.
This process of experimentation is known as ablation.
For both audio and vision pipelines in jina-embeddings-v5-omni, multiple ablation studies were performed before we landed on the final architecture: freeze all the encoders, train only the smaller projectors.
Relevance Please: Ep4 - Build AI Agents with Live Context xitter.gq/i/broadcasts/1yxBeeXvM…
JD retweeted
we‘re doing a ⚽️ based hacknight in SF: data sets and prices are all about soccer and we‘ll also have the game (happening in the bay area) running in the background
come for the game and stay for the tech — or the other way around luma.com/aws-elastic-hacknig…
JD retweeted
To my #DevRel friends in the Netherlands 📣
We are looking for an Advocate in Amsterdam to join the Elastic team. If you are passionate about speaking, sharing technical content with the developer community, and writing code do apply!
jobs.elastic.co/jobs/enginee…
JD retweeted
the ability to identify shortsighted or poorly written code is now the most valuable skill.
JD retweeted
Super excited to be live demoing @asymptotelabs' Agent Beacon at @elastic's Developer Meetup on May 28 in San Francisco.
I’ll walk through how Agent Beacon turns AI agent runtime activity into Elastic-native security investigations, helping teams connect suspicious behavior back to the agent workflow behind it.
I’ll be presenting alongside lead engineers from @recurly and @Intuit for a night of real production stories across search, reliability, observability, and AI runtime security.
If you're around, please swing by! Luma link below in the comments 👇




















