Building the foundational infrastructure for autonomous AI in strictly regulated environments.
London, England
Joined January 2024
- Tweets408
- Following46
- Followers35
- Likes497
Prescott Data retweeted
Most multi-agent systems route every message through one orchestrator. When it goes down, everything stops.
Join @MutuaDevOps this Thursday for a live build-along: agents that find each other and talk directly, built on JarvisCore.
Oct 22 · 11:00 AM EAT · Discord discord.gg/DEgSVevF?event=15…
Introducing JarvisCore Enterprise!
We released JarvisCore officially last month and are impressed about the fast adoption by @prescottdevs builders across the world.
Today, we go a step further. McKinsey State of AI, 2025 reports that more than 62% of organisations are experimenting with AI agents and 51% have already experienced a negative consequence from AI. This is why we are making JarvisCore Enterprise available for organizations automating operations and decision intelligence with AI agents but want to do it with:
- Human governed controls
- Deterministic control on outcomes
- Evidence layer for auditability
- AI actions grounded in their own data
- Growth and retention of their sovereign institutional data
- Proof of compliance to regulators
- Cost efficiency and ROI maximisation
Let's get you started governed, secure, and auditable!
Prescott Data retweeted
My hope for JarvisCore is that it shows a completely different way to build AI agents. Not as an experiment, but as an approach we've proven.
We open-sourced it a few months ago and kept building. Today it launches on Product Hunt. Here's what makes it different:
• No master agent. Agents are equal peers in a decentralised P2P mesh
• No MCP servers needed
• Zero-trust credentials
• Bounded memory (agents forget on a curve)
If you're building agents, I'd love to hear what's breaking for you.
Source workspaces are live in JarvisCore for your agents.😊
Developers assemble!
JarvisCore 1.13 now gives agents durable source workspaces.
Point a Mesh at a GitHub repo and the agent works from an immutable snapshot. Each step gets its own isolated copy-on-write workspace. Every edit is hash-guarded, so a stale edit is rejected instead of overwriting newer code. Commands and file changes come back as verified receipts, and only the accepted diff is kept.
You can also connect your own sources, like archives, datasets or document collections, through the same adapter interface.
Prescott Data retweeted
best way to close my day with a webinar on @typesafeai Jev in JarvisCore!
i covered the 4 places we are using Jev in our agent runtime: RAG classification and ranking, model routing, subagent routing, and directly in agent decisions
this is not the end, i believe there is much more to come in our memory assembly, tool recovery, peer delegation, and human-in-the-loop. Every agent harness, runtime, loop needs some good Jevglue!
also check out this docs.google.com/document/d/1… by @CompleteSkeptic
Prescott Data retweeted
Join us on Tuesday, Sep 22 for a Deep-technical Office Hour session with @MutuaDevops, as we dig into AI agents in production - what actually breaks once they leave the lab, and what that teaches you about building AI Agents. #Jarviscore
discord.gg/bBsVa7Qm?event=15…
Prescott Data retweeted
a nice debut to founder-led distribution "right of passage" without using "hey guys"
okay folks we've open-sourced an agent runtime and we think you will like it for 5 things:
no MCP wiring, no master agent just pure mesh with peer-to-peer, deterministic control, zero-trust through an agent broker, and a bounded memory lifecycle.
Prescott Data retweeted
Office Hours continues this Thursday and we are doing a first build along on the #JarvisCore agent runtime.
Join the conversation: discord.gg/jbRBAsMgM?event=1…
The Enterprise is a circuit of decisions across systems, people, and processes. Security around this decision circuit determines what remains sovereign.
AI agents automate these processes today but they also become a new member of the decision circuit. Hence, a new risk that threatens the sovereignty the Enterprise has cared about for decades.
#Nexus is a component of the Prescott agent runtime that eliminates this risk. The community at @prescottdevs is actively shipping to ensure easy integration into Enterprise applications.
Prescott Data retweeted
lil bro has a perk. let's go build for prod!
Our official first drop is here. $5000 worth of AI credits for real builders on our agent runtime.
We'll be issuing more communication in our developer community discord here: discord.gg/jbRBAsMgM
See you there!
Prescott Data retweeted
The team at @prescottdata built an internal tool called #ContentForge on the agent runtime (#JarvisCore) to solve their own content creation and distribution challenge. This is a tool they actually use in production.
If you are interested in such an outcome and/or want to learn from us about our open-source agent runtime, consider joining our discord community here: lnkd.in/d9wEfBnG
Watch the demo below
Prescott Data retweeted
Our house just got bigger, devs are welcome to build with us
Developers building AI agents now have a home at @prescottdevs
Our agent runtime — the same one Dromos runs on — is now open source. Built for production scale, not demos.
@askmuyukani + @sangalo__ kick off Office Hours Tuesday.
Register: discord.gg/jbRBAsMgM?event=1…
Developers building AI agents now have a home at @prescottdevs
Our agent runtime — the same one Dromos runs on — is now open source. Built for production scale, not demos.
@askmuyukani + @sangalo__ kick off Office Hours Tuesday.
Register: discord.gg/jbRBAsMgM?event=1…
We've published our research on Odin; our latest knowledge graph intelligence engine that powers insight discovery inside Dromos, our platform for healthcare and insurance intelligence and automation.
Odin introduces COMPASS (Composite Oriented Multi-signal Path Assessment) to guide AI agents through knowledge graphs at million-entity scale, surfacing meaningful patterns without pre-specifying queries. All this while maintaining end-to-end provenance for regulated environments.
Find out more in arXiv ➡️ arxiv.org/abs/2603.03097
Building agents?
Adopt → star the repos & reply #ADOPT plus what you're building
Contribute → reply #CONTRIBUTE plus your focus (integrations, recovery, memory, observability, docs, examples, etc.)
We'll DM best entry points. Who's in?👇
#MultiAgent #AIAgents #Dev #OpenSource