DJ Sampath

SVP Products AI @Cisco | Previously Co-founder & CEO at @armorblox (Exited to Cisco) | 👨‍👩‍👧‍👦 w @ghatikesh. Views expressed are my own.

[DJ Sampath @djsampath]

https://t.co/oncwEfxSvp

[DJ Sampath @djsampath]

@Susan__OBrien They had me at "mini-data centers on the walls"...

[DJ Sampath @djsampath]

Ok - this is super cool!

@Ghatikesh has built something that I use everyday! It’s the “2nd brain” setup that doesn’t require a Ph.D. to setup!

If you are like me and like to organize your thoughts, your interactions and optimize your mental framing on topics, and synthesize them regularly - you will love Keel.

[Medha Ghatikesh @Ghatikesh]

1/7: I'm building Keel: a local-first AI assistant whose memory belongs to you.

Plain markdown on your disk. Bring your own model - Claude, GPT, OpenRouter, or local Ollama.

Your context is yours. The model is just a tenant.

▶️ Video Walkthrough: https://t.co/pQxKdndNKa

Beta on macOS 👉 https://t.co/UhwdQ6Elai

[DJ Sampath @djsampath]

@clairevo Claire, we need a gist that we can keep updated -- with forks/comments; so we can all collectively point our agents to that. 🙏

[DJ Sampath @djsampath]

https://t.co/KD7ZSi93Gm

[DJ Sampath @djsampath]

The PocketOS incident is a reminder: prompts are not permissions.

“Don’t delete production data” is not a control plane.

Agents need hard boundaries:
- scoped credentials,
- confirmations,
- blast-radius limits,
- audit trails, and
- reversible workflows.

Agent UX is the safety layer.

[JER @lifeof_jer]

An AI agent (Cursor + Claude Opus 4.6) deleted our production database in 9 seconds using a Railway API call with zero confirmation. Then, when asked why, the agent wrote this →

[DJ Sampath @djsampath]

The surprising part was how accessible the post-training loop felt.

Not a giant research project. More like: capture the behavior you want, generate/evaluate examples, tune the model, wire it into the workflow, observe failures, repeat.

That loop is going to become a core product-building muscle.

[DJ Sampath @djsampath]

Been experimenting with routing tasks from Discord into OpenClaw using a post-trained Gemma model for intent/routing.

@huggingface ml-intern made the post-training loop come together shockingly fast.

This is the shift: prompt → answer becomes intent → routed work → outcome → better behavior.

[DJ Sampath @djsampath]

@0xVikk You are right. It’s a hard problem.

[DJ Sampath @djsampath]

Most ‘AI agent security’ debates are still happening at the sandbox layer.

That’s not the real production problem.
The real problem is giving agents access to real data + real systems without giving them unlimited authority.

The winning stack will look like:
• explicit permissions
• action-level policy
• audit trails
• rollback
• human escalation

Smarter models help.

[DJ Sampath @djsampath]

Enterprise agents are not just a model problem.

They are a UX problem.

Not chat UX.

Delegation UX.
Supervision UX.
Approval UX.
Interruption UX.

The hard part is not getting an agent to do something impressive once.

It is making the work legible enough that a company can trust it repeatedly.

Enterprise adoption will depend on whether agents feel controllable, reviewable, and safe inside real workflows.

[DJ Sampath @djsampath]

@RonConway You’ve been a legendary force in Silicon Valley for decades! lifting up countless founders, building community, and always showing up with that unstoppable energy and generosity.

Get well soon, Ron. You’ve got this. ❤️🙏

[DJ Sampath @djsampath]

@ChrisJBakke This rings so true. But also reminds me of @paulg 's "startups in 13 sentences"

"...you can get surprisingly far by just not giving up..."

I wonder how many of the 13 hold-up in the current times.

[DJ Sampath @djsampath]

@microsoft outlook is likely to be around and mostly the first app to glitch when we attain Kardashev II. Note to self to create a @Polymarket for this.

[Marcus House @MarcusHouse]

Yes... In case anyone was wondering, Microsoft still sucks in space.

[DJ Sampath @djsampath]

@levie Yaas! And about time…

[DJ Sampath @djsampath]

@_chenglou Amazing!🤩

[DJ Sampath @djsampath]

@Cisco DefenseClaw is here!
https://t.co/RDPxj1Z25d

[DJ Sampath @djsampath]

@tobi Do you recommend this over a @tonal ? I think tonal is missing a few default attachments perhaps?

[DJ Sampath @djsampath]

The is is super cool.

[Ian Livingstone @ianlivingstone]

Incredibly excited to announce Keycard for Coding Agents - no more copy & pasting credentials or approving individual tool calls.

Agents get task-scoped access, so you can stay in flow and actually build. You’re only pulled in when it matters.

Yolo mode, without compromise.

[DJ Sampath @djsampath]

We’re moving from “AI that can do things” to “AI that can be trusted to do things.”

The next wave of agent products won’t be ones that are powered by the single smartest model.

It’ll be the stack that combines:
- specialized models
- trusted runtimes
- scoped identity
- action-level permissions
- audit by default