Patrick Joubert

CEO @RippletideCo | Your agent decided in production. Can you reproduce it? | Decision runtime for AI agents | 3x founder, 3x exits: SAP, CircleCI, Steria

[Tracer (YC S26) @TracerML]

Today, we’re introducing Echo: one adaptive model built entirely from a pool of open-weight models.

On our first internal task mix, Echo reached Fable-level results at roughly 1/3 of the total inference cost.

Try it: https://t.co/oIymERQqB2

[Thinking Machines @thinkymachines]

Today, we are introducing Inkling.

Inkling reasons efficiently across text, image, and audio modalities. We are making the full weights available.

https://t.co/Ghebq5mG30

Available today for fine-tuning on Tinker. Play with it in the Inkling Playground. 🧵

[Lee Robinson @leerob]

New open model from Thinking Machines!

1T MoE, 1M context, multimodal, some solid evals.

Really nice blog post 👏

[Patrick Joubert @Patricksclouds]

ACTION is the word everyone loves in San Francisco right now.

AI agents can search, write, call tools and update systems.

But production asks a harder question: who gave the agent the right to act?

Action is easy to demo. Accountable action is what gets deployed.

[OpenAI Developers @OpenAIDevs]

Show Codex a workflow once. Reuse it as a skill.

Record & Replay lets you show Codex a recurring task, like filing an expense report or submitting a time-off request.

Codex turns that demo into an inspectable, editable skill.

You control when recording starts and stops.

[Sam Altman @sama]

we love you too!

[Greg Brockman @gdb]

Major ChatGPT upgrade rolling out now, in the form of GPT-5.5 Instant:

[Marcelo P. Lima @MarceloLima]

Boris Cherny of Anthropic on $NOW: "If I'm doing something and I don't have the context, I'm not going to do a great job... ServiceNow is a really a great way to bring in that context that it needs to do the job."

[Sahil Panhotra | Indie Builder @SahilPanhotra]

@steipete it is good thing ? right?

[Patrick Joubert @Patricksclouds]

One of the best pieces of product engineering analysis I’ve read this year.
The key insight: the prompts aren’t documentation. They’re compiled product decisions. Every line reveals a tradeoff, initiative vs. overreach, memory vs. noise, speed vs. cache cost. Anthropic didn’t write instructions for an LLM. They wrote an operational philosophy.
The Claude vs. Codex framing is the most useful for builders. Claude pushes toward initiative. Codex pushes toward precision. Two different theories of what an agent should do when facing ambiguity, one says “move forward,” the other says “don’t drift.”
The deeper takeaway: prompt cache isn’t an infra optimization. It’s a design constraint that shapes observable product behavior. When token economics drive UX decisions, you’re doing cost architecture, not just engineering.
And for anyone building agentic systems: the value is no longer in the model. It’s in the decision layer that controls what the model does and what it doesn’t.

[Thomas Molinier @randomtryidk]

https://t.co/3dfUSQavrl

[Thomas Molinier @randomtryidk]

https://t.co/3dfUSQavrl

[Patrick Joubert @Patricksclouds]

@RampLabs “Self-maintaining” is a bold claim when no code merges without engineer review
@AlexAuroraDev

[Patrick Joubert @Patricksclouds]

@RampLabs “Self-maintaining” is a bold claim when no code merges without engineer review
@AlexAuroraDev

[Patrick Joubert @Patricksclouds]

@JasonSCui @a16z published the clearest diagnosis of enterprise AI failure I've read from an investor.
Thesis: agents fail because they're blind. Build a context layer.
I agree. And that's why I wrote this.
Context tells an agent what to know. It doesn't tell it what it's authorized to do.
A bad answer is an error. A bad action is an incident.
Context layers are the prerequisite. Decision layers are the guarantee.
→ https://t.co/V80CZdF1mm

[Y_B @Yann_Bilien]

https://t.co/36fhz5bcoT

Hey @garrytan, just shared the addition I use in gstack: plan enforcement using the Claude Code hooks. helped beat the 5 tabs ceiling

Feel free to incorporate if it makes sense to others https://t.co/YG8MEL6Qq9

[Patrick Joubert @Patricksclouds]

@JasonSCui @a16z published the clearest diagnosis of enterprise AI failure I’ve read from an investor.
Thesis: agents fail because they’re blind. Build a context layer.
I agree. And that’s why I wrote this.
Context tells an agent what to know.
It doesn’t tell it what it’s authorized to do.
A bad answer is an error.
A bad action is an incident.
Context layers are the prerequisite. Decision layers are the guarantee.
→ https://t.co/V80CZdF1mm

[Y_B @Yann_Bilien]

https://t.co/8vo4oFSiPW

[Patrick Joubert @Patricksclouds]

Keycard, https://t.co/vMOn33dnBw, Operant AI. Three new products launched around RSAC 2026, all framing it as "guardrails." The distinction worth making: guardrails block categories of action. A decision runtime validates the specific action your agent is about to take, against your rules, before it executes.

[Patrick Joubert @Patricksclouds]

Oracle just put AI agents in charge of finance and procurement decisions. Massive. And the right next question isn't "will it work?" It's "can you replay what the agent knew and decided, six months from now?" That's what makes it enterprise-grade.