astrid retweeted
mi fantasía sexual es borrar todo rastro de mi existencia y empezar otra vida desde cero
astrid retweeted
every ai builder promised speed, none of them promised memory
bolt, new skills fixes the actual bug: you shouldn’t have to reintroduce your company every time you open a prompt box
🤝 Paid partnership
astrid retweeted
The quiet part of this launch: your team's expertise stops living in one person's head.
Every skill someone builds becomes available to everyone else instantly.
That's the kind of thing that looks small today and compounds hard in six months.
astrid retweeted
la mayoría hace tutoriales de 5 minutos de CLAUDE, este tipo hizo 4 horas
precios, prompting avanzado, mcp, subagentes, cursor, construcción de apps reales
está en inglés pero es tan visual que da igual si no lo hablas perfecto
astrid retweeted
las rebajas de verano en españa significan que cada marca pequeña necesita 47 fotos de producto de la nada y presupuesto cero para un shooting
yo hice este set con la función de imágenes de producto de pollo ai, mismo producto, 3 escenas distintas, sin estudio, sin equipo, sin problemas con la luz
@PolloAIES me dio todo el catálogo y ni tuve que esforzarme 👇🏼
🤝 Paid partnership
astrid retweeted
Un estudiante de 21 años en Ankara, estudiante de ingeniería de software y todavía vive en la residencia universitaria.
Pasó un mes escribiendo un trading bot. Cuando todo estuvo listo, le dio a "iniciar". Esa misma noche ganó 14 mil dólares.
Ni él mismo se lo creía. El setup no era tan complicado como pensaba.
Me contó los detalles. El core stack son tres cosas: OpenAI Codex, Claude Opus 4.7 y la Polymarket CLOB API.
La lógica es esta: cuando sale una noticia importante, la probabilidad en Polymarket se actualiza en pocos segundos, pero el orderbook se queda lleno al nivel anterior. Esa ventana dura entre 30 y 90 segundos. El bot escanea el feed de noticias de Bloomberg y Reuters, y aplica la fórmula:
ΔP(t) = α · news_score · e^(-λt)
α es la elasticidad de la noticia respecto al mercado. λ es la velocidad de propagación de la información. La posición se cierra antes de que el precio vuelva a su nivel.
La ejecución se hace a través de Polymarket CLOB. No hay ningún prompt manual a Claude tipo "abre un long en este nivel". El bot funciona por su cuenta.
Ahora mismo está en 50-70 mil dólares al mes. A este ritmo, son 600 mil dólares al año.
Hace un mes, en la habitación de la residencia tenía un laptop, Claude Pro y una API key de Polymarket. Ahora tiene esto.
astrid retweeted
your agent used to wait for your prompt, now it’s the one pinging you for approval
the org chart just flipped and nobody sent a memo
#HyperagentPartner
🤝 Paid partnership
astrid retweeted
mi lista de pendientes ya tiene agentes, ellos trabajan y yo no
zaro construye la app y la mantiene actualizada mientras yo finjo estar ocupada en juntas
Today, we're excited to launch Zaro.
Your knowledge is scattered across Slack threads, email chains, Google Docs, Notion pages, and calendar invites. Everyone's asking the same questions, chasing the same updates. Context dies the moment you switch tabs. It's exhausting and it's everywhere.
Zaro ends that.
One workspace. Connect your tools, drop in your files, and build apps that stay live with your data. Spin up agents that compile your briefings, chase deadlines, and keep the busywork off your plate. No more hunting. No more "where is that doc?"
Everything you know, finally working for you.
You can sign up now at Zaro.ai
For more information comment below! We have also just launched on Product Hunt so we'll be answering comments there all day too!
Today, we're excited to launch Zaro.
Your knowledge is scattered across Slack threads, email chains, Google Docs, Notion pages, and calendar invites. Everyone's asking the same questions, chasing the same updates. Context dies the moment you switch tabs. It's exhausting and it's everywhere.
Zaro ends that.
One workspace. Connect your tools, drop in your files, and build apps that stay live with your data. Spin up agents that compile your briefings, chase deadlines, and keep the busywork off your plate. No more hunting. No more "where is that doc?"
Everything you know, finally working for you.
You can sign up now at Zaro.ai
For more information comment below! We have also just launched on Product Hunt so we'll be answering comments there all day too!
astrid retweeted
notion, instacart, gusto, opendoor, dbt, angelList, lemonade all quietly admitting their agents were one bad prompt away from a security incident
🤝 Paid partnership
Today, we’re announcing Runlayer has raised $30M from Felicis and Khosla Ventures to help companies go all in on AI.
Runlayer is the golden path for AI: enablement, security, and control in one platform.
So, how does it give your team the right tools for AI? 🧵
Runlayer: Go all in on AI
The golden path for enterprise: AI enablement, security, and control in one platform. Trusted by Instacart, Gusto, dbt Labs, and many of the F500s. Everything you need to go all in on AI.
astrid retweeted
integrations used to take 4-8 weeks to build
Parloa collapsed that to hours and the agent self-heals when something breaks🥱
🤝 Paid partnership
Introducing Parloa’s Agent Skills: a better way for CX leaders to connect AI agents to the enterprise systems they need to get real work done.
To resolve customer issues, your agent needs to talk to your CRM, booking engine, ticketing platform, and compliance requirements. These connections typically require significant engineering work, delaying AI agent go-lives.
To accelerate the deployment time, we built Agent Skills on MCP (Model Context Protocol). Now, business teams can configure full integration chains directly in Parloa’s AI Agent Management Platform (AMP), with no code or middleware:
> Time to build integrations drops from up to 4-8 weeks to a matter of hours
> Every tool call follows the same logic and self-heals when something goes wrong
> Success Conditions let you define what “done” means for each task and track real outcomes
> Every execution chain is auditable, retryable, and owned by your business team
The early results speak for themselves:
- 67-second reduction in average handle time
- 39% improvement in customer communication during call transfers
- 20% more reliable routing in multi-tool environments
Learn more about how Parloa’s Agent Skills work: parloa.com/blog/agent-skills…


















