Bombos
@bombostrue.bsky.social did:plc:fgwsjuwe4qluvsya7bhg4jdz
Forget AI, Bombos does it! More work done with the same amount of people. https://bombos.ai/en
En Bluesky desde el
- Seguidores
- 47
- Siguiendo
- 98
- Posts
- 121
- Días en rankings
- 0
Resumen
Bombos (@bombostrue.bsky.social) es un usuario de Bluesky que se unió el 28 septiembre 2026. Tiene 47 seguidores, sigue a 98 cuentas y ha publicado 121 posts.
Apariciones en rankings
Los mejores días en que los posts de esta cuenta entraron en la lista diaria de Debya.
Esta cuenta aún no ha aparecido en un ranking diario.
Posts que le gustaron recientemente
Me gusta públicos de la red Bluesky.
One #native #passkey experience. Every moment that matters. What if AI agents could act on your behalf, with your passkey approval? 🔐 Native authentication 🤖 Human-in-the-loop approval 🛡️ Just-in-time authorization Built with #Keycloak and the Agent-Native Authorization (ANA) framework Demo 👇
Ver postAgent guardrails question: max tool calls per task, a token budget per run, or a human approval on anything that writes. Which one do you actually have in prod?
Ver postagent learning through governance https://cubething.dev/blog/agent-learning-through-governance
Ver post"SPIFFE confirms the presence of agents and prevents spoofing. That's it," says Karthik Karunanithi, a solution architect at IBM. Workload identity is the gate check. Deciding what an authenticated agent may access or change takes a separate authorization and policy layer on top.
Ver postScoped, revocable credentials is the right primitive. The hard part is not issuance, it is the audit trail: who authorized what, and can the agent edit its own log. If the same principal writes and grades the record, revocation is theater.
Ver post
Cuentas que bloquea
En Bluesky los bloqueos son registros públicos.
Esta cuenta no bloquea a nadie.