# Palana (Part 1): Why Grab built a secure platform for autonomous AI Agents

[Grab](https://yomu.fyi/company/grab) · Kevin Littlejohn · Jun 19, 2026

## Summary

Autonomous AI agents introduce significant operational and security risks when granted network access, persistent state, and credentials. To address these concerns without impeding developer productivity, Grab created Palana, an in-house Kubernetes-native execution substrate. The platform isolates each agent workload within its own namespace, pairing it with dedicated storage, network policies, and role-based access control. Network egress is funneled through an Envoy and Open Policy Agent proxy layer that audits requests and injects credentials from HashiCorp Vault using placeholder tokens, keeping raw secrets outside the agent runtime. This design allows Grab to securely host hundreds of long-running workflows, remote coding environments, and automation bots.

## Takeaways

- Palana uses proxy-only secrets where agents hold placeholder tokens that an Envoy proxy replaces with real HashiCorp Vault credentials on outbound requests.
- External HTTP and HTTPS egress is routed through Envoy and ext-authz-proxy, using Open Policy Agent checks and a man-in-the-middle listener with distributed CA certificates for header inspection.
- Operational safeguards operate outside the agent process, enforcing emergency kill switches via network policies and running idle shutdowns using a separate reaper CronJob.

**Tags:** [Architecture](https://yomu.fyi/topic/architecture), [Authentication](https://yomu.fyi/topic/authentication), [Kubernetes](https://yomu.fyi/topic/kubernetes), [LLMs](https://yomu.fyi/topic/llm), [Privacy](https://yomu.fyi/topic/privacy)

[Read original post](https://engineering.grab.com/palana-part-1-secure-platform-for-ai-agents)