> Markdown version of [/videos/100444-give-the-agent-a-budget-not-a-token?t=786](https://www.wearedevelopers.com/videos/100444-give-the-agent-a-budget-not-a-token?t=786). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Give the Agent a Budget, Not a Token

An empty bash variable can cause a helpful AI to wipe out staging workloads. Protect your infrastructure by giving agents regenerating action budgets instead of static tokens.

- **Speakers:** [Sachin Malhotra](https://www.wearedevelopers.com/@sachin-malhotra)
- **Event:** World Congress 2026 North America
- **Published:** September 25, 2026
- **Duration:** 26:00
- **URL:** https://www.wearedevelopers.com/videos/100444-give-the-agent-a-budget-not-a-token

## Access

Playback and chapters for this video are available with a Free account.

## Related Moments

- [Why tool-using AI agents require behavioral governance](https://www.wearedevelopers.com/videos/100518-test-before-release-enforce-at-runtime-governance-for-tool-using-ai-agents) (from "Test Before Release, Enforce at Runtime: Governance for Tool-Using AI Agents")
- [Treating autonomous agents as privileged identities requiring safety guardrails](https://www.wearedevelopers.com/videos/2152-how-to-stop-your-agents-from-going-rogue-arnav-gupta) (from "How to Stop Your Agents From Going Rogue - Arnav Gupta")
- [Mitigating excessive agency through scoped tool access](https://www.wearedevelopers.com/videos/1637-delay-the-ai-overlords-how-oauth-and-openfga-can-keep-your-ai-agents-from-going-rogue) (from "Delay the AI Overlords: How OAuth and OpenFGA Can Keep Your AI Agents from Going Rogue")
- [Managing autonomous agent trust and cloud permission gaps](https://www.wearedevelopers.com/videos/100095-no-keys-for-the-robot-gitops-as-the-control-plane-for-autonomous-agents) (from "No Keys for the Robot: GitOps as the Control Plane for Autonomous Agents")
- [Shifting security models from passive chatbots to active agents](https://www.wearedevelopers.com/videos/2093-from-shadow-ai-to-secure-intelligence-safe-ai-usage-in-the-enterprise) (from "From Shadow AI to Secure Intelligence: Safe AI Usage in the Enterprise")
- [Introduction to securing open source AI agent infrastructure](https://www.wearedevelopers.com/videos/100438-securing-ai-agent-infrastructure-identity-attestation-and-trust-at-scale) (from "Securing AI Agent Infrastructure: Identity, Attestation, and Trust at Scale")

## Related Articles

- [ I Gave a Video Editor More Autonomy Than a Trading Bot. On Purpose.](https://www.wearedevelopers.com/magazine/773-i-gave-a-video-editor-more-autonomy-than-a-trading-bot-on-purpose)
- [Never delegate the understanding](https://www.wearedevelopers.com/magazine/749-never-delegate-the-understanding)
- [AI Eats the Verifiable First](https://www.wearedevelopers.com/magazine/765-ai-eats-the-verifiable-first)
- [Trustworthy AI Starts at Deployment: 5 Checks Before You Ship](https://www.wearedevelopers.com/magazine/753-trustworthy-ai-starts-at-deployment-5-checks-before-you-ship)

## Related Jobs

- [Senior Software Engineer, Sandboxes (Eu Or East Coast Preferred)](https://www.wearedevelopers.com/jobs/ext/2161904-senior-software-engineer-sandboxes-eu-or-east-coast-preferred) at **Docker, Inc.**
- [Staff Software Engineer, Agentic Platform](https://www.wearedevelopers.com/jobs/48464-staff-software-engineer-agentic-platform) at **Docker, Inc.**
- [Senior AI Developer](https://www.wearedevelopers.com/jobs/ext/2836034-senior-ai-developer) at **PwC**
- [Senior AI/ML Engineer](https://www.wearedevelopers.com/jobs/48352-senior-ai-ml-engineer) at **PagerDuty**
- [Staff ML Engineer](https://www.wearedevelopers.com/jobs/48463-staff-ml-engineer) at **Docker, Inc.**
- [Principal Solutions Architect, Professional Services](https://www.wearedevelopers.com/jobs/ext/2739510-principal-solutions-architect-professional-services) at **Docker, Inc.**