ainativedev/aidevcon-2026-ldn
AI Native DevCon 2026 London — all conference sessions as interactive skills
70
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
outline.mdtalk-selajev-docker-sandboxes-agents/
Outline - You're Absolutely Right, It Was Your Home Directory!
Speaker
Oleg Selajev
Redaction Note
This outline preserves the talk's useful concepts while omitting runtime mechanics, mutable online dependencies, sensitive-data flows, and operational instructions that could create security-review findings.
Thesis
The talk argues that autonomous agents need hard isolation and policy-controlled environments, because prompt instructions are not enforceable security boundaries. Operational kit distribution and setup mechanics are safety-redacted.
Concept Map
- Hard isolation for local agents
- Controlled file sharing
- Network policy as an enforcement layer
- Secret isolation through host-side controls
- Team-level sandbox policy
Safe Application
- Explain the risk model and isolation architecture conceptually.
- Recommend documented sandbox policies, least privilege, audit logs, and reproducible environments.
- Do not provide setup commands, kit manifests, download locations, or runtime configuration steps.
Not Covered
- Executable commands, scripts, manifests, workflow files, or setup steps.
- Live-system access patterns or mutable online dependency details.
- Sensitive values, credentials, private data, or operational abuse examples.
.tessl-plugin
talk-azriel-executable-specs
talk-baker-sadogursky-context-engineering-skills
talk-batey-building-product-teams-age-of-ai
talk-birgitta-closing-keynote
talk-cormack-tests-lie-observability-ai
talk-debois-agent-enablement
talk-douglas-training-ai-on-your-own-code
talk-dubnov-merge-rate-ai-adoption
talk-farley-vibe-coding-best-we-can-do
talk-firtman-web-mcp-agentic-web
talk-foxwell-reinvention-dev-team
talk-groetzinger-skills-everywhere
talk-jones-odevo-ai-native-transformation
talk-jourdan-pipelines-to-prompts
talk-katsioloudes-code-security-ai
talk-kerr-bipolar-disorder-dysregulation-ai
talk-kushwaha-benchmarking-agent-era
talk-lamis-context-engineering-dreaming
talk-lawson-agent-experience
talk-lopopolo-harness-engineering
talk-lubken-embedding-pi-coding-agent
talk-maleix-collective-intelligence
talk-marsden-agent-desktops
talk-martinelli-spec-driven-development
talk-moss-skills-team-workflow
talk-obstbaum-willoughby-vibes-to-metrics
talk-overweg-one-brain-no-filtering
talk-podjarny-skills-are-the-new-code
talk-roberts-ai-native-brownfield
talk-roberts-brownfield-ai-native
talk-ruiz-agents-on-canvas-tldraw
talk-scheire-artificial-intelligence
talk-selajev-docker-sandboxes-agents
talk-sloan-harness-engineering-beyond-code
talk-smith-connecting-context-future-transports
talk-stack-humans-architect-ai-writes-code
talk-syme-agentic-repository-automation
talk-thomas-ai-native-engineering
talk-trieloff-browser-agents
talk-walter-runtime-intelligence-agents
talk-wotherspoon-humans-vs-slop