# Tony > Tony: offensive security and security engineering, working across penetration testing, adversary simulation, cloud infrastructure and autonomous AI systems. Personal site of Tony: Security. Systems. Software. Every page is also available as Markdown at the same path with a .md extension (listed below). Work entries describe types of work repeated across many engagements, never specific clients. Posts marked (draft) are work in progress. ## Pages - [Tony](https://satunix.github.io/site/index.md): Introduction and key information. - [Work](https://satunix.github.io/site/work.md): Representative engagement types (types of work, never specific clients). - [Projects](https://satunix.github.io/site/projects.md): Personal research and experiments: agent security, autonomous systems, private AI. - [CV](https://satunix.github.io/site/cv.md): Roles, capabilities, credentials and skills. - [Links](https://satunix.github.io/site/links.md): Profiles and feed. - [Writing](https://satunix.github.io/site/blog.md): Index of posts, newest first. ## Writing - [Why more agent autonomy creates a security architecture problem](https://satunix.github.io/site/blog/agent-autonomy-is-a-security-architecture-problem.md) (draft): Authority, delegation, trust boundaries and least privilege, once the thing acting on your behalf makes its own decisions. - [Why agent memory is not just a vector database](https://satunix.github.io/site/blog/agent-memory-is-not-a-vector-database.md) (draft): Task state, provenance, authority and time all matter. Similarity search alone captures none of them. - [Agents need a control plane, not just a system prompt](https://satunix.github.io/site/blog/agents-need-a-control-plane.md) (draft): A system prompt is a request, not a boundary. Tool-using agents need enforcement that sits outside the model. - [Pentesting cloud IAM as a graph problem](https://satunix.github.io/site/blog/cloud-iam-as-a-graph-problem.md) (draft): Roles, trust policies, STS and cross-account access form a graph. Testing it means finding paths, not misconfigurations. - [Designing cyber agents that know their rules of engagement](https://satunix.github.io/site/blog/cyber-agents-and-rules-of-engagement.md) (draft): Scope should be enforceable machine state, not prose buried in a prompt. - [Dynamic delegation: letting agent topology follow the problem](https://satunix.github.io/site/blog/dynamic-delegation.md) (draft): Fixed multi-agent org charts may be the wrong abstraction. What if structure formed around each task instead? - [Building an evidence-first AI pentesting agent](https://satunix.github.io/site/blog/evidence-first-pentest-agents.md) (draft): Findings, tool calls and conclusions should all resolve back to evidence. A design for AI-assisted testing that keeps humans in charge. - [From pentester to adversarial systems engineer](https://satunix.github.io/site/blog/from-pentester-to-adversarial-systems-engineer.md) (draft): Offensive security increasingly runs through cloud, identity, APIs, CI/CD and autonomous systems. The job is changing shape. - [Local AI as security infrastructure](https://satunix.github.io/site/blog/local-ai-as-security-infrastructure.md) (draft): Privacy, model control, isolation and reproducibility: why running models yourself matters beyond cost. - [Building offensive infrastructure as infrastructure](https://satunix.github.io/site/blog/offensive-infrastructure-as-infrastructure.md) (draft): C2, telemetry, test environments and deployment pipelines deserve the same engineering discipline as production systems. - [Recursive agents and the context problem](https://satunix.github.io/site/blog/recursive-agents-and-the-context-problem.md) (draft): How does a subagent know what it needs without inheriting the entire parent context? - [Running 27B models on constrained hardware](https://satunix.github.io/site/blog/running-27b-models-on-constrained-hardware.md) (draft): Quantisation, the VRAM/RAM split, context size and throughput: lessons from running mid-size models on hardware that is not built for it. - [The approval came after the action](https://satunix.github.io/site/blog/the-approval-came-after-the-action.md) (draft): An agent changed a file before the approval prompt said it was allowed to. Why UI-level approvals are not enforcement. - [TTFT is often more important than tokens per second](https://satunix.github.io/site/blog/ttft-matters-more-than-tokens-per-second.md) (draft): For interactive and agent workloads, waiting for the first token shapes the experience more than raw generation speed. - [What adversary emulation is actually for](https://satunix.github.io/site/blog/what-adversary-emulation-is-for.md) (draft): Not a trophy hunt. Attack-path discovery, telemetry, visibility gaps and proving that detections and playbooks work. ## Optional - [Everything in one file](https://satunix.github.io/site/llms-full.txt): all pages and posts concatenated - [RSS feed](https://satunix.github.io/site/rss.xml): finished posts only - [Sitemap](https://satunix.github.io/site/sitemap-index.xml)