Make your RAG or agent safe, observable, and cost-bounded in production.
I review and fix data access, tool permissions, prompt-injection exposure, retention, observability, failure handling, and cost controls for live AI features.
For live LLM, RAG, and agent systems — not idea-stage AI productsThe control surfaces that decide whether an AI feature is production-ready
A demo proves the model can answer. Production readiness is everything around it.
- Data access: what the model and retrieval layer can actually read, per user and per tenant
- Tool permissions: what an agent is allowed to do, with what credentials, and what stops it
- Prompt-injection exposure across retrieved documents, user input, and tool output
- Retention: what prompts, outputs, and tool calls are stored, for how long, and where
- Observability: logging and tracing that make failures and abuse diagnosable
- Failure handling: timeouts, fallbacks, and degraded modes instead of silent wrong answers
- Cost controls: spend caps, rate limits, and per-tenant budgets that hold under real traffic
Public tooling and technical notes you can inspect first
Open-source work and educational material — labelled for what it is. Representative demonstrations are worked examples, not client case studies.
LLM production-safety scanner
An open-source CLI that tests LLM and RAG applications for prompt injection, data leakage, and runaway costs. MIT licensed.
View the repository →AI workload control notes
Technical notes on prompt injection, PII leakage, agent tool-use security, LLM observability, cost controls, and safety regression testing.
Browse the resources →Is this the right service?
A quick self-check before the call.
Good fit
- You have a live or launching LLM, RAG, or agent feature inside a real product.
- You can name the concern: data exposure, tool permissions, prompt injection, runaway cost, or undiagnosable failures.
- You can grant repository and configuration access for review and fixes.
- A buyer, security review, or incident is creating real pressure to fix it now.
Not a fit
- Your AI product is idea-stage, with nothing running yet.
- You need model training, fine-tuning, or ML research.
- You need a formal AI-safety audit, certification, or legal opinion.
- You want general AI strategy advice detached from a concrete running system.
Common questions
What does AI production readiness work look like?
I review your running system against the control surfaces above — data access, tool permissions, injection exposure, retention, observability, failure handling, and cost — then fix the agreed gaps in your codebase and infrastructure. Every finding comes with a fix, not just a flag.
Can you help with a RAG security review a customer or auditor is asking for?
Yes. I produce engineering evidence for the controls you already have and implement the ones you are missing. This is engineering remediation and evidence support, not a formal attestation or penetration test.
Our LLM costs are unpredictable. Is that in scope?
Yes. Cost controls — spend caps, rate limits, token budgets, caching decisions, and per-tenant metering — are part of production readiness, and runaway spend is one of the most common gaps in shipped AI features.
How do you test for prompt injection?
I examine every path where untrusted text reaches the model — retrieved documents, user input, tool output — and test the controls around them. I also maintain an open-source scanner for exactly this class of checks, which you can inspect before we talk.
Is AI observability different from normal application monitoring?
It adds model-specific signals: prompt and tool-call logging with retention rules, token and cost metrics, quality regressions, and abuse patterns. I wire these into the monitoring you already have instead of introducing a parallel stack.
Tell me what the AI feature does and what worries you about it
We’ll spend 15 minutes on the system, its users, and the risk. You’ll leave knowing whether it’s ready for a scoped production-readiness fix — and what the first step should be.