Hello

I'm Brian Feeny — AI/ML architect, Cornell instructor, and chronic overthinker. This is where I write about AI, machine learning, data, and whatever else I can't stop thinking about.

More on the about page.

Featured

• Token Economics on Amazon Bedrock: Prompt Caching and Tool Catalogs

  26 Sep, 2026

  Advice on LLM cost is usually advice on token counts. On Bedrock that is the wrong objective: a request spends in two currencies that disagree, and in an agentic loop what governs cost is whether the prefix is still cacheable. Two AWS recommendations applied together cost 18-20% more than either alone, the crossover tracks catalog tokens rather than tool count, and prompt caching makes output more deterministic, not less.

• Tenancy, Rate Limits and PII Masking on AgentCore Gateway

  23 Sep, 2026

  Three articles of per-tenant controls — budgets, caches, rate limits — all keyed on a header any caller could set. Replacing it with a validated token costs 0.53 ms. Along the way: why a request-rate limit cannot protect a token quota, why a cache hit was silently stealing quota it never spent, and why the PII screen that costs 50x less is the one you must not use.

• Semantic Caching for LLMs on AWS

  23 Sep, 2026

  An exact LLM cache almost never hits, and the obvious fix — serve the answer to the nearest stored prompt — is worse than no cache: the near-misses that change the answer sit closer in embedding space than the paraphrases that don't. A verification stage fixes the ranking and leaves a 5% floor of confidently wrong answers that you cannot measure in production. Built on DynamoDB vector search, measured three ways, and mostly an argument for not running it.

• Customizing inference on AgentCore Gateway: a plugin pipeline for routing, budgets and guardrails

  22 Sep, 2026

  Every model call through Amazon Bedrock AgentCore Gateway passes one place where you can check a budget, clamp tokens, run a guardrail, pick the model, cache the answer and meter the cost. A reference architecture that makes each of those a swappable plugin, deployed and measured, plus seven things about interceptors the documentation does not tell you.

• Scaling LiteLLM on AWS

  Updated:22 Sep, 2026

  A reference architecture and operating guide for running LiteLLM as an enterprise LLM gateway on AWS with Amazon Bedrock, plus the FinOps, governance and security work that scales with it, and a managed alternative on AgentCore Gateway.

• Replicating RouteLLM on Amazon Bedrock

  21 Sep, 2026

  Prompt-only LLM routers post strong in-distribution scores that are almost entirely recognition of which group a prompt came from. A reproduction of RouteLLM on Amazon Bedrock and AgentCore Gateway, a diagnostic suite that exposes it, and a zero-cost deferral rule that works where prompt-only routing does not.

• A telnet daemon for MorphOS, or: how to attach a shell to a socket with no pty

  19 Sep, 2026

  MorphOS never shipped a telnet daemon. Building one meant confronting the fact that the Amiga lineage has no pseudo-terminals — and that the answer is stranger and more interesting than a port. A short tour of the design, the war stories, and why it is really groundwork for an sshd.