Field Notes

Notes from the last mile of enterprise AI

Working notes on responsible AI in production — agentic architectures, governance and risk controls, MCP and A2A, and the practical engineering of trust at enterprise scale.

Responsible AI Agentic Architectures MCP & A2A Security & Governance Enterprise Scale Risk Mitigation
Agent-to-Agent · Aug 24, 2026 · 9 min

The agent that took another agent's word for it

In a multi-agent system, the risky moment isn't the model. It's the hand-off, where one agent takes another's answer and folds it into its own reasoning as settled fact, and the doubt, the source, and the authority behind that answer quietly fall off at the seam. Why agent-to-agent protocol is where identity, provenance, and the audit trail either survive the hop or get laundered into confidence nobody can defend.

Read article
Healthcare & Payers · Aug 17, 2026 · 9 min

The second opinion that has to show its work

An accurate model a clinician won't act on, or a payer can't defend, returns nothing. In medicine the value shows up only when someone signs their name under the decision. Why fairness, privacy, transparency, and human oversight aren't the compliance cost of healthcare AI, but the mechanism that turns an accurate model into a used one, and a pilot into a program that survives its first audit and appeal.

Read article
Evals as a Gate · Aug 10, 2026 · 9 min

The deploy that looked like an edit

Changing a prompt, swapping a model, or handing an agent a new tool changes what your system does in production, yet none of it clears the gate a line of code has to. Why a versioned eval suite is the release control that turns responsible AI from a policy you intend into one you can prove, and why that gate belongs in the substrate.

Read article
Data Lineage & Freshness · Aug 3, 2026 · 9 min

The document you retired is still answering

Grounding ties an answer to a real document, but it never asks whether that document is still true. When a policy is revised or a supplier is suspended, the retired copy sits in the index and keeps answering as if nothing changed. Why lineage, freshness budgets, and retraction propagation are the controls that separate a grounded system from a merely confident one.

Read article
Model Routing · Jul 27, 2026 · 9 min

The biggest model for the smallest job

Sending every request to your best model feels like the safe choice. It's the expensive one, and often not even the better answer. Why routing each request to the smallest model that clears the bar is a cost control and a quality control at once, and why that decision belongs in the substrate, not in every app.

Read article
Identity & Access · Jul 20, 2026 · 9 min

The keys nobody signed for

An agent in production is a user you never onboarded — no name, no scope, no end date, and usually a shared service account with more reach than the task needs. Why non-human identity, least privilege per task, and short-lived credentials are the governance controls that decide how far a compromised agent can travel.

Read article
Grounding & Provenance · Jul 14, 2026 · 9 min

The answer was never the hard part

Any model will hand you a confident answer in seconds. That fluency is free, and it's the trap. In an enterprise, an answer with no idea where it came from is a liability in a nice font. Why grounding, provenance, and the discipline to say "I don't have that" are the real controls behind trustworthy AI.

Read article
AI Assurance · Jul 11, 2026 · 8 min

The half-life of a working model

Software fails loudly. AI erodes quietly. A model that passed its acceptance test in March is not the system running in July, and a governance sign-off that ended at go-live is a photo of a system that already left. Why the real control is the evaluation that never stops running.

Read article
Agentic Architecture · Jul 6, 2026 · 9 min

The swarm you didn't need

The pitch decks keep adding agents. Ours keep removing them. Why the number of agents in your architecture isn't a measure of how advanced it is, but of how much control you've quietly given up, and how it drives your risk and your bill.

Read article
User-First AI · Jun 29, 2026 · 8 min

The co-pilot for everyone else

The whole AI boom was aimed at one person: the developer. Meanwhile the claims analyst, the sourcing manager, and the investigator were still doing the work by hand. Why we build for the person making the decision, not the person shipping the code.

Read article
AI Risk Mitigation · Jun 29, 2026 · 10 min

The blast radius of a helpful agent

A compromised chatbot says something wrong. A compromised agent does something wrong, with your credentials, inside your systems. The security question for enterprise AI isn't whether the model can be tricked. It's how far the damage travels when it is.

Read article
AI Cost Controls · Jun 22, 2026 · 9 min

The bill nobody modeled

The AI sticker shock that lands six months into production is almost never about the price per token. It's about the consumption pattern your architecture quietly committed to — long before anyone looked at an invoice.

Read article
Enterprise Scale · Jun 15, 2026 · 9 min

The floor under the stack

Enterprises don't have an AI problem — they have an AI sprawl problem. Why we build the expensive, dangerous machinery once, and let governance, guardrails, and agents compound across every solution in the portfolio.

Read article
Agentic Architectures · Jun 10, 2026 · 10 min

The protocols beneath the agents

Most enterprise AI conversations argue about model choice. The harder questions are about what the model is allowed to touch, how it talks to other agents, and what that wiring leaves auditable. A field view of MCP and A2A in production.

Read article
Agentic AI · Jun 8, 2026 · 10 min

Agentic AI needs a hand on the wheel

A chatbot can be wrong. An agent can be wrong and act on it. Where autonomy actually breaks down in claims, investigations, and sourcing — and what human oversight has to look like if it isn't going to be a slogan.

Read article
Governance · Jun 7, 2026 · 9 min

The last mile of responsible AI

Policy frameworks have outpaced production reality. The bottleneck in 2026 isn't principles — it's the runtime controls that make those principles enforceable when an agent is actually deciding something on your behalf.

Read article