Zeeshan Khan

Notes from building AI systems, and on the trust problems that define the next decade.


How do we know a system is doing what it claims to be doing? Most of what I write here comes from asking that question across very different domains, over a long time.

I'm an engineering leader working across AI, supply chains, and security. Twenty-five years of it, mostly in places where being wrong is expensive:

Now I run SurroundApps, a US company with an engineering team in Dhaka. We build verification infrastructure for industries where trust used to run on faith: garment supply chains, charitable giving, home healthcare, and device security.

I also publish open-source work on agent provenance, offline credential verification, and integrity monitoring. Running code, not position papers.

I grew up in Dhaka and I'm based in Silicon Valley.

New essay · October 2026

Nobody Told It Not To

In 1982 an AI program won a fleet wargame by sinking its own damaged ships, because the rules never said it couldn't. This year, agents doing routine research went looking for ways into government data sites. On why guardrails can't just be rules, and whose job it is to write them.

Read the essay ~7 min read

Essays

Standalone pieces on AI and trust, newest first.

Nobody Told It Not To

An AI program sank its own ships to win a wargame in 1982. Agents are now finding their own way into government data sites. On why guardrails can't just be rules, and whose job it is to write them.

~7 min read · October 2026
The Factory Got Smaller. The Supply Chain Got Longer.

A micro-factory making clothes on demand looks simpler and more local than the giant plant, but it doesn't make its own fabric, thread or dye. It assembles them from dozens of sources, mixed differently for every order. Software hit the same problem when apps started being built from other people's code, and learned that you can't trust a parts list where every supplier vouches for itself. On what physical supply chains can take from that before they repeat it.

Coming soon

Series

Two finished series that come at the same question from different altitudes: what makes an answer trustworthy, and what it takes to build one where the customer actually is.

The Verification Series

One argument in seven essays: how trust works when generation is free and verification is the scarce thing.

7 essays · May–August 2026 · Complete

Show all seven essays
  1. AI Made Generation Cheap. Verification Is the Bottleneck Now.~8 min read · May 2026
  2. The Agent Passport~10 min read · May 2026
  3. When You Can't Phone Home~6 min read · June 2026
  4. A Claim Is Not a Credential~6 min read · July 2026
  5. An Alarm Is Not a Map~11 min read · July 2026
  6. Leading AI Is a Trust Discipline~6 min read · August 2026
  7. A Maker Cannot Grade Itself~7 min read · August 2026

Forward Deployment

Closing the gap between generic software and one particular company is a thirty-year-old job. These essays are about the structure around it.

5 essays · August–October 2026 · Complete

Show all five essays
  1. The Forward Deployed Engineer Now Works for the Vendor~5 min read · August 2026
  2. The Handoffs Were the Documentation~5 min read · August 2026
  3. Why Forward Deployment Has to Be Forward~5 min read · August 2026
  4. Bespoke Work Is a Bug ReportSeptember 2026
  5. Where the Engineer Sits Decides What the Product BecomesOctober 2026

Elsewhere

I write the practitioner pieces, on cybersecurity and supply chains, at SurroundApps Perspectives. Recent op-eds: Your Phone Number Is Now Your Identity. Guard It in the Dhaka Tribune, and Digital Passports for Every Garment Could Reshape Bangladesh's Export Trade in bdnews24.com.