---
title: "Practitioner's Corner"
canonical: "https://current.tinyfish.ai/issue/21/practitioners-corner"
publication: "TinyFish"
publisher: "TinyFish"
language: "en-US"
guide: "https://current.tinyfish.ai/llms.txt"
permalink: "https://current.tinyfish.ai/issue/21/practitioners-corner"
issue: 21
section: "practitioners-corner"
description: "Lessons from the field—what we see building at scale"
authors: ["Nora Kaplan","Rina Takahashi"]
published: 2026-03-22
updated: 2026-03-19
articles: 9
---

# TinyFish

> CURRENT is a journal about AI agents in production, for the engineering and product leaders who have to make them work. Drawing on experience building enterprise web agents, it explains why the demo succeeded and the deployment didn't, and what that means for choosing vendors, briefing the board, and avoiding mistakes others have already made.

[Read on the website](<https://current.tinyfish.ai/issue/21/practitioners-corner>)

## Issue 21 — Practitioner's Corner

Lessons from the field—what we see building at scale

### The Translated Dependency

- [The Next Translation Layer](<https://current.tinyfish.ai/issue/21/practitioners-corner/article/11694/markdown>) — By [Nora Kaplan](<https://current.tinyfish.ai/team/26/markdown>) · Published 2026-03-19 · Format: The Translated Dependency

The IRS's Individual Master File has been running since 1961. It was supposed to be replaced decades ago. Instead, layer after layer of new technology grew around it—databases, portals, APIs—each one promising to make the last one obsolete. None did. And at some point, the logic that kept things working migrated out of the code and into the people operating it. The workarounds became the process.

### Building for Breakage

- [Building Browser Agents for a Web That Fights Back](<https://current.tinyfish.ai/issue/21/practitioners-corner/article/11695/markdown>) — By [Rina Takahashi](<https://current.tinyfish.ai/team/25/markdown>) · Published 2026-03-19 · Format: Building for Breakage

A government portal in Delaware goes offline at night. A dropdown is actually a textbox. A checkbox arrives pre-checked, hoping nobody notices. The web is a collection of pages to read and forms to fill. It is also, for anything trying to automate those forms, an adversary: elements misidentified, structures obfuscated, layouts rearranging between visits. Most browser agents get built as though the environment cooperates.

### Three Failed Modernizations

- [I Am the Diagram](<https://current.tinyfish.ai/issue/21/practitioners-corner/article/11696/markdown>) — Published 2026-03-19

*The following interview is a composite construction. Marisol Vega-Lundquist is not a real person. She is built from publicly documented patterns of government IT modernization failure, GAO reports, and the operational realities described by actual state workforce agency officials during and after the COVID-19 unemployment surge. Her specifics are invented. Her situation is not.*

### The Broken Simulation

- [Amazon's AGI Lab Is Building Faithful Copies of Broken Software to Train Its Most Advanced Agents](<https://current.tinyfish.ai/issue/21/practitioners-corner/article/11697/markdown>) — Published 2026-03-19

Every enterprise AI pitch starts the same way: modernize the stack, add APIs, escape the legacy mess. Amazon's AGI Lab is running the opposite play. Its researchers build reinforcement learning gyms that faithfully reproduce decades-old software, quirks included. Modal windows appearing late. Fields rejecting input until some other value saves first. Forms silently resetting midflow.

### Further Reading

- **How Agentic AI Helps Heal the Systems We Can't Replace** — [Source](<https://www.amazon.science/blog/how-agentic-ai-helps-heal-the-systems-we-cant-replace>) — Published 2026-03-19

Reframes legacy system quirks as training signal, not obstacles. The sharpest inversion of the replacement narrative this week.

- **5 AI Agent Failure Patterns and Production Fixes** — [Source](<https://earezki.com/ai-news/2026-03-07-5-ai-agent-failures-that-will-kill-your-production-deployment-and-how-i-fixed-them/>) — Published 2026-03-19

Practitioner taxonomy of what breaks when agents meet production logic they weren't trained to expect.

- **Agentic AI Is Forcing Analytics and Operations to Converge** — [Source](<https://www.theregister.com/2026/03/17/agentic_ai_forcing_analytics/>) — Published 2026-03-19

Agents dissolve the workload boundaries enterprise data architecture was built around. The infrastructure consequences are just starting.

- **The State of AI and Browser Automation in 2026** — [Source](<https://www.browserless.io/blog/state-of-ai-browser-automation-2026>) — Published 2026-03-19

Governance and observability layers between browser agents and legacy portals remain mostly human-shaped. Useful ecosystem snapshot.

- **Why AI Pilots Fail in Production and the 2026 Integration Roadmap** — [Source](<https://composio.dev/blog/why-ai-agent-pilots-fail-2026-integration-roadmap>) — Published 2026-03-19

Frames the gap as an OS problem: models work, but the operating layer for enterprise integration doesn't exist yet.

## Other sections in Issue 21

- [Daily Brief](<https://current.tinyfish.ai/issue/21/daily-brief/markdown>)
- [Market Pulse](<https://current.tinyfish.ai/issue/21/market-pulse/markdown>)
- [Foundations](<https://current.tinyfish.ai/issue/21/foundations/markdown>)
- [Echoes](<https://current.tinyfish.ai/issue/21/echoes/markdown>)
- [Vision](<https://current.tinyfish.ai/issue/21/vision/markdown>)

## More

- [Publication guide](<https://current.tinyfish.ai/llms.txt>)
- [Issue archive](<https://current.tinyfish.ai/issues/markdown>)
