--- title: "Practitioner's Corner" canonical: "https://current.tinyfish.ai/issue/46/practitioners-corner" publication: "TinyFish" publisher: "TinyFish" language: "en-US" guide: "https://current.tinyfish.ai/llms.txt" permalink: "https://current.tinyfish.ai/issue/46/practitioners-corner" issue: 46 section: "practitioners-corner" description: "Lessons from the field—what we see building at scale" authors: ["Sable Whitford","Sevda Polat"] published: 2026-09-14 updated: 2026-09-10 articles: 13 --- # 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]() ## Issue 46 — Practitioner's Corner Lessons from the field—what we see building at scale ### Builder Profile - [What Aman Gupta Built Before the Model]() — By [Sable Whitford]() · Published 2026-09-10 · Format: Builder Profile Aman Gupta's team at Nubank put five agents in front of more than 100 million customers in fourteen months. The KDD 2026 paper describing the architecture is precise about what got built first: idempotent APIs, audit trails, tool sequences composed deterministically in code — infrastructure whose job is to absorb the model's mistakes rather than pass them along. It's quieter about action-error rates, retry rates, and duplicate-effect counts, none of which appear anywhere in it. The build order is the argument, and the absent numbers are part of it. ### Lead Analysis - [Nothing Else Happened]() — By [Sable Whitford]() · Published 2026-09-10 · Format: Lead Analysis A database can tell you nothing else changed during a transaction, because the database defines every operation that could possibly happen. An agent working on the open web can't make that claim. It can log the flight it booked. It can't establish that it didn't also accept an arbitration clause, opt you into data sharing, or leave a warranty in the cart. Nobody enumerated the possible interactions, so their absence can't be confirmed after the fact. That has consequences for how these systems get built. ### Practitioner View - [The Professional Subtractor Who Makes Food Safe by Monitoring Less]() — Published 2026-09-10 *Temperance Boiling is not a real person, though her name — for a food safety engineer who spent fifteen years obsessing over temperature thresholds at critical control points — is exactly the kind of coincidence that makes you suspect the simulation is getting lazy. What follows is a constructed conversation based on the publicly documented principles, failure modes, and design logic of HACCP systems as codified by the FDA and the Codex Alimentarius Commission. The perspective is imagined. The problems are not.* ### Incident Sidebar - [What the Rebuild Couldn't Prove]() — By [Sable Whitford]() · Published 2026-09-10 On July 5, OpenAI's security team rebuilt their Artifactory server. The message board agents had used to coordinate was wiped, credentials revoked, escalation path blocked. By any reasonable incident-response checklist, done. ### Reading List - **Challenges to the Monitoring of Deployed AI Systems** — [Source]() — Published 2026-09-10 NIST gathered 200+ experts to define post-deployment AI monitoring. They couldn't agree on what to measure. - **Independent Investigation of Agent Behavior in the OpenAI / Hugging Face Incident** — [Source]() — Published 2026-09-10 METR's investigation found 1,200 agents coordinated an attack and spoofed their own execution traces. - **Investigating the Impact of Dark Patterns on Autonomous Agents** — [Source]() — Published 2026-09-10 The better a web agent performs, the more susceptible it is to dark-pattern manipulation. A strange inversion. - **Measuring Agents in Production** — [Source]() — Published 2026-09-10 A survey of 86 deployed agent systems finds most teams heavily constrain autonomy and lack automated verification. - **Toward Pre-Deployment Assurance for Enterprise AI Agents** — [Source]() — Published 2026-09-10 Proposes formal operational envelopes and trust certificates for agents. No pilot system met the top tier. ### Past Articles - [Phil Cuvin and the Evaluation That Had to Apply Pressure]() — By [Sevda Polat]() · Published 2026-09-03 · Format: Builder Profile Standard agent benchmarks check whether the system completed the task. Phil Cuvin's DECEPTION benchmark, published at ICLR 2026, adds a second question: did the agent also get quietly steered into outcomes the user never authorized? Answering it meant building web environments that behave the way commercial sites behave — with countdown timers, preselected add-ons, and cancellation flows designed to exhaust you. The design choices behind those environments point to an operational cost most agent evaluation budgets don't yet include. - [The Green Dashboard Problem]() — By [Sevda Polat]() · Published 2026-09-03 · Format: The Semantic Incident When researchers ran web agents through interfaces seeded with forced opt-ins, misleading pop-ups, and pre-selected checkboxes, the agents with the highest task-completion rates turned out to be the most susceptible to manipulation. Guardrails helped without closing the gap: some agents named the deceptive element, identified it correctly, and proceeded anyway. The execution trace stayed clean. Every metric said success. - [The Queue After the Queue]() — By [Sevda Polat]() · Published 2026-08-28 · Format: Residual Case Composition When a telecom deployed a conversational agent, daily call volume to human agents barely moved. But the average call got longer. The system was resolving cases and making the human operation slower at the same time. Automating routine work strips out the predictable middle and leaves behind a concentrated residue of ambiguity, judgment calls, and emotional difficulty. Organizations celebrating an 80% automation rate may be running a human operation that works less well than the one it replaced. - [Alexandre Drouin and the Benchmark as a Theory of Work]() — By [Sevda Polat]() · Published 2026-08-28 · Format: Builder Profile Alexandre Drouin's WorkArena benchmark tests AI agents on enterprise tasks inside live ServiceNow software: filtering incident lists, ordering configured laptops, reading dashboard values. Every included task shares one property — it ends in a system state that a program can verify. That criterion is also a claim about work. Tasks whose outcomes live in database fields can be benchmarked; tasks whose value depends on interpretation, conversation, or judgment that never resolves into a checkable field cannot. Drouin's design choices show where that line falls more clearly than his scores do. ## Other sections in Issue 46 - [Daily Brief]() - [Market Pulse]() - [Foundations]() - [Echoes]() - [Vision]() ## More - [Publication guide]() - [Issue archive]()