# Your Agent Works in the Demo. Now Make It Survive Monday.

DevFeed: [Your Agent Works in the Demo. Now Make It Survive Monday.](<https://devfeed.tech/articles/your-agent-works-in-the-demo-now-make-it-survive-monday-114138.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/your-agent-works-in-the-demo-now-make-it-survive-monday/>)

Author: Gursimar Singh

Published: 2026-11-03T12:30:00Z

Content type: article

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [agent orchestration](<https://devfeed.tech/topics/agent-orchestration.md>), [long-running](<https://devfeed.tech/topics/long-running.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-harness](<https://devfeed.tech/tags/agent-harness.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-engineering](<https://devfeed.tech/tags/agentic-engineering.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [api](<https://devfeed.tech/tags/api.md>), [artifical-intelligence](<https://devfeed.tech/tags/artifical-intelligence.md>), [audit](<https://devfeed.tech/tags/audit.md>), [audit-trail](<https://devfeed.tech/tags/audit-trail.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [blast-radius](<https://devfeed.tech/tags/blast-radius.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [business](<https://devfeed.tech/tags/business.md>), [bytedance](<https://devfeed.tech/tags/bytedance.md>), [case-study](<https://devfeed.tech/tags/case-study.md>), [checkpoint](<https://devfeed.tech/tags/checkpoint.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-code-harness](<https://devfeed.tech/tags/claude-code-harness.md>), [claude-md](<https://devfeed.tech/tags/claude-md.md>), [code](<https://devfeed.tech/tags/code.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [harness](<https://devfeed.tech/tags/harness.md>), [llm](<https://devfeed.tech/tags/llm.md>)

## AI overview

Production agents depend on a harness that controls tools, permissions, memory, checks and human sign-off; the article's core guidance is to let models reason while enforcing boundaries in code. It contrasts rigid, code-defined pipelines with agents that choose steps inside safeguards, using DeerFlow 2.0, Claude Code and MiroFlow as examples. For data cleansing, it recommends deterministic code for testable normalization and exact matches, model proposals with reasons and confidence for ambiguous cases, and expert approval for costly or regulated decisions. The workflow stages writes, records changes and approvers, and supports replay and rollback; its review queue must be staffed to avoid delays or rubber-stamping. Practical steps include assigning each decision to code, a model or a person; limiting autonomy with hard scope and resource caps; checking actions before and after; logging traces; and making changes reversible. Benchmark claims should be checked for data split, subset, run aggregation, grading and comparable model/tool budgets.

## Source excerpt

The demo is the easy part The post Your Agent Works in the Demo. Now Make It Survive Monday. appeared first on Towards Data Science.