AI News selected for Professionals and Decision Makers
Model And Product Updates

Effective harnesses for long-running agents

01:00 · November 26, 2025 · Antropic Engineering Blog

Effective harnesses for long-running agents

Agents still face challenges working across many context windows. We looked to human engineers for inspiration in creating a more effective harness for long-running agents.

Summary

As AI agents take on complex tasks that span hours or days, the fundamental constraint is that each new session starts with no memory of prior work. Context windows force agents to operate in discrete shifts, much like engineers arriving on a project with no handover notes. The Claude Agent SDK provides compaction to manage token usage within a single window, yet this mechanism alone proves insufficient for sustained progress on production-grade applications.

The practical response is a two-part harness. An initializer agent runs first and creates the necessary scaffolding: a comprehensive JSON file listing every required feature, each initially marked as failing, plus supporting scripts such as an init.sh that starts the development server and performs a basic end-to-end check. Subsequent coding agents are then instructed to advance exactly one feature at a time, updating only the status field in the JSON file while leaving the codebase in a merge-ready state.

To prevent agents from guessing at prior changes or declaring work complete prematurely, each coding session must produce both a git commit with a descriptive message and an entry in a claude-progress.txt file. These artifacts allow the next agent to reconstruct the current state quickly. Explicit instructions also require the agent to verify functionality through browser automation rather than relying solely on unit tests or server responses, addressing the common failure of marking incomplete features as done.

Even with these measures, certain limitations persist. Vision constraints in tools such as the Puppeteer MCP prevent reliable detection of browser-native elements like alert modals, and the approach remains specialized for full-stack web development. Broader questions also remain open, particularly whether a single general-purpose agent or a collection of specialized agents yields better results across extended workflows.

Why it matters

Highly actionable for Product Teams and Builders with concrete implementation guidance, exact model references (Opus 4.5), and workflow strategies directly applicable to agent development and observability.

More in this beat
agent-memoryai-agentsanthropicclaudecontext-managementgitharness-engineeringllm-agents
Scaling Managed Agents: Decoupling the brain from the hands

02:00 · April 8, 2026

Scaling Managed Agents: Decoupling the brain from the hands

Highly actionable for Product Teams and Builders implementing agent workflows with Claude, including code-level interface patterns, security mitigations, and performance gains like reduced TTFT. Directly addresses model updates, harness evolution, and production observability.

Relevance 80 · Audience 85

Building a C compiler with a team of parallel Claudes

01:00 · February 5, 2026

Building a C compiler with a team of parallel Claudes

Directly demonstrates actionable agent-team workflows, test harness patterns, and parallelism techniques that Product Teams and Builders can adapt for complex software projects using current Claude APIs.

Relevance 85 · Audience 90

Equipping agents for the real world with Agent Skills

02:00 · October 16, 2025

Equipping agents for the real world with Agent Skills

Directly actionable for Product Teams and Builders: provides concrete implementation patterns, evaluation guidelines, and code patterns for building specialized agents. Addresses lifecycle, observability via progressive loading, and risks like malicious skills.

Relevance 78 · Audience 85

Claude Tag now reads even more of the room

02:00 · August 13, 2026

Claude Tag now reads even more of the room

This update is highly relevant for product teams and builders as it demonstrates advanced context-aware AI integration within daily collaboration tools like Slack. Dutch AI practitioners and SMEs can leverage this to streamline engineering workflows and improve team productivity without incurring extra usage limits.

Relevance 85 · Audience 95

Context Graphs for Proactive Enterprise Agents

06:00 · July 11, 2026

Context Graphs for Proactive Enterprise Agents

High technical depth, novel proactive architecture, and complete reproducible implementation make it directly actionable for Dutch AI researchers and advanced enterprise practitioners developing agent systems.

Relevance 78 · Audience 92

Introducing Claude Tag

02:00 · June 23, 2026

Introducing Claude Tag

This update introduces a new paradigm for human-AI collaboration within existing workflows, directly impacting how product teams build and debug. Its enterprise-grade access controls and data scoping make it highly viable for Dutch organizations adhering to strict data governance.

Relevance 85 · Audience 95

Harness design for long-running application development

01:00 · March 24, 2026

Harness design for long-running application development

This article provides highly actionable architectural patterns for product teams and builders developing autonomous AI agents. It offers concrete solutions to common LLM limitations like context degradation and self-evaluation bias, which are critical for Dutch AI engineering teams building robust, long-running applications.

Relevance 85 · Audience 95

Long-Context Isn't the Answer

01:00 · March 23, 2026

Long-Context Isn't the Answer

It provides actionable insights for ML Engineers on managing LLM context windows in production, highlighting the hidden costs of long-context models. The proposed architectural solutions, like sub-agent orchestration, are highly relevant for Dutch enterprises building reliable and efficient AI systems.

Relevance 85 · Audience 95

How monday.com transformed its platform into an agent-first product where humans and agents collaborate

02:00 · August 20, 2026

How monday.com transformed its platform into an agent-first product where humans and agents collaborate

This case study is highly relevant for product teams and builders as it provides a strategic blueprint for transitioning from superficial AI features to a native, agent-first architecture. It offers actionable insights into integrating LLMs like Claude into core workflows, which is highly applicable for Dutch SaaS companies and AI practitioners looking to drive sustained user engagement.

Relevance 75 · Audience 90