AI Enhanced Engineer

Thought provoking piece 👇

generativeprogrammer.com

One of the questions you will often hear in the years to come, answered in a clear, concrete, and hype-free way.

Enjoy!

What is an AI agent? | AI Enhanced Engineer A field guide for engineers: the loop, the autonomy spectrum, the harness, and demo-to-production reality, with working code.

Agentic Software Engineering — Pulse #2. Three things that landed this month:

• You can now steer a coding agent's behavior from inside the model — drift is a measurable signal you can correct on the fly.
• More compute isn't better. Accuracy peaks at a middle amount of spend, then flattens — and the agents can't predict their own usage.
• "An AI reviewed the code" often means no human actually did. Most agent-written changes get merged with little real review.

Read the full pulse 👇

https://open.substack.com/pub/aienhancedengineer/p/agentic-software-engineering-field

At AIEE, keeping up with 𝗮𝗴𝗲𝗻𝘁𝗶𝗰 𝘀𝗼𝗳𝘁𝘄𝗮𝗿𝗲 𝗲𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 is part of the job.

Written notes and mental models were not enough. The field moves faster than any manual tracking system can handle.

So we built a 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲.

A verifiable ingestion and processing system with a single design goal: 𝗲𝗱𝘂𝗰𝗮𝘁𝗲 𝘂𝘀 𝗮𝘀 𝗳𝗮𝘀𝘁 𝗮𝗻𝗱 𝗽𝗿𝗲𝗰𝗶𝘀𝗲𝗹𝘆 𝗮𝘀 𝗽𝗼𝘀𝘀𝗶𝗯𝗹𝗲.

It tracks papers, anchors concepts to primary sources, ranks findings by a composite signal (key insights, cross-field reach, empirical claims, recency decay), and produces a structured digest the team reads before shipping anything.

We're calling the output a 𝗙𝗶𝗲𝗹𝗱 𝗣𝘂𝗹𝘀𝗲. And we're sharing it openly.

𝗣𝘂𝗹𝘀𝗲 #𝟭 is live. It covers the state of the field, the concepts crystallizing, the patterns stabilizing, and the top 7 papers worth your attention right now.

The headline finding: 𝗮𝗴𝗲𝗻𝘁 𝗯𝗲𝗵𝗮𝘃𝗶𝗼𝗿 𝗶𝘀 𝗮 𝘁𝗮𝗿𝗴𝗲𝘁 𝗼𝗳 𝗱𝗲𝘀𝗶𝗴𝗻, not just an emergent property of the model. Five converging papers from Jan-Apr 2026 make this case independently, and it changes how you should think about 𝗵𝗮𝗿𝗻𝗲𝘀𝘀 𝗲𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴.

If you're building with or around coding agents, this digest was made for you.



https://open.substack.com/pub/aienhancedengineer/p/agentic-swe-field-pulse-1

Agentic SWE: Field Pulse #1 2026-05-10 · State of the field, the concepts crystallizing, the patterns stabilizing, and this pulse's top 7 papers.

“Which MCPs and tools do you use in your Claude Code setup?”

We have been asked this question repeatedly these last few months.

This article is the full answer, link in the comments! 👇🏽

𝐀𝐧𝐭𝐡𝐫𝐨𝐩𝐢𝐜 is doubling 𝐂𝐥𝐚𝐮𝐝𝐞 usage limits through 𝐌𝐚𝐫𝐜𝐡 𝟐𝟕.

If you're on Free, Pro, Max, or Team — you get 𝟐𝐱 usage automatically during off-peak hours (outside 8 AM–2 PM ET on weekdays). No action needed.

It applies across 𝐂𝐥𝐚𝐮𝐝𝐞 𝐂𝐨𝐝𝐞, web, desktop, mobile, and more.

Good time to push that project forward → https://support.claude.com/en/articles/14063676-claude-march-2026-usage-promotion

Claude March 2026 usage promotion | Claude Help Center We're offering a limited-time promotion that doubles usage limits for Claude users outside 8 AM-2 PM ET/5-11 AM PT on weekdays. This promotion is available for Free, Pro, Max, and Team plans. Enterprise plans are not included in this promotion. What is the promotion?From March 13, 2026 through March...

Your AI experiments often start with simple local file loading. But in production, you’re suddenly dealing with multiple data sources across different environments.

That’s where the Repository Pattern from Domain-Driven Design comes in. By creating a clean abstraction layer, you can implement a DocumentRepository with both local and cloud backends—so the same code runs everywhere.

✅ Tests run locally without credentials (saving thousands in API costs)
💡 Development happens at zero cost
🚀 Deployment is just an environment variable change

By hiding the messy complexity of data access behind a simple interface, you free yourself to focus on AI logic instead of infrastructure plumbing. Take a look at our new article: Production AI Systems: Solving the Data Loading Chaos, where we share practical patterns for working with multiple data sources—from experiment to production.

Production AI Systems: The Data Loading Chaos Part 2: Abstracting the data layer in AI applications

We are an 𝐀𝐈-𝐍𝐚𝐭𝐢𝐯𝐞 organization focused on 𝐛𝐮𝐢𝐥𝐝𝐢𝐧𝐠, 𝐟𝐢𝐱𝐢𝐧𝐠, and 𝐨𝐩𝐞𝐫𝐚𝐭𝐢𝐧𝐠 𝐀𝐫𝐭𝐢𝐟𝐢𝐜𝐢𝐚𝐥 𝐈𝐧𝐭𝐞𝐥𝐥𝐢𝐠𝐞𝐧𝐜𝐞 𝐚𝐭 𝐬𝐜𝐚𝐥𝐞.

Discover our services → https://aiee.io

What part of building AI at scale is giving you the most trouble right now?

Production-Grade AI Systems | AI Enhanced Engineer We build, fix, and operate Artificial Intelligence at scale. Production-grade AI engineering: assessments, remediation, custom development, and managed operations.

Our 𝗳𝗼𝘂𝗻𝗱𝗶𝗻𝗴 𝗲𝗻𝗴𝗶𝗻𝗲𝗲𝗿 just dropped 𝗣𝗮𝗿𝘁 𝟭 of our 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁𝘀 𝘀𝗲𝗿𝗶𝗲𝘀.

The core message: most teams are building 𝗮𝗴𝗲𝗻𝘁𝘀 when they should be building 𝘄𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀.

𝗖𝗵𝗮𝘁𝗯𝗼𝘁 → prompt, respond, stop.
𝗔𝗴𝗲𝗻𝘁 → goal, plan, execute tools, loop until done.

The reality check nobody wants to hear: your agent aces 𝟵𝟬% of test cases in dev, then 𝗲𝗱𝗴𝗲 𝗰𝗮𝘀𝗲𝘀 take 𝟯-𝟲 𝗺𝗼𝗻𝘁𝗵𝘀 of 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻 𝘁𝗿𝗮𝗳𝗳𝗶𝗰 to surface. Some failures require 𝗿𝗲𝗮𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝗶𝗻𝗴 𝘁𝗵𝗲 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲, not 𝗽𝗿𝗼𝗺𝗽𝘁 𝗳𝗶𝘅𝗲𝘀.

Practical advice: start with workflows, deploy at low 𝗮𝘂𝘁𝗼𝗻𝗼𝗺𝘆, and increase it over months, not sprints and only where absolutely needed.

This is Part 1 of a series covering 𝗮𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲 𝗽𝗮𝘁𝘁𝗲𝗿𝗻𝘀, 𝘁𝗲𝘀𝘁𝗶𝗻𝗴, 𝗳𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸𝘀, and 𝗼𝗯𝘀𝗲𝗿𝘃𝗮𝗯𝗶𝗹𝗶𝘁𝘆 — all linked to working code.

🔗 https://aienhancedengineer.substack.com/p/ai-agents-in-production-the-engineering

AI Agents in Production: The Foundations Part 1: A Practical Introduction