Subscribe
Sign in
Home
Interviews
Newsletter Issues
Software Architecture
Engineering Leadership
Practical Deep-Dives
C++
Python
Sponsor Deep Engineering
About
Latest
Top
Discussions
Deep Engineering #65: Nikolai Kutiavin on Designing C++ Projects as Components, Not Files
On target-centric CMake, enforced dependencies, and search logic you can test without starting Qt
Sep 24
•
Saqib Jan
10
Governance Has to Become Infrastructure When Agents Write the Code
On why review processes built for human-paced development break under AI, and what it takes to make engineering standards enforceable by machines
Sep 23
•
Saqib Jan
1
1
EY Bounds Agent Autonomy by Risk, Not by Capability
On why the agent boundary is a governance decision, and what has to exist before enterprise AI moves past the pilot
Sep 22
•
Saqib Jan
Deep Engineering #64: Vijoy Pandey on How Team Topologies Strain As AI Shrinks the Delivery Unit
Inside the architecture of an organizational memory engine, the source hierarchy that governs what enters it, and the decision structure that routes…
Sep 17
•
Saqib Jan
11
How Cisco's Outshift Runs Engineering On AI Tiny Teams And A Memory Engine
Vijoy Pandey shrank his teams to five people and explains what that costs, and the memory engine and decision leads Outshift built to hold it together
Sep 17
•
Saqib Jan
37:35
Deep Engineering #63: Imran Ahmad on Building the Deterministic Shell Around an AI System
The model will still be wrong. Making sure the wrong answer cannot do anything about it.
Sep 10
•
Saqib Jan
and
Imran Ahmad
4
Reliable AI Systems Are Five Rings of Boring Code
On Input validation, context assembly, bounded control flow, output guards, and telemetry. About forty lines of ordinary software wrapped around one…
Sep 10
•
Imran Ahmad
How 10 years of C++ changed the way I see a C++ project
Component boundaries, target-centric CMake, and code designed for testability in a small Qt application.
Sep 9
Deep Engineering #62: James Ward on Wiring Agents to Tools, Data and Everything Else
A model is inert on its own, and most of what makes an agent useful is engineering that happens outside it
Sep 3
•
Saqib Jan
12
1
Agents Are Just LLMs With Integrations, Running in a Loop
On Tools, MCP, tool search, skills, memory, RAG and human in the loop, built with Spring AI and Java
Sep 2
•
Saqib Jan
August 2026
Engineering Teams Are Paying Back Their AI Speed Gains With Interest on Review
Agents are opening pull requests faster than many development teams can verify them, and engineering leaders are absorbing the difference in review…
Aug 31
•
Saqib Jan
2
1
Deep Engineering #61: Sándor Dargó on Reviewing Code an Agent Wrote
What changes when the author accepted every line instead of writing it, and why useful comments need action, information, and a reference
Aug 27
•
Saqib Jan
10
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts