Maximizing Efficiency with AI Agents

Ken Judy
Ken Judy
Originally: Dec 3, 2025 | Enhanced: Jul 29, 2026
2 min read
Technology AICodingProductivitySoftware DevelopmentAgile

Maximizing Efficiency with AI Agents

2 Technology Post AI, Coding, Productivity, Software Development, Agile Dec 3, 2025 1764806400000

If you use ai agents to build code and you want to move faster without slowing down actual delivery then work with the agent to:

  1. Analyze the breadth of the codebase to reduce code duplication.

  2. Scope work down to 1-3 hr increments.

  3. Plan out the implementation in detail. Save the plan out as a file and follow along.

  4. Build test first in small steps with frequent commits whenever you complete a task.

  5. Analyze the completed work to identify gaps between analysis, plan and build code

  6. Take 5-10 min. to retrospect on what you’ve learned and what you can do better next session

If you want to read more or look at my prompts here are my articles on the topic:

Originally published on LinkedIn on Dec 3, 2025. Enhanced for this site with expanded insights and additional resources.

← Back to Articles and Posts

Related Content

innovation emblem

Insights on Using Anthropic Claude Models

Using Anthropic Claude models for coding:

Opus is strong on analysis. Industry benchmarks show it’s strong at coding, but I find it ambitious and rangy. It drifts beyond its mission when struggling, and will charge down supposition paths without grounding.

Sonnet is good at tasking out work and quite good at following through on well-defined tasks, but can be short-sighted in terms of pattern and method reuse.

The current version of Haiku falls short. It shows its age with anti-patterns like aggressively duplicating code and hardcoding values, particularly when spins on a task.

So, for now, I live in Sonnet. I use Opus mostly for analysis on big problems. I’ve stopped trying to use Haiku for now. Would love to hear from someone who is getting decent results in complex code with one of the smaller models.

Technology AICoding
1 min read
agility emblem

Optimizing Work Through Evidence-Based Checks

Yeah, that explains it. Avoiding work as an optimization. “Pull of the Weasel”. I’ve seen this, “This red test is a pre-existing problem, I’ll keep moving forward”

I code using a skill to enforce a Plan-Do-Check-Act cycle.

In the check template, I’ll adjust so that each verification requires cited evidence, not just a checkbox. From “All tests passing [ ]”… to “All tests passing, show output. [ ]”

I’ll see if I work better with the agent by anchoring in visible signals rather than generating findings. My role in the loop is reading actual output, not deciding whether to believe a summary.

Technology AgileProductivity
1 min read
agility emblem

AI Coding Practice Insights

My writeup on my plan-do-check-act AI coding practice is live on InfoQ.

It works well with plan mode. In fact, it anticipated it.

And retrospection is alive and well!

I provide links to prompts and code metrics github actions.

Technology AICoding
1 min read