How do engineering teams maximize productivity with strategic use of AI enabled software tools?

Our recent team discussion Black Flag Design on AI-assisted development, particularly using Cursor, provided interesting insights into optimizing workflows, efficiency, and costs. Here's what me, Bobby Nicholson, Ryan...

Eli Wood headshot

Eli Wood

April 29, 2025 2 min read Updated April 18, 2026 Original LinkedIn post
How do engineering teams maximize productivity with strategic use of AI enabled software tools? cover image

Our recent team discussion Black Flag Design on AI-assisted development, particularly using Cursor, provided interesting insights into optimizing workflows, efficiency, and costs.

Here's what me, Bobby N. , Ryan St. Pierre , Keith Pattison , and Matías Barrios discussed based on what we're seeing in the ways of working:

Different AI Interaction Modes and Their Impact:

Our team members exhibit diverse AI interaction styles: some heavily utilize agent-based completions for broader coding tasks, while others primarily rely on tab completions for predictable patterns.

Tab completions are more obvious as extremely efficient and cost-effective, especially beneficial in repetitive coding scenarios following established patterns.

Efficiency and Cost Balance:

Heavy reliance on AI agents, while boosting productivity significantly (up to 50,000 suggested changes in one day), incurs higher costs.

Recognizing when and how to strategically leverage agents versus simpler interactions (like chat or tab completions) is essential.

Intentional AI Usage:

We identified the importance of deliberate AI usage. Chat interactions are ideal for initial planning, exploration, and detailed problem-solving discussions.

In larger codebases such as our enterprise systems, Agent interactions should be primarily for executing well-defined tasks or code generation.

Shared Context and Documentation:

Creating shared context, such as comprehensive PRDs or documentation, significantly improves the efficiency of subsequent AI-assisted interactions.

Structured documentation aids the AI in better understanding and contextualizing tasks, reducing redundant or unnecessary code generations.

Actionable Steps & Recommendations:

  • Clearly define scenarios suited for agent tasks versus those better handled via chat or manual coding supported by tab completions.
  • Establish and communicate guidelines or best practices clearly delineating optimal AI interaction modes based on task complexity and type.
  • Enhance transparency and consistency in documenting AI-driven processes to ensure clarity and alignment among team members.
  • Regularly share successful strategies and insights from individual workflows to foster continuous improvement and collective learning.

Points of Debate:

  • Cost versus creativity: Some team members prefer expansive, agent-driven approaches for broader creativity, despite higher costs, while others prioritize cost-effective simplicity.
  • Structured planning (e.g., formal PRDs) has supporters who argue it enhances clarity and productivity, while others feel it can inhibit creative coding processes.

Overall, we concluded that a strategic, intentional approach to AI use, paired with open communication and shared best practices, will best serve productivity and cost-efficiency.


About the author

Eli Wood headshot
Eli Wood

CEO, Black Flag Design

Eli Wood leads Black Flag Design, a creative technology company focused on shipping ambitious digital products, AI systems, and design-forward software with a direct point of view on how technology changes work.

Related stories

More from the journal

Pen-and-ink sketch of a small clockwork robot working at a tool-covered workbench late at night while a human sleeps peacefully on a couch in the background, a wall clock reading 2:00 above
ai April 24, 2026 13 min read

The Agent Stays Up Late, Not Me

Every senior engineer knows the right way to set up a codebase. None of them do it. Here’s the four-stage framework we use — The Ratchet — to take a vibe-coded project all the way to a thing you’d trust in production, and the punchline about why this only just became worth doing.

Most teams have always known they should be running tests, type-checking, security audits, accessibility checks, dead-code analysis, prose linting, and a coverage floor. Most teams run two of those. Here’s why that math has finally inverted, and the four-stage framework we use to ratchet a vibe-coded project to a hardened one.

Keith Pattison

Keith Pattison

Founder, Black Flag Design

Read
Black Flag Journal
claude code April 20, 2026 5 min read

What a Year of Claude Code Trails Tells You About Your Team

Claude Code leaves evidence — sessions, commits, PRs, review notes. Read it like a logbook and you'll find what devs actually need to know before they go deeper.

After a year of shipping with Claude Code across real client work, the signal isn't in any single session — it's in the trails. Here's what those trails told us about where Claude Code shines, where it drifts, and the habits devs should build before they lean in harder.

Eli Wood headshot

Eli Wood

CEO, Black Flag Design

Read
Black Flag Journal
playbook April 20, 2026 6 min read

The Black Flag Playbook: Six Principles for Shipping with AI

Battle-tested principles for teams building real software with AI-generated code. Human judgment, tight scope, and weekly evidence — the disciplines that keep AI-built systems reliable.

The six rules we use to ship production software with AI. Small scope, weekly demos, human-led oversight, and continuous improvement — drawn from six months of real client engagements.

Keith Pattison

Keith Pattison

Founder, Black Flag Design

Read