We scan new podcasts and send you the top 5 insights daily.
James McAulay says his weekly retro is the skill he uses religiously, while daily standups often slip. Claude noticed stale outreach tasks and unnecessary GitHub refactors, then pushed him to ask whether work was really moving the needle. That outside view helped him catch avoidance and procrastination patterns.
With AI agents completing development tasks in minutes, two-week agile sprints are inefficient. A new "Heartbeat Protocol," replacing stand-ups with hourly telemetry checks, is needed to manage rapid, agent-driven progress.
Treat your agent as a productivity coach by asking it meta-questions like "What have I been procrastinating on?" or "What tool can you build me tonight?". The agent uses its memory of your tasks and habits to proactively suggest improvements and automations.
Shift weekly meetings from simple status reports to a problem-solving forum. An 'Execution Friction Check-in' focuses on three questions: 'Where are you stuck?', 'What have you tried?', and 'What support do you need?'. This surfaces bottlenecks and encourages collaborative solutions rather than just reporting progress.
Instead of slow quarterly planning, Mustafa Suleiman's division uses rapid 6-8 week cycles, each ending with an in-person meetup for retrospectives and planning. This rhythm creates clear, falsifiable missions suitable for the fast-paced nature of AI development, keeping the entire organization synchronized and focused.
A practical way to combat procrastination is to review your weekly accomplishments and calendar. Ask what activities were genuinely pushing the business forward (e.g., talking to customers) versus what was busywork created to avoid the simple, uncomfortable tasks that truly matter.
An unmaintained Agent OS has a shelf life of about eight weeks before context files are outdated and skills become irrelevant. To ensure compounding value, you must periodically conduct retrospectives with your agents, auditing which parts of the system are underutilized or stale and need updating.
A powerful, non-obvious use for AI assistants is proactive stakeholder management. Amol Avasare runs a scheduled task for Claude to look across his Slack channels and projects to find potential areas of misalignment. This helps him surface and resolve issues before they derail projects.
The primary value of a retrospective isn't just analyzing campaign results. It's creating a dedicated, safe space to discuss internal team dynamics, communication breakdowns, and process issues that caused stress or inefficiency. This focus on 'how' the work got done builds trust and improves future sprints.
Elevate your AI from a reactive tool to a proactive employee by setting up scheduled routines. Instead of just coding, task it with recurring operator work like creating a 'morning brief' from customer notes or running a 'weekly ops review' of open issues. This maintains business momentum and surfaces key insights.
Top engineers and designers waste significant time on coordination tasks like updating project management tools and attending stand-ups. Owner built an internal agent that listens to GitHub, Slack, and meetings to automate this alignment work, freeing up talent to focus on building.