Answer extracted from the Unprompted: Real AI in IC podcast — listen to the full episode below.
How does an annual leave assistant agent help employees manage time off?
The annual leave assistant asks employees when they're leaving and returning, then automatically drafts both internal and external out-of-office messages. It scans their active workload, identifies what's still open, recommends how to close or handoff those actions, and prioritizes them so nothing slips through the cracks before or after time away.
This agent solves a common problem: people are often time-poor when preparing to leave, and the mental load of organizing your work before vacation is significant. Instead of manually reviewing every in-progress item, the leave assistant handles the triage automatically.
The process is straightforward. The agent asks two simple questions—departure and return dates—then gets to work scanning your task list. It creates a structured table of outstanding actions, showing what's been worked on and what requires immediate attention or handoff. Employees can then quickly see what needs to be closed, delegated, or simply flagged before they leave.
As Rebecca Lindsay explains in the episode, this is part of a broader philosophy: giving teams the tools to handle communication and workflow challenges at scale, rather than creating bottlenecks in the process.
"We want to be giving you the tools to do great comms yourself, and that is precisely what AI can enable us to do at scale."
Rebecca Lindsay — Internal Comms Manager at Hyper Exponential, where she leads AI experimentation within the company's enablement squad. She has built multiple AI agents to streamline internal communications workflows, from out-of-office automation to emotionally intelligent message review.
The annual leave assistant is one of several agents Rebecca has developed at Hyper Exponential, where the culture actively encourages using AI in daily work. For more on how Rebecca approaches prompt engineering and multi-layered data integration to build better AI agents, listen to the full conversation.
Solving the handoff bottleneck before time off
Employees leaving on vacation face a particular challenge: they need to make sure their team knows what's in flight and what should be paused. The annual leave assistant eliminates the manual work of cataloging and explaining each open action. Instead, it generates the summary automatically, including suggested next steps for each item.
This also reduces anxiety. Rather than worrying they've forgotten something or left their team in the dark, employees have a verified checklist before they go. The agent's prioritization means they can focus their final hours on the truly urgent items, not everything at once.
Integration with broader AI workflows
The leave assistant works best when it has access to structured data about ongoing work—task lists, project management tools, or communication records. This is why Rebecca emphasizes the importance of layered data in building effective AI agents. The richer the context the agent has access to, the better its recommendations will be.
The out-of-office messages it drafts can also be customized—separate templates for internal colleagues versus external clients, tailored tone, and specific instructions for urgent matters. This saves the human from writing multiple versions and ensures consistency in messaging across the organization.
Key takeaways
- The annual leave assistant automates the entire preparation process by asking only departure and return dates, then scanning your workload for you.
- It creates a prioritized table of outstanding actions, showing what needs to be closed, delegated, or handed off before you leave.
- The agent drafts both internal and external out-of-office messages automatically, reducing manual communication overhead.
- Having access to structured task data and communication history makes the agent's recommendations far more accurate and actionable.
See also
What is the role of layered data in building more effective internal communications strategies with AI?
Rebecca compiles a personal internal comms brain containing multiple data sources: internal comms survey results, employee satisfaction data, and event data. This layered approach allows AI agents to make recommendations aligned with the organization's unique context and priorities.
How does an emotionally intelligent communications checker agent work and what are its limitations?
Rebecca created a rudimentary agent that reviews communications against key principles of emotionally intelligent communication using a scoring rubric. While useful for consistency, it cannot replace human judgment on nuanced emotional messaging and requires careful refinement.
What prompt engineering techniques help ensure better AI agent outcomes?
Rebecca recommends asking the AI tool to clarify your requirements before running the prompt, recognizing that you don't always know what you don't know. She also suggests using structured data inputs and iterating on prompts based on real outputs rather than expecting perfection on the first run.