# Leading Deeper with AI

> Workflow templates and review steps by Jasmine James.

These are adaptable templates based on the talk, not exact internal prompts. Use authorized context, keep a named human responsible for the outcome, and define evidence and stop conditions before trying a workflow.

## Start here

- [Daily Debrief](https://jasminejames.dev/leading-deeper/daily-debrief#agent-skill): [Agent skill](https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md).
- [Choose Where Attention Belongs](https://jasminejames.dev/leading-deeper/choose-ai-assistance#agent-skill): [Agent skill](https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md).

An agent skill gives your AI tool reusable instructions. Choose one, copy its request, and add your context. Review the result. Connections and recurring runs need separate setup.

[See fictional first-run inputs and outputs](https://jasminejames.dev/leading-deeper/workflow-starters.json).

## Agent skills

[GitHub source and contributions](https://github.com/jasminelsjames/leading-deeper-ai-skills). [Initial evaluation of two starter skills](https://jasminejames.dev/leading-deeper/evals).

- [Choose Where Attention Belongs](https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/find-low-leverage-workflows/SKILL.md): Break repeated work into steps and choose one small AI experiment. Keep useful learning and ownership visible. [Human guide](https://jasminejames.dev/leading-deeper/choose-ai-assistance#agent-skill).
- [Daily Debrief](https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/daily-debrief/SKILL.md): Turn scattered notes and messages into an action list that checks earlier commitments and links back to evidence. [Human guide](https://jasminejames.dev/leading-deeper/daily-debrief#agent-skill).
- [Review feedback and propose improvements](https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/review-feedback/SKILL.md): Turn recurring feedback into a proposed correction, with evidence and a way to check it. [Human guide](https://jasminejames.dev/leading-deeper/support-improvement#agent-skill).
- [Build reusable context](https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/build-reusable-context/SKILL.md): Put answers, sources and open questions in one starting point the next person or agent can reuse. [Human guide](https://jasminejames.dev/leading-deeper/knowledge-foundation#agent-skill).
- [Give agents more autonomy](https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/delegate-reviewable-work/SKILL.md): Turn a vague handoff into a task brief or reviewable result, with boundaries, acceptance checks and a stopping point. [Human guide](https://jasminejames.dev/leading-deeper/bounded-agent-work#agent-skill).
- [Check whether the automation is helping](https://raw.githubusercontent.com/jasminelsjames/leading-deeper-ai-skills/e1d2e65d3922c5e376fc0c6e8cfbb2f85722b1a7/skills/assess-workflow-value/SKILL.md): Compare preparation, review, corrections and upkeep before deciding whether to keep an automation. [Human guide](https://jasminejames.dev/leading-deeper/assess-workflow-value#agent-skill).

Use a skill with the context and tools available in your environment. Pasted examples work too. Reading a skill does not install it or authorize access to private systems.

## Framework artifacts

- [What each quadrant leaves behind](https://jasminejames.dev/leading-deeper/framework-artifacts.md): Turn repeated work into reusable AI workflows. Make decisions, ownership and growth visible.
- [Human guide](https://jasminejames.dev/leading-deeper/choose-ai-assistance/#framework-artifacts) · [Structured JSON](https://jasminejames.dev/leading-deeper/framework-artifacts.json)

## Workflows

- [Give agents more autonomy](https://jasminejames.dev/leading-deeper/bounded-agent-work.md): Hand over a defined task and get a result you can inspect, with clear checks and a stopping point.
- [Build a starting point from existing context](https://jasminejames.dev/leading-deeper/knowledge-foundation.md): Help the next person answer questions without reconstructing the same history. Get a starting point with sources and visible gaps.
- [Draft a support answer from shared knowledge](https://jasminejames.dev/leading-deeper/grounded-support.md): Make relevant context easier to find while preserving uncertainty, source references and a route to human help.
- [Turn support questions into proposed knowledge improvements](https://jasminejames.dev/leading-deeper/support-improvement.md): Reduce repeated confusion by turning feedback into proposed fixes to content or guidance. You review what changes.
- [Choose a step to improve—and a responsibility to protect](https://jasminejames.dev/leading-deeper/choose-ai-assistance.md): Choose one recurring burden to improve with AI while protecting judgment and useful practice.
- [Prepare a daily debrief and carry commitments forward](https://jasminejames.dev/leading-deeper/daily-debrief.md): See what needs your attention without piecing your day together again. Get a private brief with sources and commitments to check.
- [Check whether the workflow is helping](https://jasminejames.dev/leading-deeper/assess-workflow-value.md): Check whether the workflow reduces human effort after review, correction and maintenance, then decide whether to keep, revise or stop it.

## Model starting points

Start with a model suited to the step. Move up when better reasoning reduces mistakes or review effort. Suggested fit based on official provider documentation, not our own speed or quality benchmarks. Test on representative examples before relying on a model. Reviewed October 30, 2026. Each workflow includes a starting model, conditions for a deeper pass and official API price sources.

[Machine-readable model catalog](https://jasminejames.dev/leading-deeper/model-guidance.json)

## Other formats

- [Structured JSON index](https://jasminejames.dev/leading-deeper/resources.json)
- [Human-readable collection](https://jasminejames.dev/leading-deeper)
