# AI use cases for Awesome Fde Resources (global-fde/awesome-fde-resources) Repo: [global-fde/awesome-fde-resources](https://github.com/global-fde/awesome-fde-resources) | Use cases: 4 | Page: https://dedupedai.com/use-cases/global-fde-awesome-fde-resources/ A curated GitHub list of books, guides, case studies, tools, and opportunities for Forward Deployed Engineers working on production AI delivery. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Pick evaluation tools for a customer LLM app: https://dedupedai.com/use-cases/global-fde-awesome-fde-resources/pick-evaluation-tools-for-llm-app/ - Find a reference build for a customer workflow: https://dedupedai.com/use-cases/global-fde-awesome-fde-resources/find-reference-build-for-customer-workflow/ - Harden a customer-facing agent before launch: https://dedupedai.com/use-cases/global-fde-awesome-fde-resources/harden-customer-agent-before-launch/ - Plan an FDE skills path from the reading list: https://dedupedai.com/use-cases/global-fde-awesome-fde-resources/plan-fde-skills-path-from-reading-list/ ## How to pick evaluation tools for a customer LLM app with Awesome Fde Resources Repo: [global-fde/awesome-fde-resources](https://github.com/global-fde/awesome-fde-resources) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README Shortlist evaluation and observability tools for a customer's LLM or RAG app. **Who it is for:** An FDE on a customer project who must show that an LLM or RAG app works before handoff. **The problem:** Teams need a way to measure answer quality and trace system behavior before they trust it. **The outcome:** A shortlist of two or three evaluation tools, each with a stated reason. ### Steps 1. Open the Tools section of the README and list the evaluation and observability entries. 2. Pick the tools that match the app type: RAG, agents, or general LLM. 3. Open each candidate's GitHub page and check its README for the features you need. 4. Write a one-page comparison against the customer's required metrics. ### Prompt to paste into your agent ```text Using the Tools section of the global-fde/awesome-fde-resources README, shortlist three evaluation tools for a . For each tool, state the feature match from its own repo README and the main gap. Verify each link opens to the named project before you report. ``` ### Caveat The README only lists these tools without testing or ranking them, so verify each project's current state yourself. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/global-fde-awesome-fde-resources/pick-evaluation-tools-for-llm-app/ ## How to find a reference build for a customer workflow with Awesome Fde Resources Repo: [global-fde/awesome-fde-resources](https://github.com/global-fde/awesome-fde-resources) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README Locate a working example in the Cases section that matches a customer's AI use case. **Who it is for:** An FDE scoping a new AI workflow who needs a proven starting point instead of a blank repo. **The problem:** Building from scratch slows discovery and delivery when a similar system already exists. **The outcome:** One or two reference projects linked to the customer use case, with notes on what to reuse. ### Steps 1. Open the Cases and reference implementations section. 2. Match the customer domain to an entry, such as the enterprise notebooks for marketing, pricing, supply chain, or manufacturing. 3. Open the candidate repo and check its license and recent activity. 4. Note which parts to reuse and which parts to rewrite. ### Prompt to paste into your agent ```text Read the Cases and reference implementations section of global-fde/awesome-fde-resources and pick the two entries closest to a . Output a table with project name, link, fit, and reuse notes. Verify the license stated in each linked project before recommending it. ``` ### Caveat Linked projects remain under their owners' licenses, so reuse rights must be checked in each project. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/global-fde-awesome-fde-resources/find-reference-build-for-customer-workflow/ ## How to harden a customer-facing agent before launch with Awesome Fde Resources Repo: [global-fde/awesome-fde-resources](https://github.com/global-fde/awesome-fde-resources) | Difficulty: Advanced | Time: 2 hours | Basis: From the README Review an agent for reliability and prompt injection using listed guidance and tools. **Who it is for:** An FDE preparing a customer-facing agent for production who must address reliability and security. **The problem:** Agents can fail, be manipulated through prompt injection, or act outside their intended scope. **The outcome:** A launch checklist that marks each principle or finding as pass, fail, or not tested. ### Steps 1. Read the 12-factor-agents repo for its reliability principles. 2. Review the Best practices entries on MCP security and red teaming. 3. Open NVIDIA-NeMo Guardrails and decide which guardrails apply to the agent. 4. With the owner's permission, scan the agent, its MCP servers, or its skills with snyk/agent-scan. 5. Record findings in the launch checklist and list open gaps. ### Prompt to paste into your agent ```text Using the 12-factor-agents and snyk/agent-scan repos listed in global-fde/awesome-fde-resources, review the agent at . Produce a checklist where each principle or finding is marked pass, fail, or not tested. Verify that you scanned only targets the owner authorized. ``` ### Caveat The README gives only a one-line description of each scanner, so confirm its coverage in the tool's own documentation. Risk, credentials: Scanning an agent may require access to its tools, MCP servers, or skills, so use test credentials and never production secrets. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/global-fde-awesome-fde-resources/harden-customer-agent-before-launch/ ## How to plan an FDE skills path from the reading list with Awesome Fde Resources Repo: [global-fde/awesome-fde-resources](https://github.com/global-fde/awesome-fde-resources) | Difficulty: Beginner | Time: 60 minutes | Basis: From the README Turn the Getting started list into an ordered four-week study plan for a new FDE. **Who it is for:** A new Forward Deployed Engineer or a hiring manager onboarding someone into customer delivery work. **The problem:** The Getting started list has many entries across topics and no suggested order. **The outcome:** A four-week reading plan with one resource per week and a stated goal for each. ### Steps 1. Open the Getting started section and note the entry for each topic. 2. Group the entries into delivery, agents, MLOps, and security. 3. Assign one resource per week over four weeks, starting with the FDE-specific guides. 4. Add a short check question at the end of each week. ### Prompt to paste into your agent ```text Read the Getting started section of global-fde/awesome-fde-resources and build a four-week study plan for a . Output one resource per week with its link and a check question. Verify every link comes from that section. ``` ### Caveat Some entries are Chinese-language or full courses with their own time demands, so check language and length before assigning them. Dual-use notice: only use this on software, sites and systems you own or are authorized to test. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/global-fde-awesome-fde-resources/plan-fde-skills-path-from-reading-list/