Custom GPT for Agility Recovery Documentation
Overview
During the Agility Recovery training course project, Asymmetric built a custom AI knowledge system trained exclusively on Agility Recovery's internal documentation. Rather than relying on general-purpose AI outputs, the team ingested 197–277 source documents to create a domain-specific expert system capable of answering questions, generating content, and producing learning assets in Agility Recovery's own language and terminology.
This approach directly improved the quality of the [1] RISE 360 training course by grounding all generated content in the client's actual materials rather than generic industry knowledge.
How It Was Built
Document Ingestion
- Sourced all available documents from Agility Recovery's SharePoint training folder, plus additional materials gathered by the Asymmetric team
- Documents included: case studies, price lists, presentations, product catalogs, branding materials, and website content
- All files were converted to PDF format before upload (a time-intensive but necessary step)
- Two versions of the GPT were created on different platforms, with the second version containing approximately 277 documents and additional output capabilities
Memory Constraints
The first GPT instance hit a memory ceiling at approximately 100 documents. The team addressed this by:
1. Creating a second instance on a platform with higher capacity
2. Accepting the current corpus as sufficient for the initial course build, with a plan to expand as new documents become available
"We felt like it was pretty bloody smart. So we didn't really need to get a whole lot deeper." — Mark Hope
Capabilities
The custom GPT system supports a range of content generation and analysis tasks:
| Capability | Description |
|---|---|
| Q&A / Research | Answer questions about Agility Recovery products, terminology, and services |
| Mind Mapping | Generate visual concept maps from the full document corpus |
| Quiz Creation | Produce knowledge-check questions grounded in actual content |
| Report Generation | Summarize topics or products across multiple source documents |
| Flashcard Creation | Build study aids from document content |
| Block Analysis | Analyze RISE 360 content structure (e.g., text block ratios, interactive element distribution) |
| Course Content Drafting | Generate module text using client-specific language and product names |
Why This Matters for Course Quality
The initial course content draft was criticized by the client for being too cybersecurity-focused and not accurately reflecting Agility Recovery's core product language. The custom GPT addressed this by:
- Learning Agility Recovery's product naming conventions (e.g., Ready Power, Ready Financial, Ready Tech, Ready Financial Plus, Ready Financial Plus Essentials Bundle)
- Understanding customer terminology and how the company refers to its own clients
- Surfacing case study examples from the document corpus
- Enabling the team to identify content gaps — areas where no source material exists and the client needs to provide additional input
"It's not just taking ChatGPT garbage... it's taking 197 Agility Recovery documents and trying to understand them all and then help create the course from that." — Mark Hope
Content Balance Insight
One concrete output of the GPT-assisted analysis was a RISE 360 block distribution recommendation:
- ~65% text blocks (standard content delivery)
- ~35% interactive elements (statements, knowledge checks, accordions, tabs, quotes, galleries)
Overuse of interactive elements (flip cards, drag-and-drop) was identified as a risk — making courses feel "childlike" rather than professional. The GPT helped audit existing modules against this ratio.
Example block summary from Modules 1–3:
- 42 text blocks
- 22 knowledge checks
- 15 interactive tabs
- 12 accordions
- 12 statement blocks
- 8 quotes, 1 image, 1 gallery
Ongoing Use
The system is designed to grow with the project:
- As Agility Recovery provides additional product documentation (e.g., detailed Ready Financial tier breakdowns), those documents can be fed into the GPT to improve future module accuracy
- The team (specifically Raphael, the developer assigned to module building) uses the GPT to flag content gaps and request clarification from the client
- Gus Donelson acknowledged that some product collateral is thin or underdeveloped on Agility Recovery's side, making the GPT's ability to surface gaps a useful project management tool
Related
- [2]
- [3]
- [4]
- [5]