From Chaos to Executable Architecture: Redefining AWS Presales with Kiro and MCPs
The Challenge: The Cold Call "Black Hole" In cloud consulting, clients understand their business pain (like crashes or high costs), not technical details. Historically, translating rushed notes into diagrams and cost estimates created a brutal bottleneck. This latency between identifying a client's problem and delivering a technical proposal is where projects die. To fix this, I needed operational symmetry between business requirements and AWS infrastructure.
🏗️ The Strategy: An Augmented Presales Workflow
After iterating and seeking efficiencies, I have consolidated one possible professional workflow using Kiro (an AI agent with deep knowledge of AWS infrastructure) powered by Model Context Protocols (MCP).
This approach transforms the chaos of a raw transcript into a deployable architecture through four critical phases:
- Phase 1: Transcript Ingestion and Business Case. The process begins by extracting raw transcripts from platforms like Teams or Zoom. By injecting this text into the Kiro CLI or IDE, I instruct it to extract the primary pain point and structure a prioritized business case: what the problem is, what the proposed solution is, and what specific AWS services are required to mitigate the risk.
- Phase 2: Auto-Generated Visual Architecture (The Power of the Draw MCP). Presenting a block of text to a client does not close deals. Using the
drawMCP integrated into Kiro, I translate the business case into editable.drawiodiagrams. This allows me to arrive at the second client call visually demonstrating how AWS services interact to solve their problem.
- Phase 3: Estimation and APN Registration. With a clear visual architecture, I instruct Kiro to generate average consumption values for the selected services. This data is transferred to the AWS Pricing Calculator to create a realistic financial estimate, while simultaneously giving us the exact technical context to register the opportunity in the AWS APN (Partner Network) portal for evaluation.
- Phase 4: The "Devil's Advocate" (Auditing Blind Spots). This is the biggest battle scar I have earned: there is always something the client omitted to say. I ask Kiro to analyze the proposed architecture against the original transcript and generate a list of critical questions. If there are doubts or uncertainties regarding the workload, Kiro formulates the exact questions I need to send the client (via email or in the next session) to bulletproof the design prior to implementation.
⚠️ Lessons Learned (The "Hard Way")
Do not assume that the diagram generated in the first iteration is the final one. The biggest mistake in presales is falling in love with the first proposed architecture.
- Strict Validation: When using the
drawMCP, always review the logical connections. A diagram might look aesthetically pleasing, but Kiro might assume a database should be public if you did not provide a strict security directive. - Defensive Prompting: When requesting average values for the AWS calculator, always demand that the agent break down the "why" behind that metric (e.g., compute hours per month, outbound data transfer). Without that context, defending the price to the client will be impossible.
💰 Business Value and ROI
As cloud engineers, our job is not just configuring consoles; it is translating commercial pain into resilient infrastructure. This hybrid workflow not only accelerates the creation of technical proposals, but also standardizes the quality of architectures, reduces the risk of costly omissions, and allows projects to be presented to the AWS APN with a superior level of technical maturity.
⚖️ Technical & Legal Safe Harbor Disclaimer
AUTHORSHIP AND INDEPENDENT CAPACITY: This publication is authored solely by me in my individual and private capacity. The views, methodologies, and technical workflows expressed herein are my own and do not necessarily reflect the official policy, position, or strategic direction of my current or former employers, clients, or any legal entity I am affiliated with.
INTELLECTUAL PROPERTY & CONFIDENTIALITY COMPLIANCE:
- Zero Proprietary Disclosure: This content has been developed using publicly available information, official documentation, and personal research. No confidential information, trade secrets, internal proprietary source code, or non-public infrastructure schemas belonging to my employer or any third party have been used, referenced, or disclosed in this publication.
- Independent Development: The workflows described (including applied industry scenarios and hands-on experimentation) are based on general industry best practices and were not developed as a "work for hire" or as part of specific assigned duties for any organization.
- Standard Industry Tools: References to third-party tools (AWS, Kiro, APN, Teams, Zoom) are for educational purposes and based on commercially available features.
LIMITATION OF LIABILITY (NO WARRANTY): All code snippets, scripts, and architectural patterns are provided "AS IS" without warranty of any kind, express or implied, including but not limited to the warranties of merchantability or fitness for a particular purpose. In no event shall the author be liable for any claim, damages, or other liability arising from the use of this technical information.
COMPLIANCE: This contribution is made in good faith and intended to foster community knowledge under the AWS Builder Terms and the MIT-0 License for any included source code.
Enjoyed reading this content? Let the author know!
Your likes, comments, shares, and saves help creators reach more builders.
Loading recommendations
Loading article