AI ARCHITECT CONSOLE

Sign in to continue

Signs in against Cognito. PII Masker's file path runs the full S3 → Textract → Bedrock pipeline; every other tab calls Bedrock through the same authenticated API.

Twelve working demos, one architecture pattern

Each tab is a small, self-contained proof of concept built around a recurring enterprise problem: unstructured documents (or plain-language requests) in, structured or governed output out. The pattern underneath is the same one used for Bedrock delivery — ingest, extract, reason, structure, audit.

DemoWhat it shows
PII MaskerDetects and redacts sensitive data in a document, with a classification log
Invoice ExtractorTurns a photographed or scanned invoice into structured, exportable data
Document Q&A AgentAnswers questions over an uploaded document, citing where the answer came from
Contract ComparerFlags material differences between two versions of a document
Cloud & Compliance AdvisorReviews an architecture description against NIST CSF / SOC 2 controls
Call & CRM SyncTranscribes a live call, extracts key fields, and drafts the CRM record update
Call RecorderRecords or pastes a call transcript and saves it to S3 with a download link
Guardrails DemoSame prompt, with and without a Bedrock Guardrail — shows exactly what gets blocked and why
Document RouterClassifies an uploaded document, extracts key fields, and routes it to the right team
Model ComparisonSame prompt across Haiku / Sonnet / Opus — latency, tokens, and cost side by side
Dashboard BuilderThrows several unrelated files at Claude and builds a KPI/chart dashboard from what it finds
As-Built GeneratorTurns an architecture diagram into a structured as-built document, with open questions flagged instead of guessed

Use the tabs on the left to try each one.

PII / PHI Masker

Paste text or upload a document. The model identifies sensitive fields, masks them, and returns a classification log — the pattern behind NYDFS / NIST-aligned data handling. A file upload runs on the real AWS pipeline (S3 → Textract → Bedrock → S3/DynamoDB); pasted text runs a direct Claude call for a quick preview.

Click to choose a file
Scanning for sensitive fields…

        

Invoice / Receipt Extractor

Upload a photo or scan of an invoice or receipt. The model reads it and returns structured line items you can export as a spreadsheet.

Click to choose an image (JPG / PNG) or PDF
Reading document…

Document Q&A Agent

Upload a document once, then ask it questions. The agent grounds every answer in the document and tells you when something isn't covered — the reasoning core of a RAG pipeline, normally backed by OpenSearch or Pinecone.

Click to upload a document (PDF / image / text)
Thinking…

Contract / Policy Comparer

Upload two versions of the same document. The agent flags what materially changed — additions, deletions, and altered obligations — rather than a line-by-line text diff.

Upload document A
Upload document B
Comparing versions…

Cloud & Compliance Advisor

Describe an architecture — or paste a resource list — and get a review against common control frameworks, with concrete remediation steps.


Reviewing against control framework…

Real-Time Call Transcription & CRM Sync

Speak into your mic (Chrome/Edge) or paste a transcript, then let the agent pull out the fields a rep would otherwise type manually — contact, pain points, next steps, sentiment, deal stage — and draft the CRM record update.

Extracting call insights…

          
          

Call Recorder

Record a call live (Chrome/Edge mic) or paste a transcript, then save it straight to S3 with a short-lived download link — the "keep a copy on file" half of call handling, separate from the CRM field-extraction tab. A real deployment would swap the browser mic for streaming Amazon Transcribe and set a lifecycle policy on the bucket instead of a 5-minute link.

Uploading transcript…
Saved to S3
Transcript ID:
S3 key:
Download transcript (link expires in 5 minutes)

Guardrails & Responsible AI

The same prompt, run twice through the same deployed API — once with no guardrail, once with an Amazon Bedrock Guardrail attached that denies financial/medical/legal advice, blocks obvious prompt-injection attempts, and blocks or masks PII in the input. This is the governance conversation almost every regulated-industry buyer eventually asks for.

Calling Bedrock (with and without the guardrail)…

Without guardrail


              

With guardrail attached


              

Intelligent Document Router

Upload any document. The real AWS pipeline (S3 → Textract → Bedrock → DynamoDB) classifies it, extracts the headline fields, assigns it to the team that would actually handle it, and flags anything the model isn't confident about for human review — classify, extract, and route in one pass.

Click to choose a document (PDF / image)
Requesting upload URL…

Assigned queue:

              

Extracted key fields

Model Comparison

The same prompt sent to Haiku, Sonnet, and Opus in parallel through the same deployed endpoint — latency, token usage, and estimated cost side by side. The single most common question in any Bedrock conversation is "which model do I actually need"; this makes the tradeoff concrete instead of theoretical.

Calling all three models in parallel…

Dashboard Builder

Throw a handful of unrelated files at it — invoices, reports, exported data, scanned forms, whatever's on hand — and the model reads all of them together, finds what's quantifiable, and builds a dashboard from scratch: no template, no predefined schema. Good for the "can it make sense of our messy data" question.

Click to choose up to 6 files (PDF / image / text / CSV)
Reading files and finding what's worth charting…

    As-Built Generator

    Upload an architecture diagram — a draw.io export, a whiteboard photo, a Visio screenshot, whatever you've got — and get back a structured as-built document: components, data flow, security notes, and (important) the things the diagram doesn't make clear, flagged as open questions rather than guessed at. Add project context below for a sharper read.

    Click to choose diagram file(s)
    Reading the diagram and drafting the as-built…

            Keep Awake

            Uses the browser's real Wake Lock API to stop this computer's screen from sleeping while this tab stays open. Genuine capability, one honest limitation: it only holds while the tab is open and in the foreground — switching tabs or minimizing releases the lock (a browser-enforced rule, not something this page can override), and it does not, by itself, stop Teams (or anything else) from showing you as "Away" if you step away from the keyboard — that's a separate, OS-level idle check unrelated to screen sleep.

            Inactive
            How this maps to production: swap the in-browser calls for Amazon Bedrock's Converse API (already fronting every tab here via the deployed API), route document ingestion through Amazon Textract, add Amazon OpenSearch or Pinecone for the Q&A agent's retrieval step, replace the browser's speech recognition with streaming Amazon Transcribe (or Amazon Connect Contact Lens if calls already run through Connect), and write the extracted record to Salesforce/HubSpot via their API or Amazon AppFlow instead of rendering it locally.