The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
A requirement can look clear — until you start asking what the system actually needs to do.
I tested this with a paperless banking workflow in Solution Blueprint Agent.
On the surface, the requirement describes a straightforward flow: a customer books a consultation, submits a digital form, and the bank processes the transaction.
But before implementation, several decisions immediately matter:
→ What actually marks the transaction as completed?
→ What happens if the booking changes after processing has started?
→ Does submitting the form authorize the transaction, or is another approval required?
None of these should be silently assumed.
They affect the workflow, state transitions, data model, integrations, and eventually the backend implementation.
That’s the part I’m continuing to refine with Solution Blueprint Agent: making unresolved decisions visible before they become code.
I built the product end to end, including the analysis workflow, AI orchestration, backend, and frontend.
Here’s a short demo of how it works:
solutionblueprint.app/?src=contra
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
AI is powerful. But when the technology is complex, the brand needs to make it easier to understand.
For NOVAiris, I explored how an AI infrastructure company could build a brand that feels intelligent, credible, and clear to modern businesses.
I started with the business problem, audience, positioning, and brand personality then translated that strategy into a visual identity system.
Strategy → Positioning → Identity
Because strong branding isn't decoration.
It gives a business a clearer way to be understood.
In AI infrastructure the audience is often technical buyers and non-technical decision makers at the same time. When you worked through positioning, did you lean the identity toward one of those two, or try to hold both?
I built an AI agent that handles customer operations — refunds, order lookups, and support tickets — with a human approval gate built into the workflow. The agent proposes the action, pauses, and waits for a human to approve before anything executes. The LLM never makes the final call. Role-based access and a full audit trail are enforced in code, not prompts. Deployed live on Azure Container Apps.
The pause for human sign off keeps refunds safe while still offloading the lookup work to the agent.
Automated LinkedIn Hiring Signal & AI Outbound Engine
Overview:
Designed and deployed an autonomous outbound lead generation system using n8n. The workflow captures hiring intent signals from LinkedIn, identifies relevant executive buyers, enriches verified contact data, and drafts contextualized sales copy through an integrated LLM.
Tech Stack:
n8n • Apify • SearchLeads API • OpenRouter (Nemotron LLM) • Google Sheets API • Telegram Bot API • JavaScript
Core Deliverables:
Automated Signal Scraping: Continuous monitoring of fresh job posts across target industries.
Granular Data Filtering: Exclusion logic for staffing agencies, company headcounts over 250, and unverified domains.
Multi-Source Enrichment: Automated discovery of decision-makers (C-Level, VP, Director) with validated work emails.
Context-Aware Email Generation: Custom prompting architecture that maps the open role's requirements directly into a tailored value proposition.
Data Synchronization & Alerts: Bi-directional sync with Google Sheets and real-time push alerts via Telegram.
Impact:
Replaces 10+ hours of weekly manual SDR prospecting with a continuous background process that delivers high-intent, enriched leads directly to the sales inbox.
