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 citation can still point to the wrong answer.
In Shamrock Marketing's technical PDF library, I tagged passages by product, workflow and standard before retrieving context with Azure AI Search. That matters when two products use similar language but require different procedures.
When I assess a RAG assistant, I test those near-miss questions first. Does the cited page match the exact product and procedure? If it cannot, the system should say it lacks enough evidence.
Case study: https://contra.com/p/WqR6YO2e-shamrock-marketing-or-citation-backed-technical-rag
tagging by product before retrieval is such a smart fix for lookalike docs 👌
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
If you're paying for Claude, Cursor, or Codex and you're still pasting the same vague prompt into every new chat, the model isn't your bottleneck.
Here's the tell: you type some version of "we don't do it that way" more than once a week. That correction is real engineering knowledge. Right now it lives in your head and dies when the conversation ends.
Two things fix that.
Knowledge is the context you make available; your architecture, your business rules, your API docs, your constraints, and the reasons behind the decisions you already argued about once.
Skills are the recurring work written down once: the steps, not the explanation.
Adding an API endpoint, concretely. Knowledge tells the agent how auth works, what the data model looks like, and why the team picked the conventions it did. The skill tells it what to do: read the two closest existing endpoints, follow the same validation pattern, update the API contract, run the tests that cover it.
You still review the diff. You still own the decision. You've just stopped re-explaining your own codebase five times a week.
Start with one task you repeat. Write the steps. Supply the context. Then check the thing that actually matters: did the rework go down, or does it only feel more organized?
A subscription buys access. Getting useful work out of it is engineering.
The "we don't do it that way" test is a great way to put it. Every correction you repeat should end up in a rules file, not in the next chat. Making that a habit changed how I work with agents too.
AI Support Platform
A landing page concept for an AI-powered customer support platform.
The goal was to create a SaaS experience that feels simple, clear, and product-focused without falling into the usual overly technical AI aesthetic.
I focused on:
Clear product storytelling
Strong visual hierarchy
Minimal, modern UI
Product-focused sections
Clean interactions and spacing
A calm visual language that keeps the product at the center
Designed to make AI support feel less complicated and more approachable.
Outstanding work
I’ve been building HTML and React templates for a while. I have a roadmap of 10+ templates. I might release them in batches or all at once.
The templates will have AGENTS.md and DESIGN.md files for you agent.
You nailed the overall mood here. The details just reinforce it nicely.