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
My scheduling agent has no button to book a meeting. That is the best decision in it.
Caldra reads the inbox, finds the threads that are about scheduling, checks the calendar and proposes a time. A person approves, and the approval does the booking.
I learned why the hard way. Someone changed their password, the calendar token died with it, and the lookup came back empty. The agent read "no events" as "completely free" and proposed a slot on top of a meeting that was always there.
Because it couldn't book, the damage was one wrong suggestion. The fix wasn't a prompt, either. An auth failure is now a hard stop that reaches the user. Empty is not free.
How Caldra is built: ergini.com/work/caldra
What would you never let an agent do without asking you first?
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
Challenges
View all
Related posts
I can easily say this is a black diamond. wonderful execution
midcode 2.0 is out. The biggest update so far.
the idea in the long run is to edit all frontend and backend visually + agentically
New interface
More integrations Vue, Astro, Angular, Shopify and 15 more stacks, edited on the canvas
Databases: your tables and SQL
Start projects from scratch, and a marketplace of starters
midcode.app
Enterprise RAG AI: Private Doc Intelligence
A fast-growing B2B software firm needed a secure, enterprise-grade Retrieval-Augmented Generation (RAG) system to query thousands of confidential internal documents (legal contracts, technical architecture specs, Notion pages, and employee SOPs) in real time without third-party data leakage.
Key Challenges:
High hallucination risk and irrelevant context retrieval using standard keyword search.
Managing multi-format files (scanned PDFs, tables, markdown) with strict access control based on user hierarchy.
Technical Implementation & Solution:
• Engineered an automated ingestion pipeline in Python with LlamaIndex and LangChain for semantic chunking and metadata preservation.
• Integrated a hybrid vector search architecture pairing dense embeddings (OpenAI text-embedding-3) with sparse BM25 indexing in Qdrant.
• Added a cross-encoder re-ranking layer (Cohere Re-ranker) to prune low-relevance chunks, reducing API token costs by 40%.
• Built robust Role-Based Access Control (RBAC) via FastAPI endpoints, ensuring departmental data isolation.
Results & Impact:
• Dropped internal information retrieval time from 20 minutes to under 4 seconds.
• Attained 98% factual precision with traceable in-line page citations.
• Full on-prem Docker deployment ensuring 100% private data security.
I'd test revoking a user's document access mid-conversation. In your RBAC flow, do cached retrieval results get rechecked against current permissions before they're sent to the reranker or model?