---
title: "AI Developer (@lycore) | Hashnode"
description: "build production-ready AI integrations, mobile apps, and web platforms for businesses that want real results."
url: "https://hashnode.com/@lycore"
---

@lycore

# AI Developer

@lycore · Joined April 2026

build production-ready AI integrations, mobile apps, and web platforms for businesses that want real results.

### [Don't Let the Meeting Bot File the Ticket: Building Around Anthropic's Claude Meetings Beta](https://aidevpro.hashnode.dev/claude-meetings-review-before-you-file-the-ticket?utm_source=hashnode&utm_medium=feed)

Claude Meetings joins Google Meet as a visible participant. How engineering teams should handle consent, connected tools, and ticket review.

18 min read · [aidevpro.hashnode.dev](https://aidevpro.hashnode.dev/claude-meetings-review-before-you-file-the-ticket?utm_source=hashnode&utm_medium=feed)

[3d ago](https://hashnode.com/posts/claude-meetings-review-before-you-file-the-ticket/6af69705337f1f4696e0d9ec)

### [Don't Put the Prompt on the Span: Tracing Django AI Agents with OpenTelemetry (Part 6)](https://aidevpro.hashnode.dev/opentelemetry-tracing-ai-agents-django?utm_source=hashnode&utm_medium=feed)

Trace Django AI agents with OpenTelemetry GenAI conventions: PII-safe spans, prompt refs, tail sampling on cost, and debugging a bad answer.

15 min read · [aidevpro.hashnode.dev](https://aidevpro.hashnode.dev/opentelemetry-tracing-ai-agents-django?utm_source=hashnode&utm_medium=feed)

[6d ago](https://hashnode.com/posts/opentelemetry-tracing-ai-agents-django/6af396b662b23cd0618a9d4e)

### [What Does One Successful AI Workflow Cost? Measuring LLM Spend in Django (Part 5)](https://aidevpro.hashnode.dev/llm-cost-per-successful-workflow-django?utm_source=hashnode&utm_medium=feed)

Divide all LLM spend, failures and retries included, by real business successes. Price prompt caching's three buckets correctly and add a budget guard that fails closed before the call.

18 min read · [aidevpro.hashnode.dev](https://aidevpro.hashnode.dev/llm-cost-per-successful-workflow-django?utm_source=hashnode&utm_medium=feed)

[Nov 8](https://hashnode.com/posts/llm-cost-per-successful-workflow-django/6af0f5d1811d1e6519dabb91)

### [Your RAG Post-Filter Is a Leak: Permission-Aware Retrieval in Django (Part 4)](https://aidevpro.hashnode.dev/permission-aware-rag-django-prefilter?utm_source=hashnode&utm_medium=feed)

Pre-filter tenant and ACL into Django RAG before top-k. Same Part 2 grant door, canary tests, no post-filter leaks.

14 min read · [aidevpro.hashnode.dev](https://aidevpro.hashnode.dev/permission-aware-rag-django-prefilter?utm_source=hashnode&utm_medium=feed)

[3](https://hashnode.com/posts/permission-aware-rag-django-prefilter/6aed0010158ca9774357d55e) [Nov 5](https://hashnode.com/posts/permission-aware-rag-django-prefilter/6aed0010158ca9774357d55e)

### [Your MCP Server Is a Second API: How to Add One to Django Without Skipping Row-Level Checks (Part 3)](https://aidevpro.hashnode.dev/mcp-server-django-row-level-permissions-agents?utm_source=hashnode&utm_medium=feed)

Thin MCP tools that go through the same scoped, audited, row-level door as your agents, plus five Django mounting traps and a 14-test suite.

17 min read · [aidevpro.hashnode.dev](https://aidevpro.hashnode.dev/mcp-server-django-row-level-permissions-agents?utm_source=hashnode&utm_medium=feed)

[Nov 3](https://hashnode.com/posts/mcp-server-django-row-level-permissions-agents/6aea5e591cf78420bc1a8e0a)
