AI Engineering• 12 min
Assembly AI: Speech-to-Text at Scale
Real-time transcription architecture, speaker diarization, and cost optimization strategies for processing 1M+ minutes of audio — cutting our bill by 45%.
#assembly-ai#speech-to-text
#ai-engineering
17 posts
AI Engineering• 14 min
ChatGPT: Building Production Apps with GPT-4o
How we built a document processing pipeline handling 10K+ pages daily using ChatGPT's API — with structured outputs, function calling, and streaming patterns.
#chatgpt#openai
AI Engineering• 15 min
Claude: Engineering with Long-Context LLMs
How we migrated from GPT-4 to Claude for code analysis — leveraging 200K token context windows, prompt caching, and multi-shot prompting to cut costs by 60%.
#claude#anthropic
AI Engineering• 15 min
DeepSeek: Self-Hosting Open-Source LLMs
Running DeepSeek V3 and R1 locally on Kubernetes — how we cut API costs by 90%, the hardware requirements, and the quantization trade-offs we made.
#deepseek#self-hosting
AI Engineering• 13 min
Gemini: Multi-Modal AI for Code and Beyond
Benchmarking Gemini 2.5 Pro against GPT-4o for code generation, image understanding, and audio processing — a 3-month study with production workloads.
#gemini#google
AI Engineering• 14 min
Grok: Real-Time Knowledge Graphs and Conversational AI
Building a Grok-inspired real-time knowledge graph system that ingests live data streams and answers questions with up-to-the-minute accuracy.
#grok#knowledge-graph
AI Engineering• 13 min
Kimi: Long-Context LLMs for Document Intelligence
Handling 200K+ token documents with Kimi — the architecture for processing entire codebases, legal contracts, and research papers in a single context window.
#kimi#long-context
AI Engineering• 12 min
Kling: Video Generation Benchmarks and Integration
Benchmarking Kling against Sora 2, Veo 3, and other video generation models — a head-to-head comparison on quality, cost, latency, and API ergonomics.
#kling#video-generation
AI Engineering• 13 min
Manus: Multi-Agent Automation Pipelines
Evaluating Manus as an AI agent framework for our automation pipeline — how it handles complex multi-step tasks and where it still needs human oversight.
#manus#agents
AI Engineering• 16 min
Meta AI: Fine-Tuning Llama for Production
From data curation and LoRA training to deployment and monitoring — our 6-month journey fine-tuning Llama 3 for production with 40% accuracy improvement.
#meta-ai#llama
AI Engineering• 14 min
NanoBanana: Building Agentic Workflows
Building a multi-agent system with NanoBanana — architecture patterns, tool-calling orchestration, and lessons from deploying agentic workflows in production.
#nanobanana#agents
open-source-ai• 18 min
OpenAI Symphony: Orchestrating Autonomous Coding Agents at Scale
OpenAI's open-source Symphony framework that monitors Linear boards, spawns autonomous coding agents, and delivers proof-of-work — without a single GPU.
#openai-symphony#agent-orchestration
AI Engineering• 16 min
Perplexity: Building Real-Time Search and RAG Systems
Real-time web retrieval, citation-grounded generation, and the architecture behind sub-second answers — building a Perplexity-style search engine.
#perplexity#rag
AI Engineering• 11 min
Sora 2: Video Generation for Engineering Documentation
Benchmarking quality, cost per minute, and the 5 patterns that produced watchable results — experiments with OpenAI Sora 2 for technical explainer videos.
#sora-2#openai
AI Engineering• 12 min
Veo 3: Text-to-Video for Technical Demos
Prompt engineering patterns, temporal consistency techniques, and how we integrated Google Veo 3 into our documentation pipeline for product demo videos.
#veo-3#text-to-video
open-source-ai• 15 min
Webwright: Terminal-native web agent achieving 86.7% on Online-Mind2Web
Terminal-native web agent achieving 86.7% on Online-Mind2Web — Microsoft Research's MIT-licensed harness beating every open-source alternative by 15+ points.
#webwright#microsoft
AI Engineering• 12 min
Building a Multi-Agent RAG Pipeline: Lessons from Production
How we built a production RAG system that handles 10K+ queries daily — the architecture, the failures, and the hard-won optimizations that cut latency by 60%.
#rag#llm