Join us

ContentUpdates from Techmango Technology...
Link
@faun shared a link, 5 months, 3 weeks ago
FAUN.dev()

Effectively building AI agents on AWS Serverless

AWS just dropped support for buildingserverless agentic AI systems. You’ll need the Strands Agents SDK, Bedrock AgentCore (preview), plus trusty tools like Lambda and ECS. What’s new? Agentic AI flips the script. Instead of dumb prompt-in, response-out bots, you getgoal-driven loopswith memory, too.. read more  

Effectively building AI agents on AWS Serverless
Link
@faun shared a link, 5 months, 3 weeks ago
FAUN.dev()

Are OpenAI and Anthropic Really Losing Money on Inference?

DeepSeek R1 running on H100s puts input-token costs near$0.003 per million—while output tokens still punch in north of$3. That’s a 1,000x spread. So if a job leans heavy on input—think code linting or parsing big docs—those margins stay fat, even with cautious compute. System shift:This lop-sided .. read more  

Are OpenAI and Anthropic Really Losing Money on Inference?
Link
@faun shared a link, 5 months, 3 weeks ago
FAUN.dev()

Combining GenAI & Agentic AI to build scalable, autonomous systems

Agentic AI doesn’t just crank out content—it takes the wheel. Where GenAI reacts, Agentic AI plans, perceives, and acts. Think less autocomplete, more autonomous ops. Hook them together, and you get a full-stack brain: content creation, real-time decisions, adaptive workflows, all learning as they .. read more  

Combining GenAI & Agentic AI to build scalable, autonomous systems
Link
@faun shared a link, 5 months, 3 weeks ago
FAUN.dev()

37 Things I Learned About Information Retrieval in Two Years at a Vector Database Company

A Weaviate engineer pulls back the curtain on two years of hard-earned lessons in vector search—breaking downBM25,embedding models,ANN algorithms, andRAG pipelines. The real story? Retrieval workflows keep moving—from keyword-heavy (sparse) toward embedding-driven (dense). Across IR use cases, the .. read more  

Link
@faun shared a link, 5 months, 3 weeks ago
FAUN.dev()

I set up an email triage system using Home Assistant and a local LLM, here's how you can too

A DIY email triage rig usingHome Assistant, IMAP, andOllamawires up local LLM smarts with YAML-fueled automation. At the core: an8B dolphin-llamamodel running on GPU, chewing through messy HTML emails, tagging them, and firing off priority-sorted summaries via notifications. Why it matters:A signal.. read more  

I set up an email triage system using Home Assistant and a local LLM, here's how you can too
Link
@faun shared a link, 5 months, 3 weeks ago
FAUN.dev()

The Most Important Machine Learning Equations: A Comprehensive Guide

A new reference rounds up the core ML equations—Bayes’ Theorem, cross-entropy, eigen decomposition, attention—and shows how they plug into real Python code using NumPy, TensorFlow, and scikit-learn. It hits the big four: probability, linear algebra, optimization, and generative modeling. Stuff that.. read more  

Link
@faun shared a link, 5 months, 3 weeks ago
FAUN.dev()

Introducing AWS Cloud Control API MCP Server: Natural Language Infrastructure Management on AWS

AWS dropped theCloud Control API MCP Server, a mouthful of a name for a tool that makes 1,200+ AWS resources manageable through a standard CRUDL API—using natural language. Think: describe what you want, and tools like Amazon Q Developer turn it into actual infra code. It doesn’t stop there. It val.. read more  

Introducing AWS Cloud Control API MCP Server: Natural Language Infrastructure Management on AWS
Link
@faun shared a link, 5 months, 3 weeks ago
FAUN.dev()

Availability Models: Because “Highly Available” Isn’t Saying Much

Antithesis and Jepsen want to kill hand-wavy "high availability" talk. Instead, they push for clearavailability models—majority,total,sticky, etc.—that spell out when an operationactuallyworks during failures. It's about precision, not platitudes. Why it matters:This reframes availability from a va.. read more  

Availability Models: Because “Highly Available” Isn’t Saying Much
Link
@faun shared a link, 5 months, 3 weeks ago
FAUN.dev()

Observability in Go: What Real Engineers Are Saying in 2025

Go observability still feels like pulling teeth. Manual instrumentation? Tedious. Span coverage? Spotty. Telemetry volume? Totally out of hand. Even with OpenTelemetry gaining traction, Go lags behind Java and Python when it comes to auto-instrumentation and clean context propagation. Devs are hunt.. read more  

Observability in Go: What Real Engineers Are Saying in 2025
Link
@faun shared a link, 5 months, 3 weeks ago
FAUN.dev()

How to prepare for the Bitnami Changes coming soon

The Bitnami team has delayed the deletion of the Bitnami public catalog until September 29th. They will conduct a series of brownouts to prepare users for the upcoming changes, with the affected applications list being published on the day of each brownout. Users are advised to switch to Bitnami Sec.. read more  

Techmango Technology Services (TTS) is a high-spirited IT services company and has consistently grown today as a huge entity with a workforce strength of 400+ highly skilled staff which is founded in 2014. A Nasscom Partnered and CMMi Level 3 initiated IT company, with a difference. As a client-centered and quality conscious IT company, we offer a wide spectrum of technology services and solutions to help our clients meet their business needs on time and within cost-effective parameters. TTS does its best to provide you with Custom Software Development that will keep you steps ahead of your competitors by continuously improving your IT-based business solutions. We use the latest software development platforms and tools to achieve this thereby delivering you the best solutions which make you stand alone in the industry killing competition. We also employ the latest project management techniques and software engineering practices. Our Services portfolio broadly comprises Application Services, Infrastructure Services, and Professional Services delivered using our Flexi Global Delivery Model.