Tekko

Language

Get in Touch

Usually respond within 24 hours

Blogs

Our latest insight

Tips, tutorials, and perspectives from the tekko.id team about the digital and technology world.

Mastering Deterministic RAG: Self-Correcting Workflows with LangGraph
AI & ML

Mastering Deterministic RAG: Self-Correcting Workflows with LangGraph

Build production-grade RAG pipelines using LangGraph to implement state-machine control, self-correction loops, and human-in-the-loop verification.

7 min
Building Fault-Tolerant AI Agents with Temporal and LangGraph
Architecture

Building Fault-Tolerant AI Agents with Temporal and LangGraph

Learn how to combine LangGraph’s agentic orchestration with Temporal’s durable execution to build production-grade, state-recoverable AI workflows.

7 min
Database Branching: Better CI/CD with Neon and GitHub Actions
DevOps

Database Branching: Better CI/CD with Neon and GitHub Actions

Stop fighting over shared staging databases. Learn how to automate isolated Postgres branches for every PR using Neon and GitHub Actions.

8 min
Implementing Semantic Cache-Aside for LLMs with Upstash Vector
AI & ML

Implementing Semantic Cache-Aside for LLMs with Upstash Vector

Learn how to slash LLM latency and inference costs by implementing a semantic cache-aside pattern using Upstash Vector and Redis for similarity-based query reuse.

7 min
Querying Multi-GB Parquet Files in the Browser with DuckDB-Wasm
Architecture

Querying Multi-GB Parquet Files in the Browser with DuckDB-Wasm

Learn how to build high-performance client-side analytics by leveraging DuckDB-Wasm, Apache Arrow, and Parquet to query gigabytes of data with sub-second latency.

7 min
Scaling LLMs: Implementing Semantic Caching with Redis
Architecture

Scaling LLMs: Implementing Semantic Caching with Redis

Reduce LLM latency and costs by implementing semantic caching. Learn how to use Redis vector similarity search to reuse responses for semantically equivalent queries.

7 min
Testing RAG: Building LLM Eval Pipelines with DeepEval and Pytest
AI & ML

Testing RAG: Building LLM Eval Pipelines with DeepEval and Pytest

Move past manual 'vibe checks' by building automated evaluation pipelines to quantify RAG hallucinations and faithfulness using DeepEval and Pytest.

7 min
Scaling SaaS Authorization: Implementing ReBAC with OpenFGA and Go
Security

Scaling SaaS Authorization: Implementing ReBAC with OpenFGA and Go

Learn how to build flexible, relationship-based access control for complex multi-tenant SaaS applications using OpenFGA and Go, inspired by Google's Zanzibar.

7 min
Sidecar-less Service Mesh: Securing Kubernetes with Cilium eBPF
DevOps

Sidecar-less Service Mesh: Securing Kubernetes with Cilium eBPF

Learn how to eliminate sidecar overhead and secure Kubernetes networking using Cilium eBPF for mutual authentication and observability via Hubble.

7 min