Bulk Content Engine: How Context and RAG Tags Make the Orchestrator Smarter
My Bulk Content Engine now pauses and resumes at any point, because the orchestrator maintains its own context — plus RAG tags per task.
Martin Rau ·
Workflow Automation
in AI Orchestration
Wiederkehrende KI-Abläufe als automatisierte Workflows abbilden.
Blog Posts
Three AIs, One Edge Function: How I Structurally Prevent Drift in Parallel AI Work
Three AIs deployed edge functions in parallel without coordinating. The deterministic workflow I built afterwards — and why atomic claiming is the core.
Martin Rau ·
Encyclopedia
Human-in-the-Loop — Approval Gates for AI Agents
What human-in-the-loop means in agent workflows: approval gates, intervention points before critical actions, and why they are mandatory for irreversible steps.
Martin Rau
Prompt Chaining
Chaining several LLM calls into a pipeline: one step's output becomes the next step's input, gates as checks, and when chaining beats a mega-prompt.
Martin Rau
Agent Observability and Tracing — Spans, Logs and Debugging AI Agents
How tracing makes agent steps and tool calls visible as spans — the basis for debugging and cost control, with tools like LangSmith and Langfuse.
Redaktion
Evaluator-Optimizer Loop
One AI agent generates, a second one evaluates and critiques — looping around until the result meets a clear quality bar.
Martin Rau
Error Handling: Retry and Idempotency
Retries with backoff, idempotency, timeouts, and rollback: the reliability patterns that keep AI agents from failing at every network hiccup.
Martin Rau
State Management and Checkpointing
How agent workflows save state after every step (checkpointing) and resume exactly where they stopped after a crash — durable execution explained.
Redaktion
News
Execution engine without an IDE: tickets from the dashboard to any repo
You write a ticket in the boostN dashboard and it runs on the right repository — no IDE needed. Multiple repos, in parallel, in seconds.
Redaktion