ExplainerAI in production
Microsoft UserRepGen makes inputs for a simulated user
UserRepGen turns a conversation into task and behavior descriptions. Follow the intermediate artifact through a synthetic support-assistant evaluation.
AI in production. Reliability in practice.
Latest edition ·The latest analysis
What are model weights, and how does training change them?
Follow a weight through a training update, save a tiny model, and learn how checkpoints, fine-tuning, LoRA and held-out evaluation fit together.
Read the storyFrom the publication
The latest
ExplainerAI in production
PulsarLM keeps context small by dropping old token pages
PulsarLM removes low-attention pages rather than summarizing them. A synthetic archive-retention case explains what a local agent’s recall trial must inspect.
GuideIncident response
Checking AI incident-summary citations with Python
Build a local, synthetic citation check that exposes wrong-version evidence while keeping interpretation, source freshness and action permission separate.
GuideAI in production
Hermes Agent guide: what it is, when to use it, and how to get started
Understand Hermes Agent, its origins, models, memory and skills. Choose a setup, try two checkable examples, and learn where its limits matter.
Field guides
Get closer
to the evidence.
Follow a request. Review the code. Find out what actually happened.
Explore the guidesKeep the traces that explain a failure
GuideObservability
OpenTelemetry tail sampling through a checkout failure
Tail sampling selects recorded traces by error, latency and other evidence. A checkout timeout shows how routing, waiting time and memory affect the trace a responder can retrieve.
Give AI code review a useful job
GuideAI in production
CodeRabbit: how to use AI code review
CodeRabbit brings AI feedback into pull requests, editors and the CLI. A retry loop that exceeds its caller’s deadline shows the kind of finding that can repay review time.
Recover when a tool call times out
GuideAI in production
Recovering an automation write after a timeout
A missing response can leave a worker already created. Durable operation IDs and the destination’s idempotency contract let a replacement executor recover the original request.
Put it into practice
Less blank page.
More working plan.
Free reliability tools. No account needed.
Open the workbenchThe AI tools guide
Find the right AI tool for the job.
Coding assistants, code review and agent supervision.
Browse the guideCompanies & products