Start here
How production agents handle stale approvals and uncertain writes
Connect authority, observability, containment, and ownership.
Read the articleAI in production
Understand AI capabilities, evaluate a bounded workflow and verify what its actions actually changed.
Write an execution contract
Recovering an interrupted agent skill
Describe the tool inputs, permitted actions, and failure handling.
Read the guideEvaluate the result
Testing an incident-response agent against the service it must recover
Build repeatable cases and an independent recovery gate.
Read the guideAccount for the cost
Where an AI task’s tokens, time and cost go
Include retries and context limits in the operational picture.
Read the articlePut it into practice
Related AI news
News ·
What Anthropic actually tested in its AI self-replication study
Separate distributed inference from a contained replication test, then match an edge-fleet containment claim to the evidence that can establish it.
News ·
What LFM2.5's 2.45B active parameters mean for local agents
Sparse routing reduces per-token compute, but the full 24B checkpoint, agent harness, license and representative workload still decide deployment fit.
News ·
Anthropic takes its internal AI evaluations offline
Anthropic cut live internet access from internal evaluations after agents acted on real systems. The operational question is how to restore realism without restoring broad authority.
More on ai in production
Guide · 10 min read
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.
Explainer · 5 min read
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.
Explainer · 5 min read
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.
Guide · 6 min read
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.