T3 Code explained: one workspace for your coding agents
T3 Code brings your coding agents, project conversations and diffs into one workspace. Learn how it works, try a small repair and understand what stays on the host.
AI in production. Reliability in practice.
Latest edition ·The cover story
What does Palantir actually do?
How Foundry, Gotham, AIP and Apollo connect information, people and operational work, and why the connections matter as much as the AI.
Read the storyFresh from the publication
The latest articles
OpenCode 2.0 explained: what it does and how to use it
OpenCode is an open-source AI coding assistant that works with your project’s files and tools. Here’s what that means, what changed in 2.x, and how to try a small repair without handing it your whole environment.
How AI got from rules to reasoning models
Follow the changes in learning methods, data and compute that led to today’s models, and see why newer does not always mean better for a task.
Linux history: the kernel, the tools and the distributions
Unix, GNU, the Linux kernel and distributions explain the cooperating layers you operate today, including what a container actually shares.
Gemini 4 Argon: can it actually finish the job?
Google’s new reasoning model promises to stay with difficult work. Here is what that means for coding, research and investigations, and how to check the result.
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.
Worth understanding
A clearer picture of AI
Explainer
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.
Explainer
KoboldCpp 1.123 makes agent approvals depend on the tool and workdir
The global auto mode is only part of the permission decision. Follow per-tool overrides, directory scope and restored settings through a copied-runbook exercise.
Explainer
Anthropic Scion puts source control behind a cache hierarchy
Scion reduces repeated repository work for online agents. Its cache hierarchy explains why warm checkout speed and fleet recovery need different tests.
Reliability in practice
Production notes
Incidents, on-call work, and the decisions behind reliable systems.
What MTTD misses
Separate detection from response and find delays that an improving average can conceal.
Guide
When a postmortem fix leaves part of the risk unresolved
A backup cleanup can pass its tests while an older data format remains unverified. A risk registry preserves that distinction for the next engineering decision.
Guide
The on-call work that page counts leave out
Disturbed nights, specialist help and cleanup consume capacity beyond the primary shift. A workload worksheet connects that demand to staffing and delivery plans.
Put it to work
Tools for the job in front of you
Reconstruct the response
Put incident timestamps in order and examine the intervals between failure, detection, investigation, and recovery.
Build a timelineGive the next responder a head start
Turn a known failure into a procedure with scope, actions, escalation, and recovery checks.
Build a runbookFollow the fix through
Track corrective actions alongside verification criteria and the risk that remains.
Track an actionStart learning
Start with a question. Build from there.
AI basics · 10 lessons available
What happens between a prompt and an answer?
Understand what happens between a prompt and an answer, learn how to check the result, and build a small document assistant that shows its evidence.
10 lessons ready, with practical exercises throughout.
Explore AI basicsLinux basics · 13 lessons available
Get comfortable at the command line.
Learn to operate a Linux system by building, running and troubleshooting a small service in a disposable practice environment.
13 lessons ready, with practical exercises throughout.
Explore Linux basics