Jev Soft-Ranks Skills — Agents Still Decide
Jev skill selection without hiding skills: gate on need, shortlist three, inject one suggestion line, let the agent decide, and log every override it makes.
Read the storyTHE INTEL LIBRARY
Playbooks
Managed Permissions Users Can’t Override — Test It Across Harnesses
Copilot enterprise managed permissions claim users can't override them. Prove it: one deny, ten bypass rows, run in Copilot, Claude Code, Codex and JetBrains.
Read the story
The Rule of Two: Split the Lane That Holds All Three
The agents Rule of Two for a real fleet: score each lane on untrusted input, private data and egress, split all-three lanes, and lint configs before they run.
Read the story
Test What Survives a Cross-CLI Session Import
Import Claude Code session history into another tool only after a fidelity test: mark turns, tool calls, approvals, branch and model carried or dropped.
Read the story
A Renamed Tool Is a Disabled Guard: Contract-Test Hook Coverage Before Antigravity’s Oct 5 Cutover
Antigravity agent hooks match tool names and fail open, and 09-2026 renamed the file tools. Test guard coverage and replay wire fixtures before Oct 5.
Read the story
Unauthored Hooks Are Persistence: Remove Them and Prove They Stay Gone
Claude Code hooks malware survives a declined consent prompt. Baseline hooks, logon tasks and PATH shims off-box, allowlist helpers, prove removal holds.
Read the story
Your Vendor Lane May Not Be the Last Hop
AI vendor data routing can carry your prompt past the vendor you signed with. Register each lane's last hop, then cap its data class at what you can verify.
Read the story
Vendor Permission Verdicts: Which Ones Still Need Your Approval?
Claude Managed Agents permission policy verdicts, normalized: log allows and denials as evidence, queue only real asks, and mark unseen verdicts unavailable.
Read the story
One Checkout, One Owner: Native CLI Worktrees vs Your Lane Runner
Codex, Claude Code and Cursor now create git worktrees for AI agents. Give each checkout one owner, lock what your runner owns and prove it with a decoy.
Read the story
Annotation Is Not Approval: The Human in the Loop Annotation Approval Split
Human in the loop annotation approval blurs when note-taking sits beside deploy, pin and schedule buttons. Tier gestures by consequence; check the gate weekly.
Read the story
AutoClaw Connectors: The Weekly Blast-Radius Inventory
AutoClaw connectors ship with no scope or revoke docs. Run a weekly inventory: what is installed, who added it, last used, write scope and a tested revoke path.
Read the story
AWS MCP Server Lambda Triage: Split Diagnostic Reads From Deploy Writes
The AWS MCP Server Lambda capability triages in one read-only call. Keep deploy writes on a separate IAM role, MCP config entry and human gate, logged apart.
Read the story
Computer Use Agent Windows Policy: Entitlements Before the Mouse Moves
A computer use agent windows policy for corporate endpoints: approved models, standard-user driver accounts, an entitlement matrix, a kill switch and logging.
Read the story
AI Credits vs Tokens: Two Billing Dialects, One Operator Ledger
AI credits vs tokens are two billing dialects. Translate a credit pack into measured jobs, price the same jobs at token rates, and keep one burn-rate ledger.
Read the story
Cyber Capability Gates Are Becoming Product SKUs: Allowlist AI Cyber Model Access by Agent Role
Gemini 3.8 Flash Cyber, Mythos 5.1 and Astra Daybreak turned cyber capability into gated SKUs. Map AI cyber model access by agent role, log it, rehearse revoke.
Read the story
DeepSeek V4.1-Flash: Rewrite the Off-Peak and Cache-Hit Runbook
DeepSeek V4.1-Flash halves prices off-peak and bills cache hits at $0.006/MTok. The UTC windows, the prompt shape that hits cache, and the re-based budgets.
Read the story
Claude Fable 5.1 Cache Reads: Meter Dollars per Overnight Job
Claude Fable 5.1 cache reads cost 0.025x base input. Meter dollars per overnight agent job and cache-hit rate, learn what breaks the cache, set effort per job.
Read the story
Model Deprecation Routing Is a Continuity Drill, Not a Changelog Line
Model deprecation routing runbook: when a provider swaps the model under your ID, run ordered fallbacks, smoke tests, spend caps per lane and human notify.
Read the storyPUT THE IDEAS TO WORKMany assistants.
Meet Automater Many assistants.
One place to remember.
Bring your AI sessions, context, and usage together with Automater.
Get started
Be the boss of all your AIs.
Lite is free forever, installs in about a minute, and reads the session history you already have.
Download Lite
Also for macOS (Apple silicon) and Linux.
Signed installer. No account. Session content stays on your disk.
