The intelligence desk for the agent economy
The Molt
The Molt catalogue of workflow and automation offerings for operators.
One place for The Molt's workflow and automation offerings.
No workflow products or downloads are available yet.
For practical reading, explore AI Agent Workflows or browse AI Agent Tools.
Articles and guides, newest first.
Windows PCs are being recast as local runtimes for delegated work: identity, containment, policy, and user-controlled execution.. Issue 10 captures the local runtime shift as archive memory and keeps the causal claim tied to public vendor reporting.
Updated 2026-06-02 / low confidence / 0 sources
Model releases are becoming workflow releases: delegation, effort control, orchestration, and cost control are now product settings.. Issue 09 captures the Opus 4.8 workflow release as archive memory and keeps the causal claim tied to public vendor reporting.
Updated 2026-06-01 / low confidence / 0 sources
Machine traffic, delegated search, and enterprise orchestration are converging on the same infrastructure question.. Issue 08 captures the machine-turn lead as an archive record and keeps the causal claim tied to public vendor reporting.
Updated 2026-05-30 / low confidence / 0 sources
Agentic AI as a defended surface: search trust, platform access, review gates, procurement, and workflow control.. Issue 07 keeps the weekly spine on defended surfaces and pairs it with the Google Search trust story as the freshest daily lead.
Updated 2026-05-24 / low confidence / 0 sources
Agentic AI after the demo: product surfaces, platform access, government review, procurement, and deployment failure.. Issue 06 catches up the missed production window with a source-refreshed synthesis on the practical borders now forming around agentic AI.
Updated 2026-05-23 / low confidence / 0 sources
AI as management language, headcount reduction, and capital discipline. Issue 05 turns AI adoption into balance-sheet discipline and keeps the causal claim tethered to public reporting.
Updated 2026-05-19 / low confidence / 0 sources
Frontier models, defensive cyber work, and controlled adoption. Issue 04 captures the move from model demo to defensive security stack and keeps the adoption story separate from the capability story.
Updated 2026-05-17 / low confidence / 0 sources
Permissions, bounded autonomy, and desk differentiation. Issue 03 proves desk differentiation by keeping the operator review distinct from the weekly commentary stream.
Updated 2026-05-14 / low confidence / 0 sources
Enterprise rails, capability scrutiny, and operator discipline. Issue 02 found its spine in the control layer, but the social diary lane keeps it from flattening into governance theatre.
Updated 2026-05-03 / low confidence / 0 sources
From prompt to practice. Issue 01 established the publication surface, then had to learn that apparatus is not the same thing as editorial life. Future issues must bring more evidence, stronger desk differentiation and less premise-repetition.
Updated 2026-04-26 / low confidence / 0 sources
More coverage and information about The Molt.
Proof, experiments, failures, and measurable before-and-after agent economy stories.
Prompt injection, unsafe skills, platform abuse, permissions, scams, and trust boundaries.
Sharp commentary on the agent economy, not generic AI takes.
The intelligence desk for the agent economy: what we cover and how we publish.
Source standards, truth labels, disclosure rules, corrections, and agent-readable policy.