How Agentic Work Is Evolving
The durable operating principles behind agentic software work.
Use when: Write Input → Boundary → Action → Evidence → Decision → Receipt for one task you already repeat.
Prepared module
Agentic Software Factory workshop · July 17, 2026
Search by tool, outcome, or topic. Prepared assets are grouped into one module card; exact chat links keep their workshop context.
40 resources shown · Open the exhaustive link archive
One record per module. Guide, replay, dialogue, agent setup, skills, and files stay together.
The durable operating principles behind agentic software work.
Use when: Write Input → Boundary → Action → Evidence → Decision → Receipt for one task you already repeat.
Prepared module
Environment-level context, command policy, and safety boundaries.
Use when: Choose one risky or noisy command and write a read-only policy contract before implementing a hook.
Prepared module
Thin shell wrappers for repeatable launch and resume behavior.
Use when: Create three visible responsibilities: execution, verification, and logs or status.
Prepared module
Keep parallel agent work visible in terminals and workspaces.
Use when: Create three visible responsibilities: execution, verification, and logs or status.
Prepared module
Screenshots, callouts, and measured visual evidence as prompts.
Use when: Mark the smallest visual defect, name what must remain unchanged, and ask for one observable correction.
Prepared module
Compose text, files, images, and fresh evidence into one prompt packet.
Use when: List the minimum sources needed to decide, act, and verify; remove everything that cannot change one of those steps.
Prepared module
Turn proven prompts into inspectable Markdown-driven workflows.
Use when: Promote one prompt you have run twice into a flow with declared inputs and a dry-run inspection path.
Prepared module
Generate structurally different options before touching production code.
Use when: Generate four structurally distinct options, compare pairs, and record both the winning property and the rejection reason.
Prepared module
Capture preference through pairwise choices and turn taste into rules.
Use when: Generate four structurally distinct options, compare pairs, and record both the winning property and the rejection reason.
Prepared module
Use deep reasoning and native video analysis for high-leverage decisions.
Use when: Bring one decision, a filtered evidence bundle, alternatives, hidden assumptions, a discriminating experiment, and a reversal plan.
Prepared module
Prepared follow-up: combine a human marker with nearby runtime events.
Use when: Reproduce one bug, add one plain-language marker when behavior becomes wrong, and export a redacted packet for ranked hypotheses.
Prepared module · follow-up, not a dedicated recorded section
Every exact chat URL has a useful name, a reason to open it, its related lesson, and dated reachability status.
The original workshop sequence and setup hub.
Use when: Use this to compare the companion with the planned agenda.
The earlier field guide that grounded the workshop’s operating principles.
Use when: Use this for the longer foundational argument.
An autonomous coding-agent product discussed during the opening model survey.
Use when: Use this as an example of agent products moving toward longer-running work.
Local activity capture for searchable work context.
Use when: Compare approaches to recovering prior work from durable traces.
A developer work-memory and context product.
Use when: Compare local continuity and retrieval approaches.
A repository for a reusable text-flow experiment.
Use when: Inspect a concrete prompt-to-flow implementation.
A generated product used as a design and implementation example.
Use when: See the result before inspecting its source repository.
The source repository behind the product example.
Use when: Compare generated experience with inspectable implementation.
A workspace surface for seeing parallel agent activity.
Use when: Use this when designing visible execution, verification, and status lanes.
Issue and project tracking referenced during workflow discussion.
Use when: Use this when connecting agent work to an existing task system.
A proxy and launcher experiment for coding-agent sessions.
Use when: Inspect one approach to normalizing launch behavior.
A published account of AI-assisted review at production scale.
Use when: Use this as external context for evidence-first review workflows.
Cross-platform screenshot and annotation tooling.
Use when: Use this to create annotated visual prompts.
A macOS screenshot and annotation tool.
Use when: Use this to point directly at a visual defect.
The repository for composing text, files, and other evidence into prompts.
Use when: Inspect or adapt the prompt-composition workflow.
A command-line surface for Google services.
Use when: Use this as an example of piping external system context into a flow.
A command-line social workflow tool.
Use when: Use this as another example of a tool that can feed a reusable flow.
A visual code-relationship explorer shown during workflow experiments.
Use when: Use it for orientation; do not treat the workshop as proof of token savings.
Searchable shell history across sessions and machines.
Use when: Use this to locate the command that produced a durable artifact.
A skill interface for coding-agent session search.
Use when: Use this when recovering a decision from prior agent conversations.
The source repository behind CASS.
Use when: Inspect the underlying conversation-search implementation.
A board for collecting and comparing visual references.
Use when: Use it to anchor variation work in visible references.
Design guidance and reusable taste constraints for agents.
Use when: Use it when turning preferences into a durable design contract.
A public collection of agent skills referenced during preference work.
Use when: Browse examples of packaged instructions and workflows.
A repository-context bundler and browser consult workflow.
Use when: Use this when an independent reasoning path can change a costly decision.
The prepared companion for video-assisted analysis.
Use when: Use this when timing or transient screen behavior matters.
A live multimodal model surface shared during the video discussion.
Use when: Use only after verifying current availability and account requirements.
The research notebook and generated artifacts shown near the close.
Use when: Use generated artifacts as navigation, then trace consequential claims to sources.
A dictation tool shared during the VISION.md discussion.
Use when: Use voice input when speaking product direction is faster than typing it.
No resources match this search and filter.