Agentic Software Factory workshop · July 17, 2026

Learn by the problem you need to solve

Choose a path, then move through orientation → concept → evidence → practice → reflection → next action. Progress stays in this browser.

Your route

How each lesson works

Scan what to notice and what to try. Open the supporting context only when you need it. Quotes are lightly edited for clarity; every timestamp opens the original recording.

How do I add autonomy without losing control?

Control and safety

Bound the task, place policy near the action, and make proof visible.

Now00:15:52–00:50:18

Bound one factory loop

What to notice

Turn one recurring task into an inspectable loop with inputs, permissions, proof, a human gate, and a durable receipt.

Try this

Write Input → Boundary → Action → Evidence → Decision → Receipt for one task you already repeat.

“If the agents can't see it, it doesn't exist.”

John Lindquist · 00:23:25
Why it works + more evidence

Concept

A software factory is not a pile of agents. The agent is one machine inside the loop. Start with the smallest reversible bet, then name the exact action that must stop for human approval.

Reflection

A gate is not “review this sometime.” It is a named stop, named evidence, and explicit approval before a consequential action.

Recording evidence: listen at 00:15:52.

“Alignment is the key word here. Is the agent aligned with your vision?”

John Lindquist · 00:32:52

Links shared for this topic

Now00:57:58–01:16:45

Put policy at the narrowest boundary

What to notice

Make stable intent and risk rules arrive before the action they should change.

Try this

Choose one risky or noisy command and write a read-only policy contract before implementing a hook.

“Meaning that… It won't ever miss because you're configuring the place where the agent is running.”

John Lindquist · 01:02:42
Why it works + more evidence

Concept

Repository files explain stable intent. Launch wrappers normalize repeated choices. Command decorators place warnings near an action. Human gates protect irreversible work. Automated checks prove correctness.

Reflection

The recorded environment demo surfaced diagnostics. Treat it as a pattern with failure evidence, not a clean universal implementation.

Recording evidence: listen at 00:57:58.

“Once this is run, we have an observable thing that shows us this is exactly what the outcome will be, and then do it.”

John Lindquist · 01:14:20
Next01:21:23–02:01:26

Keep wrappers thin and work visible

What to notice

Remove flag memorization while keeping the real command, task state, logs, and verification inspectable.

Try this

Create three visible responsibilities: execution, verification, and logs or status.

“Kind of forget the flags, especially if you're someone jumping back and forth between the different harnesses.”

John Lindquist · 01:23:01
Why it works + more evidence

Concept

A wrapper earns its place when it prevents a repeated mistake and remains easy to trace. More panes do not create understanding. Add a surface only when it represents an independently observable responsibility.

Reflection

The presenter’s terminal stack is an example. The reusable practice is consistent launch behavior and visible state.

Recording evidence: listen at 01:21:23.

“The beauty of owning your own tools is you can have them test themselves, and write themselves, and tackle themselves.”

John Lindquist · 01:37:37

Links shared for this topic

  • Herdr — A workspace surface for seeing parallel agent activity.
  • Linear — Issue and project tracking referenced during workflow discussion.
  • Claudex — A proxy and launcher experiment for coding-agent sessions.
  • Cloudflare AI code review — A published account of AI-assisted review at production scale.

How do I give an agent the right evidence?

Prompt and context

Use visual evidence, compose a focused packet, and turn repeated prompts into inspectable flows.

Now02:15:42–02:34:33

Point at the visual problem

What to notice

Replace vague design prose with an annotated image, a bounded target, and a visible success condition.

Try this

Mark the smallest visual defect, name what must remain unchanged, and ask for one observable correction.

“Screenshot, draw an arrow, or multiple arrows, and then paste.”

John Lindquist · 02:18:19
Why it works + more evidence

Concept

Images carry layout evidence that text often loses. Keep the request narrow: target, constraint, expected result, and one check at the viewport where the problem appears.

Reflection

An image can show a symptom without proving its cause. Ask the agent to inspect the implementation before choosing a fix.

Recording evidence: listen at 02:15:42.

“Please, after you're done generating the HTML, take a screenshot of the page and compare the two, so you get a diff.”

John Lindquist · 02:21:37

Links shared for this topic

  • Flameshot — Cross-platform screenshot and annotation tooling.
  • Shottr — A macOS screenshot and annotation tool.
Next02:34:33–02:51:53

Compose only the evidence the task needs

What to notice

Build a prompt packet from text, files, images, and fresh state without smuggling in an entire stale session.

Try this

List the minimum sources needed to decide, act, and verify; remove everything that cannot change one of those steps.

“How can I consolidate that into something that's gonna manage it for me?”

John Lindquist · 02:37:56
Why it works + more evidence

Concept

Input is a task plus evidence. Output is a result with a named check. The tradeoff is simple: extra context can add capability, but it also hides contradictions and consumes review attention.

Reflection

A large packet is not automatically a complete packet. Prefer relevant, current, and inspectable evidence.

Recording evidence: listen at 02:34:33.

“I usually spend the most amount of time preparing that initial prompt.”

John Lindquist · 02:39:00

Links shared for this topic

Next02:51:53–03:38:37

Turn good prompts into inspectable flows

What to notice

Reuse a task recipe that can inject fresh command output, preserve prompt structure, and expose what the agent will receive.

Try this

Promote one prompt you have run twice into a flow with declared inputs and a dry-run inspection path.

“If you think of managing context as having only the context that I need for the specific task that I want.”

John Lindquist · 02:55:29
Why it works + more evidence

Concept

A flow should remove repeated composition work, not hide it. Inspect the rendered prompt, run from known state, and preserve failures when the wrapper or check does not behave as expected.

Reflection

The recorded wrapper test did not become a clean success. The companion keeps that failure visible instead of rewriting history.

Recording evidence: listen at 02:51:53.

“It's a pre-processing step, where it runs the code that's inside of here, which means it preloads context into the markdown file.”

John Lindquist · 03:15:06

Links shared for this topic

  • Flow Text source — A repository for a reusable text-flow experiment.
  • gog CLI — A command-line surface for Google services.
  • Birdclaw — A command-line social workflow tool.
  • CodeGraph — A visual code-relationship explorer shown during workflow experiments.

How do I get better options instead of one plausible answer?

Design and taste

Generate structural alternatives, compare them, and preserve the reasons behind your choice.

Next04:42:47–05:05:27

Diverge first, then record taste

What to notice

Make important design choices visible while change is cheap, then turn preference into a reusable contract.

Try this

Generate four structurally distinct options, compare pairs, and record both the winning property and the rejection reason.

“When code is disposable, code is cheap.”

John Lindquist · 04:43:09
Why it works + more evidence

Concept

Hold content and product intent constant while varying hierarchy, density, navigation, and interaction emphasis. Promote repeated choices into DESIGN.md so the next agent can apply and challenge them.

Reflection

Four options is a bounded companion exercise. The recorded demonstration produced more; neither count is a universal rule.

Recording evidence: listen at 04:42:47.

“Never underestimate the power of just, being a curator. When the agent can be a generator.”

John Lindquist · 04:50:49

Links shared for this topic

  • Mini Arcade — A generated product used as a design and implementation example.
  • Mini Arcade source — The source repository behind the product example.
  • Inspiration Board — A board for collecting and comparing visual references.
  • Impeccable — Design guidance and reusable taste constraints for agents.

How do I recover work and diagnose what really happened?

Continuity and debugging

Rebuild trustworthy state and attach human testimony to runtime evidence.

Now04:20:03–04:42:47

Recover state before continuing

What to notice

Reconstruct the smallest trustworthy state packet instead of asking a new session to absorb stale scrollback.

Try this

Capture objective, current tree, last verified result, settled decisions, open risks, next action, and its success check.

“Just ask the agent, or ask yourself: how could I break this into a smaller task?”

John Lindquist · 04:28:49
Why it works + more evidence

Concept

History tells you where to look. The working tree, commits, tests, files, and generated artifacts tell you what is true. End long runs with one named verification so the next session inherits evidence, not confidence.

Reflection

An old continuity file can be worse than no file because it looks authoritative. Recheck it against current state.

Recording evidence: listen at 04:20:03.

“So it has a context bundle to work against.”

John Lindquist · 04:31:03

Links shared for this topic

  • Screenpipe — Local activity capture for searchable work context.
  • Pieces — A developer work-memory and context product.
  • Atuin — Searchable shell history across sessions and machines.
  • CASS skill — A skill interface for coding-agent session search.
LaterPrepared follow-up · no dedicated recording section

Attach testimony to runtime evidence

What to notice

Give a debugging agent the exact moment of failure, the human-observed symptom, and a bounded event trail.

Try this

Reproduce one bug, add one plain-language marker when behavior becomes wrong, and export a redacted packet for ranked hypotheses.

“I see this, and I wanna talk about that.”

John Lindquist · 02:22:16
Why it works + more evidence

Concept

The prepared Markers material combines human testimony with nearby console, fetch, error, and click events. That makes the next diagnostic question smaller and more discriminating.

Reflection

This module was prepared after the workshop and was not taught as a dedicated recorded section.

Recording evidence: prepared follow-up grounded in related recorded evidence.

“A lot of us spend time trying to describe bugs instead of just recording ourselves using the product.”

John Lindquist · 05:21:57

When is a stronger model or recording worth the overhead?

Advanced reasoning and video

Escalate only the hard decision and use video when behavior is the evidence.

Later05:05:27–05:25:50

Escalate the decision, not the workflow

What to notice

Spend frontier-model or video-analysis overhead only where a second reasoning or observation path can change the decision.

Try this

Bring one decision, a filtered evidence bundle, alternatives, hidden assumptions, a discriminating experiment, and a reversal plan.

“Might as well use the maximum intelligence I have access to.”

John Lindquist · 05:11:10
Why it works + more evidence

Concept

Use deeper reasoning for hard-to-reverse architecture, obscure stacks, contradictory evidence, or independent verification. Use video when timing, pointer movement, or transient UI state is the evidence.

Reflection

Workshop model names, plan tiers, prices, and limits are dated statements, not current purchasing guidance.

Recording evidence: listen at 05:05:27.

“So, it's able to walk through and analyze the videos, in chunks, in shards.”

John Lindquist · 05:19:43

Links shared for this topic

How do I automate without creating noise?

Vision and automation

Give agents durable direction, promote only proven signals, and keep open work visible.

Next05:25:50–05:40:36

Let vision guide automation

What to notice

Keep code as implementation truth while giving agents durable product direction and an explicit adherence dial.

Try this

Draft VISION.md from product evidence, then mark Preserve, May change, Must ask, and Verification for one task.

“Code is a source of truth.”

John Lindquist · 05:35:33
Why it works + more evidence

Concept

Vision describes the user, outcome, qualities, durable constraints, and open decisions. It should guide improvement without freezing a stale architecture into permanent context.

Reflection

VISION.md and AGENTS.md can serve different roles. Do not silently collapse product direction and operating instructions.

Recording evidence: listen at 05:25:50.

“This defines the end ideal of this product. And no matter what the state of the product is in, it can always push more towards that vision.”

John Lindquist · 05:37:00

Links shared for this topic

  • Workshop NotebookLM notebook — The research notebook and generated artifacts shown near the close.
  • Handy — A dictation tool shared during the VISION.md discussion.
Reference05:40:36–05:53:13

Close the loop without hiding open work

What to notice

Separate answered questions, dated claims, standing offers, and still-open deliverables.

Try this

Check the question and promise companions before depending on current dotfiles, model economics, or individual follow-up.

“And how important to you is it that it's 100% correct or even better than you expected is an important factor.”

John Lindquist · 05:44:28
Why it works + more evidence

Concept

A useful follow-up preserves status. The recording and agenda are available. Current dotfiles and comparative model-cost guidance remain open. Individual email support remains a standing offer, not a publicly verifiable artifact.

Reflection

Do not treat a generated summary or dated workshop claim as current source truth.

Recording evidence: listen at 05:40:36.

“I'll try and follow up with some more reliable information there, but…”

John Lindquist · 05:52:06