WebinarNotes/wiki/queries/2026-07-22-webinar-theses.md

Webinar Theses — From Chat Box to Your Own Agentic OS

#query

⚠️ SUPERSEDED 2026-07-28 by 2026-07-28-webinar-theses. Use that page. This one is preserved as the 2026-07-22 state of thinking (7 sources).

What the refresh changed, in short:

• Thesis 3 ("Skills are the new memory") was reframed to context you author beats context that's inferred — the v1 wording has a live counter-example (thorsten-ball ships 99%-AI-written code with no skills, no MCP, no slash commands) and the reframe is what all four practitioners actually agree on. See skills-as-memory for the three competing readings.
• Thesis 5 ("you build it, one small tool at a time") went from assertion to evidenced via explosion-of-internal-software.
• Three theses added that this set had no source for: verification / ask-for-checks, shedding weight, and ask-for-15-options.
• Flagged by 2026-07-28-lint as two ingests stale and effectively orphaned; the refresh is the fix.

Question

"I need to make some theses for the webinar (theme: 'from chatbox to your own agentic operating system'). What theses can I suggest based on what you already have?" (2026-07-22)

Answer — candidate theses

Grouped by the role they play in the talk. Each thesis is one sentence you could put on a slide; the sub-line is the grounding.

The spine (what the talk claims)

1. The model isn't the product — the harness is. Same model at every level of the demo; only the harness around it grows. The journey from chat box to OS is a journey of harness, not intelligence. — harness, Webinar script closing arc
2. A chat box is an app you open; an OS is a system that runs around you. The perspective shift is stranger → doer → yours → teammate → knows-you → always-on. — Webinar Plan through-line
3. Skills are the new memory. A folder plus a plain-text note — no code — is how the assistant stops being stateless and starts sounding like you. — skills-as-memory (Konstantin ↔ Allie ↔ Eugene convergence)
4. Context is the scarce resource. Every capability rung (tools → memory → skills → processes) is really a technique for spending limited context wisely. — context-as-scarce-resource, evolution-of-agent-tooling
5. You don't buy your OS — you build it, one small tool at a time. Tools made for exactly one person, in an evening, asked-for rather than written. — Webinar script (OS section), personal-ai-operating-system

The stakes (why now)

6. The cost of producing work is going to zero; value migrates to directing and verifying it. Judgment, ownership, taste, and relationships are what stay yours. — vault through-line (code-as-throwaway, product-ownership)
7. The gap between AI users and everyone else compounds — and is becoming irreversible. The person who builds their OS this week fears no release, because each new capability slots into a system that already knows them. — 2026-07-14-gap-between-ai-users-irreversible
8. The more the world is mediated by AI proxies, the more valuable real human connection becomes. The "market of one" raises, not lowers, the price of being human. — connections-as-moat (Sebastian ↔ Allie ↔ Eugene)

The obstacles (what the audience actually hits)

9. Adoption is blocked by friction, not resistance. People aren't against AI — the setup is. Remove three clicks and they come. — 2026-07-14-nina-interview, 2026-07-14-yulia-interview
10. Even advanced users hit structural walls: no durable memory, integrations that dead-end, drift on loose specs. The skills rung is the corpus's answer to the first and third. — 2026-07-21-larysa-interview, integration-dead-ends
11. Leave less room for imagination. Every gap in your instructions gets filled — invisibly. Tight specs and frozen skills are how you keep the agent honest. — leave-less-room-for-imagination

The method (what to do)

12. Solve first, then skillify. Don't design abstractions up front — solve the task once in conversation, then freeze the working recipe into a skill (~3 messages or >5 tool calls = it's skill time). — solve-first-then-skillify
13. The assistant does the research; you do the judgment. The Insights Collector meta-punchline: this very talk was mined out of AI-processed interview notes. — Webinar Plan §3, 2026-07-14-sebastian-eugene-interview
14. Walk in a week what took the industry three years. One hour for foundation docs, one skill from your #1 recurring annoyance, one real file in Claude Desktop tonight. — Webinar Plan §5, levels-of-ai-usage

Honest tensions (if you want a "debates" slide or Q&A ammo)

• Personal harness (Eugene) vs company-managed harness (Sebastian) — enterprise-ai-reality
• Built-in agent memory as anti-feature (Eugene/Larysa) vs persistent context docs used happily (Allie) — skills-as-memory
• Tight specs (leave-less-room-for-imagination) vs wide latitude (think-wider-not-bigger)

Evidence trail

• overview — through-line and agree/diverge map
• Raw deliverables (authored, read directly; since moved to raw/notes/): raw/notes/Webinar Plan - From Chat Box to Your Own OS.md, raw/notes/Webinar script.md (script ladder: Chat box → ReAct → Tools → Memory → Skills → Process → OS), raw/notes/Ideas for webinar.md
• Source summaries: 2026-07-14-skills-based-on-git, 2026-07-14-gap-between-ai-users-irreversible, 2026-07-14-everything-we-knew-about-software-has-changed, 2026-07-14-sebastian-eugene-interview, 2026-07-14-nina-interview, 2026-07-14-yulia-interview, 2026-07-21-larysa-interview

Follow-up questions

• Which subset fits the 30-min format? (Recommend: 1, 2, 3, 7, 9, 12, 14 as the seven load-bearing ones — one per talk segment.)
• Should theses 9–11 (obstacles) get their own station on the spine, or live inside "Do this tonight"?
• Ingesting the three webinar deliverable docs would let future queries cite them as wiki sources instead of raw.

Changed existing pages?

No concept/entity pages changed — this is pure synthesis. index.md and log.md updated.