chore: initial commit of vault before dashboard work

wiki/entities/allie-miller.md

@@ -0,0 +1,31 @@
+# Allie Miller
+
+#entity
+
+## Summary
+
+Ex-Amazon AI leader; advises OpenAI / Google / Anthropic and Fortune 500s. Popularizes the idea of a **[[personal-ai-operating-system]]** — persistent context, reusable skills, and proactive scheduled agents.
+
+## Current Understanding
+
+Allie's thesis is that the durable advantage is *infrastructure*, not prompting: build foundation context docs once, layer composable skills and scheduled workflows, and every new model release "slots into a system you already understand." She stresses mindset (agency + taste) over expertise.
+
+## Evidence
+
+- Interview "In 1 Year, the Gap… Will Be Irreversible": 3 foundation docs, 4 Claude surfaces, "just complain," proactive workflows, 4-tier model of AI work, trust calibration — [[2026-07-14-gap-between-ai-users-irreversible]].
+- Self-reported setup: 36 proactive workflows, ~28 master agents, ~100 total agents; 2–10× productivity.
+
+## Related Pages
+
+- Concepts: [[personal-ai-operating-system]], [[skills-as-memory]], [[context-as-scarce-resource]], [[connections-as-moat]]
+- Tools: [[claude-code]]
+- Compare: [[konstantin]] (same skills-as-memory idea, engineering framing), [[theo-browne]]
+- Comparison: [[theo-konstantin-allie]] — three-lens side-by-side (Theo/Konstantin/Allie)
+
+## Contradictions / Uncertainty
+
+- Predicts near-term "self-learning models with real weight updates" — distinguished from today's memory-file retrieval. Forward-looking; Status: tentative.
+
+## Next Questions
+
+- Reusable templates for the Personal Constitution / Goals / Business Strategy docs? (Directly webinar-relevant.)

wiki/entities/claude-code.md

@@ -0,0 +1,42 @@
+# Claude Code
+
+#entity
+
+## Summary
+
+Anthropic's agentic coding CLI/harness, cited across all four ingested sources as the reference [[harness]]. Used interactively and in fire-and-forget / scheduled modes.
+
+## Current Understanding
+
+Claude Code recurs as the concrete example of the "universal agent" pattern: a short system prompt, ~10–40 file/shell/search tools, a ReAct runtime loop, standardized key files (CLAUDE.md, `skills/`), and native scheduling. It supports both [[skills-as-memory|skills]] and MCP — and notably converts MCP servers *into* skills so their tools don't all hit context at once, erasing most MCP downsides ([[evolution-of-agent-tooling]]).
+
+**Practitioner limits** (from the [[2026-07-21-larysa-interview|Larysa interview]]) — the corpus's most critical first-hand read:
+
+- **Built-in memory is judged an anti-feature** by Eugene ("it'd be better if it didn't [exist]"); use skills instead. See [[skills-as-memory]].
+- **Connectors overpromise.** The agent begins work before establishing whether an integration is implemented or available for the user's account tier — see [[integration-dead-ends]]. Slack has first-class Anthropic support (paid seat required); Teams is treated as a dead end; Figma editing needs a paid account.
+- **Model selection matters within the family.** Eugene runs **4.7** in production and avoids **4.8** as "too proactive." Code output is considered production-safe from ~**4.6** onward, excluding authorization and payments ([[code-as-throwaway]]).
+- **Testing surface:** browser/web testing works; a mobile emulator got badly stuck.
+
+## Evidence
+
+- **Allie Miller:** one of "4 Claude surfaces" — the maximum-control one, with native scheduling — [[2026-07-14-gap-between-ai-users-irreversible]].
+- **Konstantin:** used (leaked) as a hackathon backend; example harness; turns MCP into skills — [[2026-07-14-skills-based-on-git]].
+- **Sebastian/Eugene:** Eugene's custom harness is built on Claude Code; solved the printer protocol in ~30 min on-site — [[2026-07-14-sebastian-eugene-interview]].
+- **Theo Browne:** markdown-file service piped to Codex/Claude on a cron — [[2026-07-14-everything-we-knew-about-software-has-changed]].
+- **Larysa/Eugene:** memory critique, connector dead-ends, 4.6/4.7/4.8 model selection, emulator failure — [[2026-07-21-larysa-interview]].
+
+## Related Pages
+
+- Concepts: [[harness]], [[skills-as-memory]], [[agentic-loops]], [[context-as-scarce-resource]], [[integration-dead-ends]], [[leave-less-room-for-imagination]]
+- Entities: [[eugene]], [[larysa]]
+- Related tools: [[hermes]] (skills-first harness), Codex CLI, OpenClaude (a Claude Code fork), Cursor, Conductor
+
+## Contradictions / Uncertainty
+
+- Sources treat Claude Code as the harness baseline but disagree on governance: personal/custom (Eugene) vs company-managed at scale (Sebastian — see [[enterprise-ai-reality]]).
+- Model-version judgements (4.7 good / 4.8 too proactive) are one practitioner's production preference at one point in time, not a benchmark, and will date quickly. Status: tentative.
+
+## Next Questions
+
+- What does a compliant, company-managed Claude Code deployment look like for regulated teams?
+- Is there a supported way to make the agent check integration entitlements *before* starting a task?

wiki/entities/eugene.md

@@ -0,0 +1,39 @@
+# Eugene
+
+#entity
+
+## Summary
+
+Senior software engineer (20+ years, ~20 commercial; computer vision, embedded/firmware, Edge Compute/IoT at [[inspectron]]), content creator, and builder of a custom [[claude-code|Claude Code]] [[harness]]. Author and presenter of the webinar *"From a chat box to your own operating system"*; interviewer of [[sebastian]], [[nina]], [[yulia]], and [[larysa]]. Champions "bring your own harness" and building small AI tools for yourself.
+
+## Current Understanding
+
+Eugene argues every developer should build a personal harness because knowing every detail makes it far more effective; he demoed one (Telegram-like UI, one agent per project, inter-agent messaging, per-agent memory, "done thinking" signal). His stated unsolved problem — building a professional network — is what makes [[connections-as-moat]] the interview's emotional center; notably, in [[2026-07-14-yulia-interview]] he independently lands on the same residual ("the human's role is just to be human — introductions, communication").
+
+Heavy Claude user on the **$200 max plan**; ran 7 project-agents in parallel; built the record→diarize→transcribe→summarize tool whose output *is* the two HR interview raws. Teaches [[levels-of-ai-usage]] and [[solve-first-then-skillify]] as the non-programmer curriculum. Predicts AI prices rise, not crash ("what I now buy for 200 will cost about 1,000"). A paid build of the HR candidate-base system for Yulia's team is on the table.
+
+**Positions sharpened in the [[2026-07-21-larysa-interview|Larysa interview]]:** built-in agent memory is an anti-feature, not an unfinished one ("it'd be better if it didn't [exist]") — [[skills-as-memory|skills]] replace it; consolidate into one workspace rather than tool-hopping ("my life just split into before and after"); [[leave-less-room-for-imagination|leave less room for imagination]], which is also his critique of build-a-whole-project-in-two-prompts demos. Runs **Claude 4.7** in production, avoiding 4.8 as "too proactive"; considers AI-written code production-safe from ~4.6 but withholds **authorization and payments**. Claims his diarization + role-inference pipeline is the real differentiator over plain GPT transcription, which "only guesses who spoke."
+
+**Likely identity:** Eugene appears to be the **owner/author of this vault** and of the webinar being prepared. Status: **tentative but strengthened** — both HR interviews name him as the webinar's author/presenter and the tool-builder; the raw `Ideas for webinar.md` notes share his references.
+
+## Evidence
+
+- Interview: BYO-harness demo, tools (Conductor for git-worktree isolation; references [[hermes]]), projects **insin** (apt-get-style edge updater) & **Keller**, the ~6-month networking blocker — [[2026-07-14-sebastian-eugene-interview]].
+- Webinar author/presenter, Inspectron, one-button interview tool, 7 parallel agents, English-first webinar titled *"From a chat box to your own operating system"* — [[2026-07-14-nina-interview]].
+- $200 max plan, levels ladder, solve-first method, price-rise prediction, paid HR-system offer, manager/subordinate framing — [[2026-07-14-yulia-interview]].
+- Memory-as-anti-feature, consolidation pitch, imagination/drift principle, 4.7-over-4.8, auth/payments carve-out, diarization+role-inference claim — [[2026-07-21-larysa-interview]].
+
+## Related Pages
+
+- Entities: [[sebastian]], [[nina]], [[yulia]], [[larysa]] (interview counterparts), [[inspectron]] (employer), [[virtido]] (webinar audience)
+- Concepts: [[harness]], [[connections-as-moat]], [[product-ownership]], [[decoupling-identity-from-profession]], [[levels-of-ai-usage]], [[solve-first-then-skillify]], [[leave-less-room-for-imagination]], [[integration-dead-ends]]
+- Tools: [[claude-code]], [[hermes]]
+
+## Contradictions / Uncertainty
+
+- Disagrees with Sebastian: BYO-harness vs company-managed; OSS as marketing vs growth; LinkedIn/content vs in-person networking.
+- Vault-owner identity is inferred; confirm before treating as fact.
+
+## Next Questions
+
+- Concretely, how does Eugene build a connections network from a standing start? (The interview's biggest open question.)

wiki/entities/hermes.md

@@ -0,0 +1,30 @@
+# Hermes
+
+#entity
+
+## Summary
+
+An AI agent [[harness]] built **entirely around [[skills-as-memory|skills]]** — it not only uses skills but creates and curates them autonomously. Central to [[konstantin]]'s talk; also referenced by [[eugene]] among his tools.
+
+## Current Understanding
+
+Hermes is the concrete demonstration of "skills as memory": it auto-creates a skill when a task costs >5 tool calls, and runs a two-layer **curator** — pruning skills unused for 30 days (deactivate) / 90 days (archive) and consolidating small skills weekly so their short-descriptions don't eat context. Konstantin reports it grew from 56 → 100 skills and kept working — impossible with classic tools.
+
+## Evidence
+
+- Konstantin's talk: auto-improvement mechanism, curator, Telegram access to shared git skills — [[2026-07-14-skills-based-on-git]].
+- Eugene lists it among his harness tools ("open clock, Hermes, paperclip") — [[2026-07-14-sebastian-eugene-interview]].
+
+## Related Pages
+
+- Entity: [[konstantin]], [[eugene]]
+- Concepts: [[skills-as-memory]], [[harness]], [[agentic-loops]], [[context-as-scarce-resource]]
+- Related tools: [[claude-code]], OpenClaude, Codex CLI
+
+## Contradictions / Uncertainty
+
+- The curator thresholds are Hermes-specific heuristics, not validated standards. Status: tentative.
+
+## Next Questions
+
+- How do Hermes' auto-consolidation decisions avoid merging skills that should stay distinct?

wiki/entities/inspectron.md

@@ -0,0 +1,28 @@
+# Inspectron
+
+#entity
+
+## Summary
+
+The company where [[eugene]] works as a senior software engineer (Edge Compute / IoT). Appears in the corpus only as background context for Eugene's day job, distinct from his webinar/AI-tooling work with the [[virtido]] HR team.
+
+## Current Understanding
+
+Both HR interviews identify Eugene as working "at Inspectron" / "on Inspectron and its clients" with ~20 years of commercial experience. No further detail about the company itself is in the corpus.
+
+## Evidence
+
+- Eugene described as senior engineer at Inspectron, Edge Compute / IoT — [[2026-07-14-nina-interview]].
+- "Works on Inspectron and its clients" — [[2026-07-14-yulia-interview]].
+
+## Related Pages
+
+- Entities: [[eugene]], [[virtido]] (the other company in the corpus)
+
+## Contradictions / Uncertainty
+
+- Nina's summary frames it as employment ("works at"); Yulia's as project work ("works on Inspectron and its clients"). Employment vs contracting is unclear. Status: tentative.
+
+## Next Questions
+
+- Is Eugene an employee or contractor? Does Inspectron relate to his **insin** edge-updater project (mentioned in [[2026-07-14-sebastian-eugene-interview]])?

wiki/entities/konstantin.md

@@ -0,0 +1,33 @@
+# Konstantin (Sber / GigaChat)
+
+#entity
+
+## Summary
+
+Engineer on Sber's GigaChat development team, doing R&D on agents. Author of the talk arguing that **git-based [[skills-as-memory|skills]] are the new memory of AI agents**.
+
+## Current Understanding
+
+Konstantin brings the model-builder's / R&D lens. His core architectural claim: put tools + data + usage history in one git repo and let the [[harness]] decide what to load. He maps the field's evolution (tools → MCP → skills, then [[agentic-loops|agent loops]]) and demonstrates auto-improvement (a weak GigaChat going 1/89 → 11/89 on a benchmark over a weekend).
+
+## Evidence
+
+- Talk "Git-based skills — the new memory of AI agents": harness definition, two-stage skill loading, git rules + CI back-pressure, personal DNA/trip/HR skills, Hermes curator, Ralph/meta loops — [[2026-07-14-skills-based-on-git]].
+- Hackathon record: 7th (Interpress-Ex, infinite-loop harness), 3rd/1st-technical (Snowbase), observed 19/20 top BitGen teams on harnesses.
+
+## Related Pages
+
+- Concepts: [[skills-as-memory]], [[harness]], [[evolution-of-agent-tooling]], [[agentic-loops]], [[context-as-scarce-resource]]
+- Tools: [[hermes]] (skills-first harness he uses/extends), [[claude-code]]
+- Timeline: [[ai-agent-evolution]]
+- Compare: [[allie-miller]] (same skills-as-memory idea, business framing), [[theo-browne]] (orchestration era)
+- Comparison: [[theo-konstantin-allie]] — three-lens side-by-side (Theo/Konstantin/Allie)
+
+## Contradictions / Uncertainty
+
+- Pruning windows (30/90 days) and the ">5 tool calls → make a skill" rule are presented as working heuristics from Hermes, not established standards. Status: tentative.
+- No standards yet for what data to put in a skill or its upper size limit.
+
+## Next Questions
+
+- How to build world-models / give agents perception (his own "missing piece")?

wiki/entities/larysa.md

@@ -0,0 +1,39 @@
+# Larysa
+
+#entity
+
+## Summary
+
+Technical business analyst / project manager and former mobile developer; interviewed by [[eugene]] as the **project-management** voice in the webinar-scoping series (alongside [[nina]] and [[yulia]]). The most technically deep non-engineer in the corpus — and the one whose frustrations are most structural.
+
+## Current Understanding
+
+Larysa is a power user by any reasonable measure: she opens pull requests, wires Claude to **ClickUp** (a Jira analog) and **Figma**, builds clickable prototypes, and writes user stories and tests. She is enthusiastic but worn down — not by wrong answers, but by two failure modes that cost her time and tokens:
+
+1. **No memory between sessions.** She explains something one day; the next day it is gone and she re-pays for the explanation. This is her stated core problem.
+2. **[[integration-dead-ends|Integrations that dead-end]].** Claude confidently starts a task, then discovers the connector isn't implemented or isn't available for her *private* (vs. corporate) account — half an hour in. "I don't know how to fight this."
+
+Her blocked builds are instructive: a Teams bot that would watch a work chat and auto-create ClickUp tasks (Teams offers no usable external API); Slack (first-class Claude support, but needs a paid seat she isn't given); full editable Figma access (needs a personal paid account).
+
+Diagnostically she sits **high on [[levels-of-ai-usage]]** — well past chatbot, acting on real files and systems — but without the [[skills-as-memory|skills]] rung, which is exactly why her pain reads as "the agent forgot." Skills are the one topic Eugene committed to covering for her in the webinar.
+
+## Evidence
+
+- Role, tooling (ClickUp/Figma/PRs/prototypes/user stories/tests), memory complaint, integration dead-ends, Teams/Slack/Figma blockers, emulator-vs-browser testing note — [[2026-07-21-larysa-interview]].
+- Flagged twice as an un-interviewed gap before this ingest — [[2026-07-14-nina-interview]], [[2026-07-14-yulia-interview]].
+
+## Related Pages
+
+- Entities: [[eugene]] (interviewer), [[nina]], [[yulia]] (same interview series), [[virtido]] (affiliation tentative), [[claude-code]]
+- Concepts: [[integration-dead-ends]], [[skills-as-memory]], [[leave-less-room-for-imagination]], [[levels-of-ai-usage]], [[solve-first-then-skillify]]
+
+## Contradictions / Uncertainty
+
+- Name is taken from the raw filename and the summary's speaker label; spelled "Larisa" in earlier notes. Status: tentative.
+- Employer never stated; [[virtido]] inferred from the shared interview series. Status: tentative.
+
+## Next Questions
+
+- Does the skills rung actually resolve her memory complaint, or is her problem cross-*project* context (which skills don't solve)?
+- Would her employer supply the paid Slack/Figma seats if a working prototype existed — i.e. is the blocker technical or budgetary?
+- What was her BA/PM pain point in [[yulia]]'s original three-item list, and does it match what surfaced here?

wiki/entities/nina.md

@@ -0,0 +1,30 @@
+# Nina
+
+#entity
+
+## Summary
+
+HR recruiter at [[virtido]]; among the most AI-forward recruiters on her team. Interviewed by [[eugene]] as a webinar-audience proxy — she supplies the concrete HR use cases (job descriptions, interview write-ups, candidate sourcing) that validate the webinar thesis. Also an ultra-trail runner (50+ km).
+
+## Current Understanding
+
+Nina is the enthusiastic practical adopter: uses paid ChatGPT, LinkedIn Recruiter, and Manatal (ATS). Her biggest pain is interview write-ups — note-taking during a call wrecks the conversation, so automatic transcription is the part that actually changes her work ("this transcript is honestly the most important thing"). She estimates going from ~5 to ~25 candidates/day with Eugene's tooling, but values the **cognitive-load reduction** more than the throughput. Her read on colleagues: they aren't resistant, they lack a frictionless path — "they'd use it if it just transcribed everything for them."
+
+## Evidence
+
+- Pain points, transcript-over-summary, friction-not-resistance, multiplier framing, 5→25 estimate — [[2026-07-14-nina-interview]].
+- Referenced as a budget-approver contact in [[2026-07-14-yulia-interview]].
+
+## Related Pages
+
+- Entities: [[eugene]] (interviewer), [[yulia]] (team colleague/lead), [[virtido]]
+- Concepts: [[solve-first-then-skillify]], [[skills-as-memory]], [[levels-of-ai-usage]]
+
+## Contradictions / Uncertainty
+
+- None recorded; her account is first-hand and consistent with Yulia's.
+
+## Next Questions
+
+- Would her team actually adopt the transcribe→summarize tool if delivered — and can it integrate with Manatal?
+- Multilingual output (EN/DE/UK) was flagged as an unlock — which languages dominate her candidate pool?

wiki/entities/sebastian.md

@@ -0,0 +1,30 @@
+# Sebastian
+
+#entity
+
+## Summary
+
+Founder/owner of [[virtido|Virtido]], a ~11-year software outsourcing/engineering company. Interviewed by [[eugene]]. Brings the services-business, client, compliance, and sales lens to how AI reshapes engineering.
+
+## Current Understanding
+
+Sebastian agrees AI can write software and that teams collapse to 2–3 people, but his signature contribution is the **enterprise counterpoint**: [[harness|"bring your own harness"]] cannot survive compliance, so a company-managed standard harness is "the interesting market" ([[enterprise-ai-reality]]). His other durable claims: seniors gain / juniors lose ([[seniority-and-the-junior-squeeze]]), and **[[connections-as-moat|in-person relationships are the last non-commoditized asset]]**.
+
+## Evidence
+
+- Interview: team collapse, enterprise lock-down (Roche ~1,200 engineers; banks), printer anecdote, profile-picture ownership story, "Big zero" on digital outreach — [[2026-07-14-sebastian-eugene-interview]].
+- Reports enterprise clients on centrally-managed VMs with zero self-install.
+
+## Related Pages
+
+- Entity: [[eugene]] (interviewer, counterpart), [[virtido]]
+- Concepts: [[harness]], [[enterprise-ai-reality]], [[seniority-and-the-junior-squeeze]], [[product-ownership]], [[connections-as-moat]], [[decoupling-identity-from-profession]], [[code-as-throwaway]]
+
+## Contradictions / Uncertainty
+
+- Disagrees with **Eugene** on harness (BYO vs company-managed), on OSS motivation (marketing vs "more OSS as code gets free"), and on networking channels (online vs in-person).
+- Disagrees with colleague **Daniel** on returning to waterfall planning.
+
+## Next Questions
+
+- How does AI transform ~1,200-engineer, multi-year enterprise programs? (He says he doesn't know.)

wiki/entities/theo-browne.md

@@ -0,0 +1,36 @@
+# Theo Browne (t3.gg)
+
+#entity
+
+## Summary
+
+Developer, educator, and founder (t3.gg / "Ping"); speaker at AIE. Advocates that engineers must radically expand ambition to keep pace with model progress.
+
+## Current Understanding
+
+Theo's argument is psychological as much as technical: senior engineers underuse frontier models because they scope work to what the *previous* model could do. His prescription — **[[think-wider-not-bigger|think wider]]**, shed developer-identity baggage, treat code as disposable — frames the "models aren't that useful for me" complaint as a scoping problem on the human's side.
+
+His second source in the vault sharpens the disposable-code stance into a discipline: **[[make-more-cheap-code]]** — keep hand-verification of shipped code intact (he explicitly rejects shipping unreviewed slop: "I hate them too. We're on the same side") while generating orders of magnitude more never-shipped code for verification and exploration. Recurring author-move across both talks: locate the bottleneck in a *human habit* (scoping, reading ratios), not in the models.
+
+## Evidence
+
+- Talk "Everything we knew about software has changed" (AIE): model eras, tier shift, breadth-vs-depth, G-brain markdown tier — [[2026-07-14-everything-we-knew-about-software-has-changed]].
+- Video "You're reading way too much code": four tiers of code, ship/no-ship line, 100:1 slop-to-ship verification ratio, dumb-model agents as API usability testers — [[2026-07-24-youre-reading-way-too-much-code]]. Mentions his current project **Lakebed** (reads every signature/API there, verifies with slop).
+- Built "Ping" (YC — "Zoom for streamers"), which he uses as the "startup → now a side project" example.
+- Replaced a PR-triage service with a markdown file on a 9 AM cron (Codex/Claude → S3).
+
+## Related Pages
+
+- Concepts: [[think-wider-not-bigger]], [[code-as-throwaway]], [[make-more-cheap-code]], [[decoupling-identity-from-profession]]
+- Timeline: [[ai-agent-evolution]]
+- Compare: [[konstantin]] (model-builder's orchestration view), [[allie-miller]] (personal-OS view)
+- Comparison: [[theo-konstantin-allie]] — three-lens side-by-side (Theo/Konstantin/Allie)
+
+## Contradictions / Uncertainty
+
+- His model-era names ("Sonnet 3.5", "Opus 4.5", "Mythos/Fable") are rhetorical framing; mapping to shipped model IDs is unverified. Status: tentative.
+- His read/write/merge counts (1,000/2,000+/~500 per day) are self-reported illustrations, not measurements. Status: tentative.
+
+## Next Questions
+
+- What does *he* now consider "too big"? (He says he no longer knows.)

wiki/entities/virtido.md

@@ -0,0 +1,36 @@
+# Virtido
+
+#entity
+
+## Summary
+
+A ~11-year-old software outsourcing/engineering company founded and owned by [[sebastian]]. Provides the enterprise/services vantage point in the [[2026-07-14-sebastian-eugene-interview|Sebastian interview]].
+
+## Current Understanding
+
+Virtido works with large, often regulated enterprise clients — the setting for Sebastian's claims about compliance-locked environments and the company-managed-harness market ([[enterprise-ai-reality]]). Team sizes cited: 10–15 engineers on big teams, collapsing toward 2–3 with AI.
+
+Its **HR/recruiting team is the audience for Eugene's webinar**: [[nina]] (recruiter) and [[yulia]] (recruiting lead, affiliation tentative) supplied the concrete pain points — job descriptions, interview write-ups, candidate sourcing — that collapse into "a candidate knowledge base plus search over it." Tooling in use: LinkedIn Recruiter, Manatal (ATS), paid ChatGPT (some team members).
+
+The audience is not only HR: [[larysa]] (technical BA/PM, affiliation tentative) is the third interviewee in the same scoping series, and she extends the tooling picture to **ClickUp** (Jira analog), **Figma**, **Teams** and **Slack** — with the last three blocked by paid-seat or API limits ([[integration-dead-ends]]). Her account also shows the seat-provisioning question is live: Anthropic supports Slack first-class, but she isn't given a seat.
+
+## Evidence
+
+- Interview: 11 years in business, enterprise clients, centrally-managed VMs; playful `humans.verti.com` / LinkedIn "human badge" riff on human differentiation — [[2026-07-14-sebastian-eugene-interview]].
+- HR pain points, team tooling, adoption-friction observation — [[2026-07-14-nina-interview]].
+- Candidate-base conclusion, budget approvers (Nina, Sergiy, "Andryuk"), paid-build discussion — [[2026-07-14-yulia-interview]].
+- BA/PM tooling (ClickUp, Figma) and paid-seat blockers — [[2026-07-21-larysa-interview]].
+
+## Related Pages
+
+- Entities: [[sebastian]] (founder), [[nina]], [[yulia]], [[larysa]], [[eugene]] (webinar presenter)
+- Concepts: [[enterprise-ai-reality]], [[connections-as-moat]], [[seniority-and-the-junior-squeeze]], [[levels-of-ai-usage]]
+
+## Contradictions / Uncertainty
+
+- Client names are largely illustrative (e.g. Roche cited as an industry reference point, not necessarily a Virtido client).
+- [[larysa]]'s employer is never stated; membership is inferred from the shared interview series. Status: tentative.
+
+## Next Questions
+
+- Is Virtido itself building/selling a company-managed harness product, or just identifying the market?

wiki/entities/yulia.md

@@ -0,0 +1,31 @@
+# Yulia
+
+#entity
+
+## Summary
+
+HR/recruiting lead (name inferred from the raw filename, Status: tentative) who brought her team's AI pain points to [[eugene]] and is organizing the webinar on the company side. Self-described beginner; the demand-side counterpart to [[nina]]'s practitioner view.
+
+## Current Understanding
+
+Yulia collected three team pain points and got the conclusion that the two recruiting ones collapse into a single build: a **candidate knowledge base** (record interviews → auto-transcribe → standardized profiles) plus search over it. She controls the process socially — refers to Nina, Sergiy and "Andryuk" as budget approvers — and was explicit there is **no deadline** for the webinar plan. A paid build of the HR system by Eugene is on the table.
+
+## Evidence
+
+- Pain points, candidate-base conclusion, webinar organization, budget approvers, no-deadline stance — [[2026-07-14-yulia-interview]].
+
+## Related Pages
+
+- Entities: [[eugene]], [[nina]], [[larysa]] (third interviewee in the series she organized), [[virtido]] (affiliation tentative — inferred from shared team with Nina)
+- Concepts: [[levels-of-ai-usage]], [[solve-first-then-skillify]]
+
+## Contradictions / Uncertainty
+
+- Speaker name is inferred from the filename "Yulia interview.md"; the transcript summary never names SPEAKER_00. Status: tentative.
+- Her employer is not stated; Virtido is inferred from the shared team with Nina. Status: tentative.
+
+## Next Questions
+
+- Confirm name and affiliation.
+- What was the third team pain point (beyond the two recruiting ones)? **Partially answered:** [[larysa]] has now been interviewed ([[2026-07-21-larysa-interview]]) and her pain points are agent memory loss and [[integration-dead-ends]] — but whether these are the same item Yulia had in her original three-point list is unconfirmed.
+- Webinar structure and scheduling were deferred back to her at the end of the Larysa interview — still open.