# Week 35 — labdocs release and local benchmark

[**Full learning notebook: explanations, step-by-step challenges, stashes and evidence**](./learning-notebook.md) · [NotebookLM export](./notebooklm.txt)

Status: NOT_STARTED. Calendar dates: not assigned. Owner: Peter Ciancaglini. Planning authority: v5 Part 7 with retained v4 details. Deeper walkthrough: [v6 · Week 35 · labdocs, part 3](../../../LABLOOP-Master-Plan-v6.md#week-35--labdocs-part-3). Active project/repository: labdocs.

[Programme](../../README.md) · [Model instructions](../../specs.md) · [Decisions](../../DECISIONS.md) · [Resources](../../SOURCES.md) · [**v6 walkthrough**](../../../LABLOOP-Master-Plan-v6.md#week-35--labdocs-part-3) · [Previous week review](../week-34-labdocs-retrieval-evaluation/review.md) · [Next week](../week-36-journal-and-joss-submissions/specs.md)

## Outcome and relevance

This week delivers the three concrete artifacts below and the supporting learning/branding/opportunity pack. The scientific or commercial outcome follows the preserved source brief, while the acceptance checks make its evidence testable. The career objective is to turn this work into something a scientist, hiring manager or buyer can inspect.

- Scientific/build priority: Connect a batchlens alarm and relevant SOP to a deviation draft with a visible human-review state and supporting evidence.
- Public/profile priority: Prepare Medium deep dive 5, release post and 60-second demo; distinguish confidentiality design from compliance claims.
- Career/relationship/commercial priority: Show the benchmark to one qualified QA or employer contact and ask which deployment constraint matters.

## Deeper walkthrough (v6)

Read [v6 · Week 35 · labdocs, part 3](../../../LABLOOP-Master-Plan-v6.md#week-35--labdocs-part-3) before Monday. It expands this week's one-row v5 brief into daily build steps and adds the **Welcome** analogy, **Learn it** (▶ core and ＋ deeper sources), **Run it** (repos with a 20-40 minute exercise), the **NotebookLM kit** and the mentor check below. Standing v6 rules: [resource rules](../../../LABLOOP-Master-Plan-v6.md#prologue-3--the-resource-rules-so-you-never-waste-an-evening-on-a-bad-source), [NotebookLM protocol](../../../LABLOOP-Master-Plan-v6.md#prologue-4--the-notebooklm-protocol-one-notebook-per-week-zero-decisions), [chapter anatomy](../../../LABLOOP-Master-Plan-v6.md#prologue-5--how-to-read-a-chapter-the-anatomy-identical-for-all-41). v6 adds depth only; it does not change a goal, gate, output or the 600-minute cap, so this specification still governs execution.

**Act VII (finale) · Threads: M, BL, $, R · Next gate: 36**

**Where this week sits.**
- ← **From:** weeks 3-4 (alarms), weeks 33-34 (records, retrieval).
- → **Feeds:** week 36 (JOSS options), week 37 (pilot), week 38 (talk demo), week 39 (fund package).
- ⟳ **Returns in:** every on-prem conversation.

**Goals.**
- 🎯 **This week:** deviation drafting with human approval; on-prem benchmark table; `labdocs v0.1` + Z6; M5 deep dive.
- 🏁 **Next milestone:** Gate 36.
- 🌟 **Final:** three instruments with DOIs, one of them regulated-ready in spirit.

**The plan (from v5 Part 7, expanded; gate and output unchanged).**
> *v5 row:* 35 | labdocs, part 3 | Privacy basics | Deviation drafting + on-prem benchmark table (v4 weeks 16-17) | `labdocs v0.1`, Z6, M5 deep dive
- **Goal:** alarm-to-signed-deviation in minutes, and a hardware/cost table.
- **Tue (study):** privacy and data governance basics: GDPR principles (Art. 5), Argentina Ley 25.326 overview, HIPAA summary (only concepts).
- **Build:** [ ] Mon: deviation drafting: batchlens alarm JSON + retrieved SOP → draft (CAPA fields) → approval step → eLabFTW record with audit entry. Done when one end-to-end deviation is signed. [ ] Wed: benchmark on 200 synthetic pages: mini PC vs 3050 vs one cloud model: accuracy per field, seconds/page, cost per 1,000 pages. Done when `make bench` regenerates the table. [ ] Fri: Docker compose of the stack; release `labdocs v0.1` + Zenodo DOI; M5 draft.
- **Sun:** **M5** deep dive "A lab's AI on a USD 300 computer: what runs where, and how well". Z6.
- **Only one thing:** the benchmark table.

**Mentor check.** *"I can show an alarm becoming a signed deviation, and a table of what a lab can run without sending data anywhere."*

## Required inputs and dependency check

- [Week 33](../week-33-labdocs-ingestion-and-traceability/specs.md): inspect its actual evidence and review; source/code artifacts must exist before the dependent task begins.
- [Week 34](../week-34-labdocs-retrieval-evaluation/specs.md): inspect its actual evidence and review; source/code artifacts must exist before the dependent task begins.
- Read [commitment](./commitment.md), [evidence](./evidence.md), [review](./review.md) and the current root TODAY/PROGRESS/QUESTIONS files.
- Read this week's chapter, [v6 · Week 35 · labdocs, part 3](../../../LABLOOP-Master-Plan-v6.md#week-35--labdocs-part-3), then the standing sections: [Part 0 · how to use the document](../../../LABLOOP-Master-Plan-v6.md#part-0--how-to-use-this-document-read-this-every-monday-for-the-first-month), [Part 3 · the scientific thesis](../../../LABLOOP-Master-Plan-v6.md#part-3--the-scientific-thesis-explained-twice-like-a-kid-then-like-a-reviewer), [Part 4 · curriculum](../../../LABLOOP-Master-Plan-v6.md#part-4--curriculum-from-zero-four-tracks-all-free-exact-units), [Part 8 · the prompt pack](../../../LABLOOP-Master-Plan-v6.md#part-8--the-prompt-pack-copy-paste-fill-the-brackets) and [Part 9 · branding and endorsement](../../../LABLOOP-Master-Plan-v6.md#part-9--branding-connection-ladder-endorsement). The same sections exist in the [v5 master](../../../LABLOOP-Master-Plan-v5.md), which remains the governing sequence; v6 reproduces them and adds depth. Retained commercial/instrument details come from [v4](../../../AI-Upskilling-Plan-Biotech-v4.md).
- Inspect the actual canonical repository state, available data, existing figures and required human/external inputs. Never assume a previous week succeeded from its folder name.
- Verify current resource links, versions, dataset rights and any live company/venue information before relying on them. Use [source catalog](../../SOURCES.md); explicitly record inaccessible resources.

## Seven-day plan: 600 minutes maximum

The model must turn these into exact physical actions using the observed files and available inputs. Each 90-minute block includes start/stop rituals. All calls, posts, debugging, reading and exercises consume this same capacity.

| Day | Budget | Work and stopping condition |
|---|---:|---|
| Monday | 90 min | Connect a batchlens alarm and relevant SOP to a deviation draft with a visible human-review state and supporting evidence. Stop when: Prepare a reproducible labdocs release with one measured local-hardware benchmark and a visible human-review step. |
| Tuesday | 90 min | Read eLabFTW security/deployment documentation and official data-protection guidance applicable to the chosen demonstration; draw the actual data flow. Produce: One concise applied note, a worked decision/example and unresolved questions. |
| Wednesday | 90 min | Benchmark the available mini PC, RTX 3050 and permitted cloud comparator on identical cases, logging accuracy, latency, memory and measured costs. Stop when: Actual device specs, settings and sample counts are given; unavailable hardware is marked untested. Reserve the last 10 minutes for the optional Wednesday note. |
| Thursday | 90 min | Apply benchmark methodology: fixed cases, resource settings, repetitions and cost accounting. Last 30 minutes: relevant deployment/research paper. Apply the Half 2 one-formal-study-block rule. |
| Friday | 90 min | Package labdocs v0.1/Z6, reproduce the benchmark and prepare deployment/data-flow documentation. Stop when: Fake mode and a clean local reproduction work; release/deposit status is evidenced. |
| Saturday | 90 min | Resolve the earliest critical spillover or dependency. Prepare any long-form publication draft from existing figures here if needed. Sandbox only after commitments are met. |
| Sunday | 60 min | 20 min build-log draft/publication when authorized; 5 min evidence/checklist; 20 min source-grounded gap review; 15 min next week's six physical actions. |

Half 2: Tuesday is the formal study block unless this is a selling/submission/decision week. Thursday supports applied review, partner work or the market task; do not add another full course.

## Learning specification

### Biology/domain unit

Material: Read eLabFTW security/deployment documentation and official data-protection guidance applicable to the chosen demonstration; draw the actual data flow.

Produce: One concise applied note, a worked decision/example and unresolved questions.

Understanding check: The note directly supports this week's experiment, collaboration, delivery or career action.

During preparation, write one worked example connected to the week's actual task, one exercise with a separate answer key and five questions. Peter supplies answers; score explanation quality and flag misconceptions in QUESTIONS. Numeric/scientific conclusions require actual data or explicitly synthetic teaching values.

### AI/scientific-method unit

Material: Apply benchmark methodology: fixed cases, resource settings, repetitions and cost accounting. Last 30 minutes: relevant deployment/research paper.

Produce: One concise applied note, a worked decision/example and unresolved questions.

Understanding check: The note directly supports this week's experiment, collaboration, delivery or career action.

Use the [prompt pack](../../../LABLOOP-Master-Plan-v6.md#part-8--the-prompt-pack-copy-paste-fill-the-brackets): P1 explanation ladder, P2 concept-to-project bridge and P3 quiz. Coding practice belongs within the allocated study/build block. Where the source asks for a favorable scientific result, substitute an honest measured comparison as explained below.

### Founder/scientist paper

Select one verified founder/scientific-lead paper relevant to this week's domain. Use [P11](../../../LABLOOP-Master-Plan-v6.md#part-8--the-prompt-pack-copy-paste-fill-the-brackets); save the question, method, numerical result with context, data workflow, three author questions and one connection sentence in founder-paper.md. Keep abstract-only access limitations explicit. On source weeks with no study, prioritize the commercial/submission task and log any skipped digest.

## Artifact contracts

These filenames are outputs to prepare during this week's execution; this scaffold does not claim they already exist. Drafts and measured results have different states. Technical code/data stay in the canonical project repository and are referenced from these coordinating files.

| Artifact | Required content / acceptance | Primary responsibility |
|---|---|---|
| `deviation-workflow.md` | Connect a batchlens alarm and relevant SOP to a deviation draft with a visible human-review state and supporting evidence. Acceptance: Prepare a reproducible labdocs release with one measured local-hardware benchmark and a visible human-review step. | Model assists; Peter checks and owns the outcome |
| `hardware-benchmark.csv` | Benchmark the available mini PC, RTX 3050 and permitted cloud comparator on identical cases, logging accuracy, latency, memory and measured costs. Acceptance: Actual device specs, settings and sample counts are given; unavailable hardware is marked untested. | Model assists; Peter checks and owns the outcome |
| `labdocs-release-checklist.md` | Package labdocs v0.1/Z6, reproduce the benchmark and prepare deployment/data-flow documentation. Acceptance: Fake mode and a clean local reproduction work; release/deposit status is evidenced. | Model assists; Peter checks and owns the outcome |
| `study-notes.md` | Selected exact free resources; bounded lesson/exercise; separate solution; quiz and grading rubric; Peter's answers and gaps when executed | Model prepares; Peter learns |
| `founder-paper.md` | Verified source and P11 digest; authentic question and connection sentence; access limitations | Model assists; Peter checks |
| `branding-pack.md` | Wednesday note, Sunday build log, X adaptation, figure/caption/alt text and the week's special asset; each claim linked to real proof | Model drafts; Peter owns voice/public claims |
| `opportunity-actions.md` | Qualified target/role, source/date, ladder stage, next action, message/interview/proposal draft and actual status | Model prepares; Peter owns external relationships |
| `evidence.md` | Actual paths/URLs, versions, checks/metrics, preparation versus execution state and external receipts when applicable | Updated after each deliverable |
| `review.md` | Checklist, learning assessment, gate status, shortfalls, next actions and carryover | Peter and reviewing model |

During preparation, future measured tables get column definitions, input requirements and run instructions with PENDING status. During execution, replace pending values only with measured outputs. Do not create realistic-looking fake evidence.

## Branding and opportunity execution brief

Branding: Prepare Medium deep dive 5, release post and 60-second demo; distinguish confidentiality design from compliance claims.

Opportunity action: Show the benchmark to one qualified QA or employer contact and ask which deployment constraint matters.

Use [career asset contracts](../../CAREER-ASSETS.md). Publish at most the agreed cadence; one figure and one supported number or admitted failure can support multiple drafts. In long-form weeks, prepare a 1,500–2,500-word article from existing evidence within the build/buffer allocation. In release/demo weeks, prepare a 60-second script: problem, input, command/action, result, limitation and proof link.

Verify individuals, jobs and affiliations at execution time. The [GridX list](../../../GridX%20Startups.csv) and v4 company map are research seeds, not current facts. Do not reveal named company weaknesses or employer/client confidential information. Keep drafted/sent/replied/booked/held statuses separate. The planning request alone does not authorize external messages or publication; honor explicit authorization in the execution session.

## Quality risks and week-specific constraints

Do not repeat the inherited USD 300 hardware claim as current pricing. No client records go to cloud comparators without an applicable data-use basis and authorization.

Apply the root scientific evidence contract: provenance; meaningful independent splits; no future-data leakage; baseline comparison; actual denominators/uncertainty; failed cases; human review where required. State whether data are simulated, public experimental, synthetic or partner-provided.

Keep source gates intact, and log scope/time conflicts in review. Missing people, money, access or results must not be replaced with invented evidence. Reduce optional polish first. A specific essential external dependency stays pending while independent preparation continues.

## Completion and gate review

This is an enabling week. Its deliverables feed the next scheduled gate: 36. Complete the acceptance checklist below; do not promote reputation from a draft.

- [ ] Monday artifact satisfies: Prepare a reproducible labdocs release with one measured local-hardware benchmark and a visible human-review step.
- [ ] Wednesday artifact satisfies: Actual device specs, settings and sample counts are given; unavailable hardware is marked untested.
- [ ] Friday artifact satisfies: Fake mode and a clean local reproduction work; release/deposit status is evidenced.
- [ ] Study pack is prepared; Peter's actual learning/quiz result is recorded separately.
- [ ] Branding and opportunity drafts use supported claims and the correct external-action state.
- [ ] Reproduction or document checks are recorded with file/version references.
- [ ] This week's special gate, if any, has real evidence or remains explicitly pending.
- [ ] Review, root progress/log and the next physical action are updated.

## Minimum viable week and recovery

Expanded minimum derived from the source goal: Prepare a reproducible labdocs release with one measured local-hardware benchmark and a visible human-review step.

Operational first step if stalled: open `deviation-workflow.md`, write the required inputs and produce the smallest checkable example in ten minutes. If a more urgent missing gate dependency controls the week, use the source minimum above.

If the full week does not fit, use [P14](../../../LABLOOP-Master-Plan-v6.md#part-8--the-prompt-pack-copy-paste-fill-the-brackets): retain one gate-critical deliverable and one directly supporting study exercise; record what is skipped versus moved. Do not mark the original full gate passed merely because the minimum was completed. After a missed week, reforecast from actual evidence and avoid a second unexamined lost week.

## Handoff to the next model

In review, state exactly what exists, what was verified, what Peter can now explain, which external events remain pending, where the canonical code/data live, and the next file/function or draft paragraph to touch. Link each fact to evidence. Carry scientific assumptions, split definitions and rights constraints forward explicitly.

## Ready-to-copy model prompt

```text
Prepare Week 35 of this LABLOOP execution plan.
Read execution-plan/specs.md, execution-plan/DECISIONS.md,
execution-plan/GATES.md and
execution-plan/weeks/week-35-labdocs-release-and-local-benchmark/specs.md, commitment.md, evidence.md and review.md.
Read prior prerequisite reviews and inspect actual repository/data state.
Use v5 as the governing sequence, the v6 Week 35 chapter
(LABLOOP-Master-Plan-v6.md) as the deeper walkthrough, and v4 only for
retained details.
Produce the full local preparation pack and the exact week-specific files named
in the artifact table. Give me a bounded lesson with exercises/answer key,
daily physical actions, technical runbook or draft, branding drafts and
career/commercial actions. Keep the total to 600 minutes.
Separate prepared artifacts from measured results and my learning completion.
Verify sources and do not invent metrics, citations, papers, people or outcomes.
Do not execute external communications, publication or spending unless the
current session already authorizes the specific action.
Finish by updating evidence/review and TODAY with the next physical action.
```

## Preserved original v5 weekly brief

v6 expands this row into a full brief, with the gate and output unchanged, inside [v6 · Week 35 · labdocs, part 3](../../../LABLOOP-Master-Plan-v6.md#week-35--labdocs-part-3).
The following is source planning text, not a claim of completion. Apply the explicit evidence corrections in this specification and DECISIONS.md.

| Week | Goal | Study (Tue) | Build (Mon/Wed/Fri) | Output |
|---|---|---|---|---|
| 35 | labdocs, part 3 | Privacy basics | Deviation drafting + on-prem benchmark table (v4 weeks 16-17) | `labdocs v0.1`, Z6, M5 deep dive |