Interactive Lab

Practice in short loops: checkpoint quiz, microtask decision, and competency progress tracking.

Checkpoint Quiz

Q1. Which output most clearly demonstrates module competency?

A measurable artifact linked to an explicit method A general reflection about interest in neuroscience A list of future goals without evidence

Competency is shown through measurable, method-linked evidence.

Q2. What should always accompany a technical claim in this curriculum?

A limitation or uncertainty statement A motivational quote A citation count

Every claim should include boundaries and uncertainty.

Q3. What is the best next step after identifying a gap in understanding?

Define a concrete practice task and verification criterion Skip to a harder module Ignore the gap if progress is slow

Progress improves when gaps become explicit practice targets.

Submit Quiz

Microtask Decision

Choose the action that best improves scientific reliability.

Record method, version, and decision rationale before sharing results Share results quickly and document details later Rely on memory for why decisions were made

Check Decision

Progress Tracker

State is saved locally in your browser for this module.

• Read capability target
• Complete studio activity
• Review assessment rubric
• Pass checkpoint quiz
• Complete microtask
• Complete annotation challenge

0% complete

Reset Progress

Annotation Challenge

Click the hotspot with the strongest evidence for the requested feature.

A B C

Selected hotspot: none

Check Annotation

Capability target

Implement an LLM-assisted patch-analysis workflow with verification gates, confidence labeling, and explicit human override policies.

Why this module matters

LLMs can accelerate triage and documentation, but unverified outputs can propagate errors quickly. Connectomics requires careful human-in-the-loop governance.

Concept set

1) Assistive, not autonomous

• Technical: LLMs should support prioritization, summarization, and protocol guidance, not final biological adjudication.
• Plain language: use LLMs to help, not to decide alone.
• Misconception guardrail: fluent output equals correct output.

2) Verification-first design

• Technical: every LLM output class should map to a verification method and acceptance threshold.
• Plain language: define how you will check answers before using them.
• Misconception guardrail: spot-checking only when output seems odd.

3) Auditability

• Technical: prompt versions, model versions, and decision logs are required for reproducibility.
• Plain language: keep records so you can explain what happened.
• Misconception guardrail: chat history alone is sufficient traceability.

Core workflow

1. Define candidate LLM tasks (triage, summary, QA aid).
2. Create prompt templates and expected output schema.
3. Add verification gates and human adjudication rules.
4. Pilot on small patch set and log failure patterns.
5. Refine prompts/policies before wider use.

60-minute tutorial run-of-show

1. 00:00-08:00 scope boundaries and failure examples.
2. 08:00-20:00 prompt template design.
3. 20:00-34:00 run sample outputs and score reliability.
4. 34:00-46:00 define verification and override rules.
5. 46:00-56:00 produce governance checklist.
6. 56:00-60:00 competency check.

Studio activity

Scenario: Build an LLM-assisted triage helper for proofreading queues.

Outputs

• prompt + schema pack,
• verification rubric,
• risk register and override policy.

Assessment rubric

• Minimum pass: clear task boundaries, verification logic, and logging fields.
• Strong performance: robust failure-mode handling and actionable governance plan.
• Failure modes: unbounded scope, no confidence policy, missing audit trail.

Teaching resources

• Module 14
• Technical Unit 08
• Connectome Quality tool

Quick practice prompt

For one LLM output type, define: acceptance threshold, verification method, and human override trigger.