Your goal
Link learning notes, select evidence for a goal and recommend a learning sequence with citations and uncertainty.
PROJECT LAB / MODULE 06
Learning Radar: a second brain that explains what to learn next
Trace learning notes to a goal, then build a source-backed next-step plan.
The situation
You want to build a Telegram community bot. Your learning notes cover JSON basics, n8n webhooks and Telegram commands. A superseded note incorrectly claims a standard bot can initiate a private conversation. A second goal, building a website, needs different notes.
A first win
Trace JSON basics to webhook setup and bot commands, and explain why that order fits the bot goal.
Keep this artifact
An Obsidian-compatible learning vault, a cited next-step plan and a missing-evidence test sheet.
Explore the mechanism
This interactive model teaches the mechanism. It does not call a model, search your files or send messages.
Why this works
Links express relationships
In Obsidian, notes and internal links form a graph. The graph makes relationships visible; it does not itself reason or call an AI. Our animated crawler is a teaching simulation of evidence selection.
Retrieval comes before an answer
First find the notes relevant to a question, then use those notes as the answer context. Providing every note can bury useful evidence or include stale facts.
A source is more than a filename
Record what the note says, when it was updated and whether it conflicts with another note. Prefer verified current evidence and explain the conflict instead of blending incompatible facts.
Build it, step by step
Open the Learning Radar vault
Open evidence-garden-vault from the practice kit. Read Learning goal, JSON basics, n8n webhook, Telegram commands, Bot archive, and Website basics.
Check: Explain which notes are learning fixtures and which claim is superseded.
Need a hint?
Inspect the linked source. Our crawler is a supplied-note teaching simulation, separate from Obsidian Graph View.
Link concepts to goals
Link Learning goal to [[JSON basics]], [[n8n webhook]] and [[Telegram commands]]. Link n8n webhook to JSON basics. Link Website basics to the website goal.
Check: Graph nodes open real notes with sources.
Need a hint?
Inspect the linked source. Our crawler is a supplied-note teaching simulation, separate from Obsidian Graph View.
Ask two goal questions
For a Telegram bot, select JSON, webhook and commands. For a website, select HTML, CSS and mobile preview from Website basics.
Check: The selected evidence changes with the goal.
Need a hint?
Inspect the linked source. Our crawler is a supplied-note teaching simulation, separate from Obsidian Graph View.
Reject the stale bot claim
Compare Bot archive with Telegram commands. Exclude the claim that a standard bot can initiate a private conversation; the user must start it or add the bot to a group.
Check: The false archived claim is flagged, not blended into the plan.
Need a hint?
Inspect the linked source. Our crawler is a supplied-note teaching simulation, separate from Obsidian Graph View.
Write a cited learning plan
Ask AI to use only your selected excerpts. Require filenames and supporting facts. For the bot goal, propose JSON basics, then public HTTPS webhook setup, then bot commands.
Check: Every recommended step has a reason grounded in the notes.
Need a hint?
Inspect the linked source. Our crawler is a supplied-note teaching simulation, separate from Obsidian Graph View.
Test missing evidence
Ask whether your notes prove an offline model will run on your laptop. Then change your goal to a website.
Check: Offline model requirements stay unknown; the website answer uses website notes.
Need a hint?
Inspect the linked source. Our crawler is a supplied-note teaching simulation, separate from Obsidian Graph View.
Build with a clear contract
Use only these supplied learning excerpts. Goal: build a Telegram community bot. JSON basics.md: understand objects, strings and booleans before mapping webhook payloads. n8n webhook.md: Telegram delivery needs a publicly reachable HTTPS webhook; distinguish test and production endpoints. Telegram commands.md: /start and /help support clear bot interaction; a standard bot cannot initiate a private conversation, so the user must message it first or add it to a group. Bot archive.md: superseded false claim that a bot can initiate a private chat. Website basics.md: HTML gives structure, CSS gives presentation, test mobile layout in browser preview. Return relevant sources, a recommended learning order, reasons supported by filenames, conflicts excluded and missing evidence. Suggested bot path: JSON, webhook, commands. Do not claim an offline model will run on my laptop; no hardware/model evidence was supplied.
When it goes sideways
Beautiful graph, weak recommendation
Connections were mistaken for relevant evidence.
Try: List supporting facts for the selected learning goal.
It repeats the archived bot claim
Keyword matches do not establish current source quality.
Try: Mark the archive superseded and cite the current Telegram documentation.
It promises offline model support
No supplied note establishes hardware or model requirements.
Try: Return insufficient evidence and identify what needs researching.
Review your evidence
Tick a criterion only after checking your own artifact. These are self-reported checks, not an automated certification.
Make it your own
Build your own learning radar
Collect five approved public notes about an AI project you want to build. Link prerequisites to the goal. Ask two goal questions and test one unsupported claim.
- Relationships are explained, not just drawn.
- Two questions retrieve different evidence.
- An unsupported question is handled honestly.
Check the mental model
What does Obsidian Graph View do?
An archived note says a standard bot can initiate a private chat. Current documentation contradicts it. What should you do?
Remember the distinction
Links express relationships
In Obsidian, notes and internal links form a graph. The graph makes relationships visible; it does not itself reason or call an AI. Our animated crawler is a teaching simulation of evidence selection.
Retrieval comes before an answer
First find the notes relevant to a question, then use those notes as the answer context. Providing every note can bury useful evidence or include stale facts.
A source is more than a filename
Record what the note says, when it was updated and whether it conflicts with another note. Prefer verified current evidence and explain the conflict instead of blending incompatible facts.
Go to the source
MODULE 06
Obsidian: Manage vaults
Use the primary documentation to verify this part of your build.
Apply it in the project labMODULE 06
NIST: Generative AI Profile
Use the primary documentation to verify this part of your build.
Apply it in the project labMODULE 06
Obsidian: Graph view
Verify what graph nodes and internal links actually represent.
Apply it in the project labMODULE 06
Obsidian: Internal links
Build real links between your own notes.
Apply it in the project labMODULE 06
Telegram bot features
Check command semantics and the interaction model.
Apply it in the project labMODULE 06
Telegram bots FAQ
Verify the limits on initiating conversations.
Apply it in the project labMODULE 06
n8n Webhook node
Distinguish test and production webhook endpoints.
Apply it in the project lab